Upload folder using huggingface_hub

.gitattributes

@@ -55,3 +55,5 @@ checkpoint-139000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-140000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-149000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-150000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-155000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-156000/trainer_state.json filter=lfs diff=lfs merge=lfs -text

checkpoint-155000/config.json

@@ -0,0 +1,79 @@
+{
+  "ar_steps": 1,
+  "architectures": [
+    "DiffVLMDiffusion"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "condition_layer": -1,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "img_cross_attention_dim": 2048,
+  "img_diffuser_depth": 1,
+  "img_ffn_dim_multiplier": null,
+  "img_hidden_size": 1536,
+  "img_multiple_of": 256,
+  "img_norm_eps": 1e-05,
+  "img_num_attention_heads": 12,
+  "img_num_kv_heads": 12,
+  "img_qk_norm": true,
+  "in_channels": 32,
+  "initializer_range": 0.02,
+  "inject_img_diffuser": false,
+  "input_size": 32,
+  "intermediate_size": 8960,
+  "layer_group_size": 7,
+  "layerwise_start_idx": 0,
+  "lora_alpha": 16,
+  "lora_bias": "none",
+  "lora_dropout": 0.05,
+  "lora_enable": false,
+  "lora_r": 64,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "non_linearity": 1,
+  "norm_elementwise_affine": true,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "patch_size": 1,
+  "repa_coeff": 0.5,
+  "repa_layers": null,
+  "repa_shared": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sample_size": 128,
+  "sampling_steps": 28,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "use_repa": false,
+  "use_residual_attn": false,
+  "use_sliding_window": false,
+  "vae_path": "mit-han-lab/dc-ae-f32c32-in-1.0-diffusers",
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

checkpoint-155000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.47.0"
+}

checkpoint-155000/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77f0dadf4c7508f044be2939ce365e43c0ccd20149ff302a73daedd33250bb0
+size 4980624888

checkpoint-155000/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705d402d201525f8ff9249e5b945c8c28b7b927b006a4a3554b26b962ec99744
+size 1918602176

checkpoint-155000/model.safetensors.index.json

@@ -0,0 +1,1167 @@
+{
+  "metadata": {
+    "total_size": 6899096400
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "img2text.bias": "model-00001-of-00002.safetensors",
+    "img2text.weight": "model-00001-of-00002.safetensors",
+    "img_norm_out.linear_1.bias": "model-00001-of-00002.safetensors",
+    "img_norm_out.linear_1.weight": "model-00001-of-00002.safetensors",
+    "img_norm_out.linear_2.bias": "model-00001-of-00002.safetensors",
+    "img_norm_out.linear_2.weight": "model-00001-of-00002.safetensors",
+    "layers.0.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.0.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.1.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.10.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.11.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.12.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.13.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.14.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.15.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.16.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.17.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.18.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.19.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.2.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.20.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.21.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.22.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.23.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.24.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.25.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.26.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.27.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.3.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.4.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.5.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.6.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.7.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.8.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.9.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "norm.weight": "model-00002-of-00002.safetensors",
+    "patch_embedder.proj.bias": "model-00001-of-00002.safetensors",
+    "patch_embedder.proj.weight": "model-00001-of-00002.safetensors",
+    "t_embedder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors",
+    "t_embedder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors",
+    "t_embedder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors",
+    "t_embedder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vae.decoder.conv_in.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.conv_in.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.conv_out.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.conv_out.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.0.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.0.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.0.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.0.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.0.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.0.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.0.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.0.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.conv_in.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.conv_in.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.conv_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.conv_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.0.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.0.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.0.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.0.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.0.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.1.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.1.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.1.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.1.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.1.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.2.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.2.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.2.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.2.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.2.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.3.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.3.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.3.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.3.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.3.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.4.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.4.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.0.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.0.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.0.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.0.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.0.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.1.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.1.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.1.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.1.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.1.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.2.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.2.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.2.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.2.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.2.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.3.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.3.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.3.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.3.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.3.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.4.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.4.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.4.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.4.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.4.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.5.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.5.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.5.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.5.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.5.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.6.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.6.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.6.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.6.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.6.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.7.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.7.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.7.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.7.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.7.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.8.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.8.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.2.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.2.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.2.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.2.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-155000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa260d9ecf8babbab8bf588c114fa03d4df6bbee47eb454bb90acb714082025
+size 7453283710

checkpoint-155000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9209c784f3384a98706ef43913e328127c8c6f76db135bfa35748a94daaa05b5
+size 16389

checkpoint-155000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1759d0755ca24a8d01ebad0a009e51deacad3798824e801bcdb4263b8264952b
+size 16389

checkpoint-155000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ea8d5562aa6940c421075824683e578a836368c9ed6df2b9ca7f2c504f5d7a
+size 16389

checkpoint-155000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f17f62eea2a83e94e28bb4f23576d3ae19591013e4b33a5d005c97eea9c48ce
+size 16389

checkpoint-155000/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b3973f2f490b4e665446c64c307cca360a4875023a56967839f260f9745a64
+size 16389

checkpoint-155000/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7f6f0310e3e1bd29179f97a6acbe0173bae4ac350ce19d3eacb6801cb18ca5
+size 16389

checkpoint-155000/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f2fc8a8b5feb6a4cdec954fa2ce6a62ed03804a92fb3c879587473b768e8ef
+size 16389

checkpoint-155000/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9a60f83b8ed3334825b40e01b4ec170c0a9c38ac2d67bbe188ba4b8ae434a5
+size 16389

checkpoint-155000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1e80ac111cad5451d2461f79ee99233275bafbd9b0b478de09d41e3bc38ea0
+size 1465

checkpoint-155000/trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e057d00b03f549764f00e170d3ce3e7f49d9ca9bd55f67c4a587c8a7d11a25
+size 23877994

checkpoint-155000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec2e60110677df269e5daeda4058c6b6559331fe735564dea9db41f6245b788
+size 6417

checkpoint-156000/config.json

@@ -0,0 +1,79 @@
+{
+  "ar_steps": 1,
+  "architectures": [
+    "DiffVLMDiffusion"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "condition_layer": -1,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "img_cross_attention_dim": 2048,
+  "img_diffuser_depth": 1,
+  "img_ffn_dim_multiplier": null,
+  "img_hidden_size": 1536,
+  "img_multiple_of": 256,
+  "img_norm_eps": 1e-05,
+  "img_num_attention_heads": 12,
+  "img_num_kv_heads": 12,
+  "img_qk_norm": true,
+  "in_channels": 32,
+  "initializer_range": 0.02,
+  "inject_img_diffuser": false,
+  "input_size": 32,
+  "intermediate_size": 8960,
+  "layer_group_size": 7,
+  "layerwise_start_idx": 0,
+  "lora_alpha": 16,
+  "lora_bias": "none",
+  "lora_dropout": 0.05,
+  "lora_enable": false,
+  "lora_r": 64,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "non_linearity": 1,
+  "norm_elementwise_affine": true,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "patch_size": 1,
+  "repa_coeff": 0.5,
+  "repa_layers": null,
+  "repa_shared": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sample_size": 128,
+  "sampling_steps": 28,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "use_repa": false,
+  "use_residual_attn": false,
+  "use_sliding_window": false,
+  "vae_path": "mit-han-lab/dc-ae-f32c32-in-1.0-diffusers",
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

checkpoint-156000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.47.0"
+}

checkpoint-156000/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b5ce36a10aba3bd01f5709646d5f44d1a93d5cfdd0a4a2e35091301b42cec66
+size 4980624888

checkpoint-156000/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705d402d201525f8ff9249e5b945c8c28b7b927b006a4a3554b26b962ec99744
+size 1918602176

checkpoint-156000/model.safetensors.index.json

@@ -0,0 +1,1167 @@
+{
+  "metadata": {
+    "total_size": 6899096400
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "img2text.bias": "model-00001-of-00002.safetensors",
+    "img2text.weight": "model-00001-of-00002.safetensors",
+    "img_norm_out.linear_1.bias": "model-00001-of-00002.safetensors",
+    "img_norm_out.linear_1.weight": "model-00001-of-00002.safetensors",
+    "img_norm_out.linear_2.bias": "model-00001-of-00002.safetensors",
+    "img_norm_out.linear_2.weight": "model-00001-of-00002.safetensors",
+    "layers.0.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.0.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.1.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.10.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.11.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.12.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.13.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.14.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.15.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.16.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.17.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.18.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.19.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.2.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.20.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.21.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.22.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.23.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.24.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.25.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.26.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.27.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.3.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.4.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.5.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.6.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.7.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.8.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
+    "layers.9.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
+    "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "norm.weight": "model-00002-of-00002.safetensors",
+    "patch_embedder.proj.bias": "model-00001-of-00002.safetensors",
+    "patch_embedder.proj.weight": "model-00001-of-00002.safetensors",
+    "t_embedder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors",
+    "t_embedder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors",
+    "t_embedder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors",
+    "t_embedder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "txt_layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "txt_layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "txt_layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vae.decoder.conv_in.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.conv_in.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.conv_out.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.conv_out.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.0.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.0.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.1.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.2.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.3.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.4.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.1.5.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.0.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.0.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.1.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.10.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.2.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.3.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.4.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.5.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.6.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.7.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.8.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.norm.running_mean": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.norm.running_var": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.2.9.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.0.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.0.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.3.2.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.0.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.0.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.4.2.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.decoder.up_blocks.5.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.conv_in.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.conv_in.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.conv_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.conv_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.0.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.0.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.0.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.0.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.0.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.1.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.1.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.1.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.1.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.1.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.2.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.2.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.2.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.2.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.2.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.3.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.3.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.3.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.3.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.3.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.4.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.1.4.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.0.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.0.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.0.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.0.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.0.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.1.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.1.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.1.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.1.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.1.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.2.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.2.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.2.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.2.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.2.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.3.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.3.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.3.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.3.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.3.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.4.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.4.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.4.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.4.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.4.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.5.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.5.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.5.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.5.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.5.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.6.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.6.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.6.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.6.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.6.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.7.conv1.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.7.conv1.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.7.conv2.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.7.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.7.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.8.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.2.8.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.2.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.3.2.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.2.conv.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.4.2.conv.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
+    "vae.encoder.down_blocks.5.1.conv_out.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-156000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c07595c32642f210c1448d00a1ce2fad01cc0e7e8376834fc8ab0be37eb73d
+size 7453283710

checkpoint-156000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f85108295823c9ab8626365098a07c04ef55e0b567138c043551a7009fadd3
+size 16389

checkpoint-156000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51269594efdccdfe032b64501cfe221cd58b811e26d8bb72355f5f5fab4b82e
+size 16389

checkpoint-156000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78aa0479089ffffa4e43f30c011ba52c94103940542cd00c33e89a1dd451ee89
+size 16389

checkpoint-156000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1de6489edafff7c1dbb551b14986e48f784440daf1d0ee52a08c29fedbf97f
+size 16389

checkpoint-156000/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430cd80656a9bf3a5e8f29140ed1e12c8d67696bd9bcde80ac519c2095f13aad
+size 16389

checkpoint-156000/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8e690bcc698d81ffee35e2bcd18e314f72f0c24a49ad5199693c568af67755
+size 16389

checkpoint-156000/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc055551feb13cf24593ed47fa64053628a827e02090a395dc55367320884b23
+size 16389

checkpoint-156000/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8301c4dff2855edeca7af503c19ea03a4c64502e5048a5b196dfe24b7a61dd
+size 16389

checkpoint-156000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f672433f21bafcec3a047599d50ae357124b6c7b52c8225f246c94bfa4c1ef8
+size 1465

checkpoint-156000/trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7938c12cf2799180f6a1c4eac688c76c2aface319d711c6b5fd9e1dbc5daacc6
+size 24033181

checkpoint-156000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6967396f6d8b8fb7e9af46b441fa882f9c15aedcfefa1a6b97093867641494a
+size 6353