Upload folder using huggingface_hub

README.md

@@ -10,13 +10,14 @@ base_model:
 
 ![lidar_map](statics/sail.png)
 
-SAIL-VL is a state-of-the-art vision-language model (VLM) developed by the Bytedance Douyin Content Team. The goal of SAIL-VL is to develope a high-performance vision language model that facilitates deployment on mobile devices and ensures accessibility and affordability for a broad audience. Through careful tuning of data and training recipes, SAIL-VL demonstrates that even a small VLM can benefit significantly from data scaling. 
+SAIL-VL is a state-of-the-art vision-language model (VLM) developed by the Bytedance Douyin Content Team. The goal of SAIL-VL is to develope a high-performance vision language model that facilitates deployment on mobile devices and ensures accessibility and affordability for a broad audience. Through careful tuning of data and training recipes, SAIL-VL demonstrates that even a small VLM can benefit significantly from data scaling.
 
-SAIL-VL V1.5 is the brand new version of our model, which incorporates advanced techniques to achieve higher performance. For visual encoding, we use the stronger AIM-V2 ViT as our vision encoder, introduce the progressive training strategy to warmup and a visual token scaling strategy during inference. During training, we introduce an adaptive stream packing strategy to support higher throughput and longer sequences. Finally, we add more conversation and reasoning data, filter out noisy data and add a new training stage for videos. With all these updates, our model outperforms recent SoTA models of comparable sizes, InternVL-3-2B, Ovis2-2B and even Qwen2.5-VL-3B.
+SAIL-VL-V1.5-pro-8B is the brand new version of our model based on SAIL-VL-v1.5-8B, which incorporates advanced techniques to achieve higher performance. For visual encoding, we use the stronger AIM-V2 ViT as our vision encoder. During training, we introduce an adaptive stream packing strategy to support higher throughput and longer sequences. Finally, we add more conversation and reasoning data, filter out noisy data and add a new training stage for videos. With all these updates, our model outperforms recent SoTA models of comparable sizes, InternVL-2.5-8B, Qwen2.5-VL-7B, Ovis2-8B and recently released InternVL-3-8B.
 
 Please enjoy our model and feel free to contact us for any question or opportunity.
 
 ## News🚀🚀🚀
+- 2024-4-22: 📖 We released the SAIL-VL-1.5-8B-pro at [🤗SAIL-VL-1.5-8B-pro](https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1.5-8B-pro)
 - 2024-4-16: 📖 We released our powerful v1.5 series models, check out at [🤗SAIL-VL-1.5-2B](https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1.5-2B)  [🤗SAIL-VL-1.5-8B](https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1.5-8B) ~
 - 2024-2-19: 📖 We released our 8B model, check out at [🤗SAIL-VL-8B](https://huggingface.co/BytedanceDouyinContent/SAIL-VL-8B) ~
 - 2024-1-10: 📖 We released our paper on Arxiv: [Scalable Vision Language Model Training via High Quality Data Curation

added_tokens.json

@@ -1,33 +1,3 @@
-{
-  "</box>": 151673,
-  "</img>": 151666,
-  "</quad>": 151669,
-  "</ref>": 151671,
-  "</tool_call>": 151658,
-  "<IMG_CONTEXT>": 151667,
-  "<box>": 151672,
-  "<img>": 151665,
-  "<quad>": 151668,
-  "<ref>": 151670,
-  "<tool_call>": 151657,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66b6bc948dec3421f01a8986f31632cf8d556aaa89f7b39c183b3dd4b5b2c83
+size 790

config.json

@@ -1,195 +1,3 @@
-{
-  "_commit_hash": null,
-  "architectures": [
-    "SailVLModel"
-  ],
-  "auto_map": {
-    "AutoConfig": "configuration_sailvl.SailVLConfig",
-    "AutoModel": "modeling_sailvl.SailVLModel",
-    "AutoModelForCausalLM": "modeling_sailvl.SailVLModel"
-  },
-
-    "downsample_ratio": 0.5,
-    "dynamic_image_size": true,
-    "force_image_size": 448,
-    "llm_config": {
-      "_name_or_path": "/tmp/huggingface_cache/Qwen2.5-7B-Instruct",
-      "add_cross_attention": false,
-      "architectures": [
-        "Qwen2ForCausalLM"
-      ],
-      "attn_implementation": "flash_attention_2",
-      "attention_dropout": 0.0,
-      "bad_words_ids": null,
-      "begin_suppress_tokens": null,
-      "bos_token_id": 151643,
-      "chunk_size_feed_forward": 0,
-      "cross_attention_hidden_size": null,
-      "decoder_start_token_id": null,
-      "diversity_penalty": 0.0,
-      "do_sample": false,
-      "early_stopping": false,
-      "encoder_no_repeat_ngram_size": 0,
-      "eos_token_id": 151645,
-      "exponential_decay_length_penalty": null,
-      "finetuning_task": null,
-      "forced_bos_token_id": null,
-      "forced_eos_token_id": null,
-      "hidden_act": "silu",
-      "hidden_size": 3584,
-      "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-      },
-      "initializer_range": 0.02,
-      "intermediate_size": 18944,
-      "is_decoder": false,
-      "is_encoder_decoder": false,
-      "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-      },
-      "length_penalty": 1.0,
-      "max_length": 20,
-      "max_position_embeddings": 32768,
-      "max_window_layers": 28,
-      "min_length": 0,
-      "model_type": "qwen2",
-      "no_repeat_ngram_size": 0,
-      "num_attention_heads": 28,
-      "num_beam_groups": 1,
-      "num_beams": 1,
-      "num_hidden_layers": 28,
-      "num_key_value_heads": 4,
-      "num_return_sequences": 1,
-      "output_attentions": false,
-      "output_hidden_states": false,
-      "output_scores": false,
-      "pad_token_id": 151643,
-      "prefix": null,
-      "problem_type": null,
-      "pruned_heads": {},
-      "remove_invalid_values": false,
-      "repetition_penalty": 1.0,
-      "return_dict": true,
-      "return_dict_in_generate": false,
-      "rms_norm_eps": 1e-06,
-      "rope_scaling": null,
-      "rope_theta": 1000000.0,
-      "sep_token_id": null,
-      "sliding_window": null,
-      "suppress_tokens": null,
-      "task_specific_params": null,
-      "temperature": 1.0,
-      "tf_legacy_loss": false,
-      "tie_encoder_decoder": false,
-      "tie_word_embeddings": false,
-      "tokenizer_class": null,
-      "top_k": 50,
-      "top_p": 1.0,
-      "torch_dtype": "bfloat16",
-      "torchscript": false,
-      "transformers_version": "4.45.1",
-      "typical_p": 1.0,
-      "use_bfloat16": false,
-      "use_cache": true,
-      "use_sliding_window": false,
-      "vocab_size": 152064
-    },
-    "max_dynamic_patch": 12,
-    "min_dynamic_patch": 1,
-    "model_type": "internvl_chat",
-    "pad2square": false,
-    "ps_version": "v2",
-    "select_layer": -1,
-    "template": "sailvl-chat",
-    "torch_dtype": "bfloat16",
-    "transformers_version": null,
-    "use_backbone_lora": 0,
-    "use_llm_lora": 0,
-    "use_thumbnail": true,
-    "vision_config": {
-      "_name_or_path": "/tmp/huggingface_cache/ovis-4B-aimv2-ViT-huge-patch14-448",
-      "add_cross_attention": false,
-      "architectures": [
-        "AIMv2Model"
-      ],
-      "attention_dropout": 0.0,
-      "auto_map": {
-        "AutoConfig": "configuration_aimv2.AIMv2Config",
-        "AutoModel": "modeling_aimv2.AIMv2Model",
-        "FlaxAutoModel": "modeling_flax_aimv2.FlaxAIMv2Model"
-      },
-      "bad_words_ids": null,
-      "begin_suppress_tokens": null,
-      "bos_token_id": null,
-      "chunk_size_feed_forward": 0,
-      "cross_attention_hidden_size": null,
-      "decoder_start_token_id": null,
-      "diversity_penalty": 0.0,
-      "do_sample": false,
-      "early_stopping": false,
-      "encoder_no_repeat_ngram_size": 0,
-      "eos_token_id": null,
-      "exponential_decay_length_penalty": null,
-      "finetuning_task": null,
-      "forced_bos_token_id": null,
-      "forced_eos_token_id": null,
-      "hidden_size": 1536,
-      "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-      },
-      "image_size": 448,
-      "intermediate_size": 4096,
-      "is_decoder": false,
-      "is_encoder_decoder": false,
-      "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-      },
-      "length_penalty": 1.0,
-      "max_length": 20,
-      "min_length": 0,
-      "model_type": "aimv2",
-      "no_repeat_ngram_size": 0,
-      "num_attention_heads": 12,
-      "num_beam_groups": 1,
-      "num_beams": 1,
-      "num_channels": 3,
-      "num_hidden_layers": 24,
-      "num_return_sequences": 1,
-      "output_attentions": false,
-      "output_hidden_states": false,
-      "output_scores": false,
-      "pad_token_id": null,
-      "patch_size": 14,
-      "prefix": null,
-      "problem_type": null,
-      "projection_dropout": 0.0,
-      "pruned_heads": {},
-      "qkv_bias": false,
-      "remove_invalid_values": false,
-      "repetition_penalty": 1.0,
-      "return_dict": true,
-      "return_dict_in_generate": false,
-      "rms_norm_eps": 1e-05,
-      "sep_token_id": null,
-      "suppress_tokens": null,
-      "task_specific_params": null,
-      "temperature": 1.0,
-      "tf_legacy_loss": false,
-      "tie_encoder_decoder": false,
-      "tie_word_embeddings": true,
-      "tokenizer_class": null,
-      "top_k": 50,
-      "top_p": 1.0,
-      "torch_dtype": "bfloat16",
-      "torchscript": false,
-      "transformers_version": "4.45.1",
-      "typical_p": 1.0,
-      "use_bfloat16": false,
-      "use_bias": false
-    }
-  }
-  
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a870d00e202374c4af836dc3d09ebd364b7a2df865455d412e33d203954ee1
+size 5685

generation_config.json

@@ -1,4 +1,3 @@
-{
-  "_from_model_config": true,
-  "transformers_version": "4.37.2"
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d76e6b0a3b31f0de871f8f5b968957e0532fd9b17214aabf151da4bdbe1804
+size 69

model.safetensors.index.json

@@ -1,525 +1,3 @@
-{
-  "metadata": {
-    "total_size": 16665065472
-  },
-  "weight_map": {
-    "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
-    "mlp1.0.bias": "model-00004-of-00004.safetensors",
-    "mlp1.0.weight": "model-00004-of-00004.safetensors",
-    "mlp1.1.bias": "model-00004-of-00004.safetensors",
-    "mlp1.1.weight": "model-00004-of-00004.safetensors",
-    "mlp1.3.bias": "model-00004-of-00004.safetensors",
-    "mlp1.3.weight": "model-00004-of-00004.safetensors",
-    "vision_model.preprocessor.patchifier.norm.weight": "model-00001-of-00004.safetensors",
-    "vision_model.preprocessor.patchifier.proj.bias": "model-00001-of-00004.safetensors",
-    "vision_model.preprocessor.patchifier.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.preprocessor.pos_embed": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.0.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.0.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.0.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.1.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.1.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.1.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.10.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.10.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.10.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.11.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.11.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.11.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.12.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.12.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.12.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.13.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.13.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.13.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.14.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.14.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.14.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.15.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.15.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.15.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.16.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.16.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.16.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.17.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.17.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.17.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.18.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.18.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.18.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.19.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.19.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.19.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.2.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.2.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.2.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.20.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.20.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.20.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.21.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.21.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.21.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.22.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.22.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.22.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.23.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.23.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.23.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.3.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.3.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.3.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.4.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.4.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.4.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.5.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.5.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.5.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.6.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.6.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.6.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.7.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.7.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.7.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.8.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.8.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.8.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.9.mlp.fc3.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.9.norm_1.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.blocks.9.norm_2.weight": "model-00001-of-00004.safetensors",
-    "vision_model.trunk.post_trunk_norm.weight": "model-00001-of-00004.safetensors"
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e8fef2586a0165bc48af24fdfb636a3dcbea9b7fa69a7df8ea7904aec4b2e0
+size 48181

special_tokens_map.json

@@ -1,31 +1,3 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
+size 613

tokenizer_config.json

@@ -1,279 +1,3 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<img>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151666": {
-      "content": "</img>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151667": {
-      "content": "<IMG_CONTEXT>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151668": {
-      "content": "<quad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151669": {
-      "content": "</quad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151670": {
-      "content": "<ref>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151671": {
-      "content": "</ref>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151672": {
-      "content": "<box>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151673": {
-      "content": "</box>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cefbcb546724024b3f8e5f24e14f5e1ea19cca39e09495255bfd8d4110cc7d5
+size 8868