Mixtral-2x12b ~ Very Experimental Architecture Choice By Self Evaluated Pruning Technique

added_tokens.json

@@ -1,4 +1,3 @@
 {
-  "<|im_end|>": 32000,
-  "<|im_start|>": 32001
+  "<pad>": 32000
 }

config.json

@@ -1,26 +1,34 @@
 {
   "_name_or_path": ".\\Mermaid\\",
   "architectures": [
-    "MistralForCausalLM"
+    "MixtralForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 5120,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 48,
-  "num_key_value_heads": 8,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 40,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 40,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.37.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32032
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "transformers_version": "4.37.2",
-  "use_cache": false
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
 }

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24758d06edf42d093e787b463fa2e7455c9b7816805cc5b7843d1494f246898e
+size 4915719208

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ed7263c00a34d152fb91cd823bddc3660e066197871b1d0bc86572f51071c1
+size 4996656336

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d2d627124232531b0f5d3b7c561d3dc1912f317078697c28a4f5420e74eccf
+size 4959956208

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b2148500e28f5e617391f7d416ce11a5fb159db1097afdbb8b44ded94a7079b
+size 4870847960

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eebbd9e259cca53975ee5cbd0398c4a19ee5deee21f875b5cb5317c8f35e4ddc
+size 4996656392

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d288f579c76c38b0a0b45c137f02716600ffed15f4aab4e99c742130195d6d48
+size 4959956224

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ef738498b727dd62574ceae9e447cc78f01a8c15a1b1aca21861e13af7a7b2
+size 611154616

model.safetensors.index.json

@@ -1,442 +1,374 @@
 {
   "metadata": {
-    "total_size": 21463572480
+    "total_size": 30310901760
   },
   "weight_map": {
-    "lm_head.weight": "model-00005-of-00005.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.42.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.42.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.43.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.43.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.44.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
-    "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.norm.weight": "model-00005-of-00005.safetensors"
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
   }
 }

special_tokens_map.json

@@ -2,21 +2,21 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
+    "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,7 +1,6 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -14,7 +13,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -22,40 +21,28 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "32000": {
-      "content": "<|im_end|>",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "legacy": true,
+  "eos_token": "</s>",
+  "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": "<s>",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false,
-  "use_fast": true
+  "use_default_system_prompt": false
 }