Upload folder using huggingface_hub

config.json

@@ -21,12 +21,12 @@
   "num_hidden_layers": 42,
   "num_key_value_heads": 8,
   "pad_token_id": 0,
-  "query_pre_attn_scalar": 224,
+  "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "sliding_window_size": 4096,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.42.3",
   "use_cache": true,
   "vocab_size": 256000

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c42f907f7ed6654e1cbbaaaaafe7f71ad09e0e86eef9d356191c2a4ea968dd1
+size 1923088992

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5777de3f3c9c2f3f377fb85cf546c1a49033bab0681637ed20ba352c03fd90
+size 1981958408

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32bc3c68ce2011a3935bb3927b53e447587540c514a79b7e1c2afeae27c8a1f3
+size 1981958400

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa690447c0516a7c8eef94d100a9b7d8ef5bb3392437f1b12794c53d445554a
+size 1981958464

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c5d1d0f4912e23ae1d07658b6eb34f7dc2209cdacd71fe0323c06aa98f5967
+size 1981958464

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b509198b3844ad87fb18e87089ea362be5e088b45e320501581a65dde08c99d6
+size 1981958464

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdffcabdfe0a72a63cd904c562605fe5d3c83321e4f688badc34c36f92aa2217
+size 1981958464

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1bf921a375897d5e11b303857c9c41bf6840f7734b44b1627add7be61d620c
+size 1981958464

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483fb9628c95b73059bd857104a0155edb2c3aa5fc209a8542755542ef4638e6
+size 1981958464

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230ee8f0b2ddb853d9a5f3e036bb5e482acb37fb23526e8951ca1b9316a4096d
+size 704709784

model.safetensors.index.json

@@ -1,471 +1,471 @@
 {
   "metadata": {
-    "total_size": 36966823936
+    "total_size": 18483411968
   },
   "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00018.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00002-of-00018.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
-    "model.layers.0.post_feedforward_layernorm.weight": "model-00002-of-00018.safetensors",
-    "model.layers.0.pre_feedforward_layernorm.weight": "model-00002-of-00018.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00006-of-00018.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
-    "model.layers.10.post_feedforward_layernorm.weight": "model-00006-of-00018.safetensors",
-    "model.layers.10.pre_feedforward_layernorm.weight": "model-00006-of-00018.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.post_feedforward_layernorm.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.pre_feedforward_layernorm.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.12.post_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.12.pre_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.13.post_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.13.pre_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.post_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.pre_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00008-of-00018.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
-    "model.layers.15.post_feedforward_layernorm.weight": "model-00008-of-00018.safetensors",
-    "model.layers.15.pre_feedforward_layernorm.weight": "model-00008-of-00018.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.post_feedforward_layernorm.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.pre_feedforward_layernorm.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.17.post_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.17.pre_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.18.post_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.18.pre_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.post_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.pre_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.2.post_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.2.pre_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00010-of-00018.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
-    "model.layers.20.post_feedforward_layernorm.weight": "model-00010-of-00018.safetensors",
-    "model.layers.20.pre_feedforward_layernorm.weight": "model-00010-of-00018.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.post_feedforward_layernorm.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.pre_feedforward_layernorm.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.22.post_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.22.pre_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.23.post_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.23.pre_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.post_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.pre_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00012-of-00018.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
-    "model.layers.25.post_feedforward_layernorm.weight": "model-00012-of-00018.safetensors",
-    "model.layers.25.pre_feedforward_layernorm.weight": "model-00012-of-00018.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.post_feedforward_layernorm.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.pre_feedforward_layernorm.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.27.post_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.27.pre_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.28.post_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.28.pre_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.post_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.pre_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.3.post_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.3.pre_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00014-of-00018.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
-    "model.layers.30.post_feedforward_layernorm.weight": "model-00014-of-00018.safetensors",
-    "model.layers.30.pre_feedforward_layernorm.weight": "model-00014-of-00018.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.post_feedforward_layernorm.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.pre_feedforward_layernorm.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.32.post_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.32.pre_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.33.post_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.33.pre_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.post_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.pre_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00016-of-00018.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
-    "model.layers.35.post_feedforward_layernorm.weight": "model-00016-of-00018.safetensors",
-    "model.layers.35.pre_feedforward_layernorm.weight": "model-00016-of-00018.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.post_feedforward_layernorm.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.pre_feedforward_layernorm.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.37.post_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.37.pre_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.38.post_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.38.pre_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.post_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.pre_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.4.post_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.4.pre_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
-    "model.layers.40.input_layernorm.weight": "model-00018-of-00018.safetensors",
-    "model.layers.40.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.40.mlp.gate_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.40.mlp.up_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
-    "model.layers.40.post_feedforward_layernorm.weight": "model-00018-of-00018.safetensors",
-    "model.layers.40.pre_feedforward_layernorm.weight": "model-00018-of-00018.safetensors",
-    "model.layers.40.self_attn.k_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.40.self_attn.o_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.40.self_attn.v_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.input_layernorm.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.mlp.gate_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.mlp.up_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.post_feedforward_layernorm.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.pre_feedforward_layernorm.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.self_attn.k_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.self_attn.o_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.41.self_attn.v_proj.weight": "model-00018-of-00018.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00004-of-00018.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
-    "model.layers.5.post_feedforward_layernorm.weight": "model-00004-of-00018.safetensors",
-    "model.layers.5.pre_feedforward_layernorm.weight": "model-00004-of-00018.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.post_feedforward_layernorm.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.pre_feedforward_layernorm.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.7.post_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.7.pre_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.8.post_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.8.pre_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.post_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.pre_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
-    "model.norm.weight": "model-00018-of-00018.safetensors"
+    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.norm.weight": "model-00010-of-00010.safetensors"
   }
 }

special_tokens_map.json

@@ -1,8 +1,7 @@
 {
   "additional_special_tokens": [
     "<start_of_turn>",
-    "<end_of_turn>",
-    "<eos>"
+    "<end_of_turn>"
   ],
   "bos_token": {
     "content": "<bos>",

tokenizer_config.json

@@ -1741,8 +1741,7 @@
   },
   "additional_special_tokens": [
     "<start_of_turn>",
-    "<end_of_turn>",
-    "<eos>"
+    "<end_of_turn>"
   ],
   "bos_token": "<bos>",
   "chat_template": "{{ '<bos>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<start_of_turn>user\n' + content + '<end_of_turn>\n<start_of_turn>model\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<end_of_turn>\n' }}{% endif %}{% endfor %}",