Upload LlamaForCausalLM

config.json

@@ -6,31 +6,24 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 100257,
-  "device": "cuda:0",
-  "dtype": "bfloat16",
   "eos_token_id": 100257,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 18624,
-  "leave_empty": true,
+  "intermediate_size": 14208,
   "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 48,
+  "num_hidden_layers": 60,
   "num_key_value_heads": 8,
-  "pop_states_at_layer": null,
   "pretraining_tp": 1,
-  "return_states_at_layer": null,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,
-  "start_at_layer": null,
-  "stash_states_at_layer": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 100288
 }

generation_config.json

@@ -2,6 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 100257,
   "eos_token_id": 100257,
-  "transformers_version": "4.44.1",
-  "use_cache": false
+  "transformers_version": "4.44.1"
 }

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa9112f6efe81d6f146cbeb774bc7b7def3669982ba9d6b60bfafd64becd5f55
-size 4849262408
+oid sha256:00c2f3c27f30abbdc932ec4fc93cbdb051fe1e475e17c3935883f3b7d5eff3f1
+size 4919551856

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eba231a77d63608f58ef7bce243167a2b3a5ef32be1442659888000601d3b85
-size 4874462424
+oid sha256:d1cfd519fb02af25ba31a853d529f2c75ec8e80a201c27f76b8bf3a25c182eaa
+size 4996673256

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a12fc59526ccae52ddc1529136af4ff20b8c532a82105770876852b8e1c83b
-size 4874462448
+oid sha256:9b8d5009370da95ba3f2b7dbb5df15643e8d0f9a920709cb97d676be54728bcd
+size 4964151144

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040671f28f12ed1177c2ecacb0476b6f3a969c3a342ae613c6ee551949fa6666
-size 4874462448
+oid sha256:3fc7c49699a20cfb3d08269a2ad96cd7540aa3859240a84e36dd7381ae09b21b
+size 4996673264

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ff052f318724d8721354119b59bd87b59095bc8bf5418fd11a57ae2a91a055
-size 4874462448
+oid sha256:97468a34381a08ed1a2c5d94885d60f9ce760b39e01853671bdb671d4f6a39dc
+size 4964151144

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85267fb7e0a726535c0fa4616e7e4ae026d89e9c8cdfd257fb0065a29048408c
-size 3293147920
+oid sha256:ce473c17678b1387b875802046f6bb06d5e3e745a8c8f69d0a0f006c062b4435
+size 2786685712

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 27640209408
+    "total_size": 27627823104
   },
   "weight_map": {
     "lm_head.weight": "model-00006-of-00006.safetensors",
@@ -77,42 +77,42 @@
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
@@ -122,15 +122,15 @@
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
@@ -167,51 +167,51 @@
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
@@ -221,33 +221,33 @@
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.33.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.33.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
@@ -257,60 +257,60 @@
     "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
@@ -320,78 +320,96 @@
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
@@ -401,6 +419,96 @@
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
@@ -410,33 +518,33 @@
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.norm.weight": "model-00006-of-00006.safetensors"
   }
 }