Trained with Unsloth

config.json

@@ -1,32 +1,36 @@
 {
-  "_name_or_path": "unsloth/qwen2.5-7b-instruct-bnb-4bit",
+  "_name_or_path": "unsloth/gemma-2-9b-it-bnb-4bit",
   "architectures": [
-    "Qwen2ForCausalLM"
+    "Gemma2ForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
-  "hidden_act": "silu",
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 3584,
   "initializer_range": 0.02,
-  "intermediate_size": 18944,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 28,
-  "model_type": "qwen2",
-  "num_attention_heads": 28,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 4,
-  "pad_token_id": 151665,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
   "torch_dtype": "float16",
   "transformers_version": "4.46.2",
-  "unsloth_fixed": true,
   "unsloth_version": "2024.11.7",
   "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 152064
+  "vocab_size": 256000
 }

generation_config.json

@@ -1,15 +1,9 @@
 {
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "max_length": 32768,
-  "pad_token_id": 151665,
-  "repetition_penalty": 1.05,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "max_length": 8192,
+  "pad_token_id": 0,
   "transformers_version": "4.46.2"
 }

pytorch_model-00001-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b2bf02cd80ac98a812a96767c52d73d4985026945703ed20ad89a3854c45bd5
-size 4877685654
+oid sha256:1c506a3569c345ccebccc5b0b6da42bbe1fa28f29dd3c465b157fac45d14b59e
+size 4903372134

pytorch_model-00002-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2825e06718b432072e8afa5b768fbffdf53f2f2f60284029d86531779ef686b
-size 4932779944
+oid sha256:76ccb62197440e7bdd4aaec08a52b8f7ee9ffec7bd5e4c70b026892277784f3f
+size 4947604025

pytorch_model-00003-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e416158d6b001b99e04e887dbd976ec0fbea235fc90cd72343aab63ae940fe3
-size 4330891098
+oid sha256:0af76fa95db9ed2db451420bb96c91475be7e2f3c76f98a231761d118ce38225
+size 4962252448

pytorch_model-00004-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d0aafa7a2169dd45ef9a10fe2cff298d57c97e347cf27d037fdbcc6b08d9f92
-size 1089996165
+oid sha256:0ec643cf0086f378ca0b9ed4e9f75f242e2f96b1b01c72d28967746bbf91628b
+size 3670346321

pytorch_model.bin.index.json

@@ -1,346 +1,471 @@
 {
   "metadata": {
-    "total_size": 15231233024
+    "total_size": 18483411968
   },
   "weight_map": {
-    "lm_head.weight": "pytorch_model-00004-of-00004.bin",
     "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00004.bin",
     "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
     "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.32.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.32.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.33.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.33.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
     "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.40.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.40.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
     "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
     "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
     "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
     "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00004.bin",
     "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.norm.weight": "pytorch_model-00003-of-00004.bin"
+    "model.norm.weight": "pytorch_model-00004-of-00004.bin"
   }
 }