Trained with Unsloth

config.json

@@ -1,37 +1,36 @@
 {
-  "_name_or_path": "unsloth/Meta-Llama-3.1-8B",
+  "_name_or_path": "unsloth/gemma-2-9b",
   "architectures": [
-    "LlamaForCausalLM"
+    "Gemma2ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
+  "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": 14336,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
   "num_key_value_heads": 8,
-  "pad_token_id": 128004,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "tie_word_embeddings": false,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.3",
   "unsloth_version": "2024.8",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 256000
 }

generation_config.json

@@ -1,12 +1,8 @@
 {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "temperature": 0.6,
-  "top_p": 0.9,
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "pad_token_id": 0,
   "transformers_version": "4.43.3"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f20a55f2b1302686cf2c1f90385bc13f4ed295a74d5e8b496573253b57e705
-size 4976698672
+oid sha256:dcfaff32e35d95154fe3f851f08733183bd4e2d7f86c77f2abdb4f12c10ced1d
+size 4903351912

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8003c0a04fa0d80038afaee3ed6e10403be374c3fd8ee450ed32406d25a21b33
-size 4999802720
+oid sha256:97cee88ba0ee1773aa3081de7f6d6cd49046ff75c8d8f60073a3c4a662babd34
+size 4947570872

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6188cdc1c463ad8d2c67d73fb056be1cefccaafa2b1f1549678d2dde5e9d342f
-size 4915916176
+oid sha256:a3191805a81d671eafa3495eae44a3f759734c9413ba3439657b189fe5c22442
+size 4962221464

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1770350ace1e41c8b1db8959727bc190eae6cb9bde18d067674ee2cb08ee1c42
-size 1168138808
+oid sha256:17bb24d8ecfed4e2807039451076386041977fa0b9cd7388fdeffd5ae5a8721e
+size 3670322200

model.safetensors.index.json

@@ -1,15 +1,16 @@
 {
   "metadata": {
-    "total_size": 16060522496
+    "total_size": 18483411968
   },
   "weight_map": {
-    "lm_head.weight": "model-00004-of-00004.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
@@ -19,6 +20,8 @@
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
@@ -28,6 +31,8 @@
     "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -37,6 +42,8 @@
     "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -46,6 +53,8 @@
     "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -55,6 +64,8 @@
     "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -64,6 +75,8 @@
     "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -73,6 +86,8 @@
     "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -82,6 +97,8 @@
     "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -91,6 +108,8 @@
     "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -100,6 +119,8 @@
     "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -109,6 +130,8 @@
     "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -118,15 +141,19 @@
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
@@ -136,6 +163,8 @@
     "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -145,6 +174,8 @@
     "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -154,6 +185,8 @@
     "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -163,6 +196,8 @@
     "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -172,6 +207,8 @@
     "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -181,6 +218,8 @@
     "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -190,6 +229,8 @@
     "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -199,6 +240,8 @@
     "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -208,6 +251,8 @@
     "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
@@ -217,6 +262,8 @@
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
@@ -226,33 +273,151 @@
     "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
@@ -262,33 +427,41 @@
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",