Trained with Unsloth

config.json

@@ -1,36 +1,39 @@
 {
-  "_name_or_path": "unsloth/gemma-2-9b-bnb-4bit",
+  "_name_or_path": "unsloth/meta-llama-3.1-8b-bnb-4bit",
   "architectures": [
-    "Gemma2ForCausalLM"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "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,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma2",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 42,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "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": "float16",
+  "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,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
+  "unsloth_fixed": true,
   "unsloth_version": "2025.3.18",
   "use_cache": true,
-  "vocab_size": 256000
+  "vocab_size": 128256
 }

generation_config.json

@@ -1,9 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 2,
-  "cache_implementation": "hybrid",
-  "eos_token_id": 1,
-  "max_length": 8192,
-  "pad_token_id": 0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "max_length": 131072,
+  "pad_token_id": 128004,
   "transformers_version": "4.49.0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54d90c5d944072a994a153a3b236f386cb6e1f03d01007c9e3d752581ea943ba
-size 4903351824
+oid sha256:48ab6ca2c66d06c32ba5f12631a754932825e568f4a70881bb62c506b3303372
+size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f0c3ee6f6f6c621e9a812ebb38b5b3518554f5ead83f687f636be2f2195144
-size 4947570728
+oid sha256:7918da8fdbcb2d64ad88a7c0204ddb60dc05c1fc281e619fda74cf20efd36fba
+size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39279d6ede33d6b54fe8856d299292b4610109edfd359e59c6fbd5f28276b640
-size 4962221328
+oid sha256:f101a2ceecd59f1642736ba3e2846686471798c424b7e66c4aaf3e4d9f3e452a
+size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1d5acc5b7c86cf4b145d74c568ddbc4f05e96b30cf2bc7528aa5477900a527
-size 3670322096
+oid sha256:092ac1eccdb46a679f38c2ca027fc8b411d8b220fdb926b2a5f0b33ae1faeb2d
+size 1168138808

model.safetensors.index.json

@@ -1,16 +1,15 @@
 {
   "metadata": {
-    "total_size": 18483411968
+    "total_size": 16060522496
   },
   "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",
@@ -20,8 +19,6 @@
     "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",
@@ -31,8 +28,6 @@
     "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",
@@ -42,8 +37,6 @@
     "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",
@@ -53,8 +46,6 @@
     "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",
@@ -64,8 +55,6 @@
     "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",
@@ -75,8 +64,6 @@
     "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",
@@ -86,8 +73,6 @@
     "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",
@@ -97,8 +82,6 @@
     "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",
@@ -108,8 +91,6 @@
     "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",
@@ -119,8 +100,6 @@
     "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",
@@ -130,8 +109,6 @@
     "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",
@@ -141,19 +118,15 @@
     "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-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-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",
@@ -163,8 +136,6 @@
     "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",
@@ -174,8 +145,6 @@
     "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",
@@ -185,8 +154,6 @@
     "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",
@@ -196,8 +163,6 @@
     "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",
@@ -207,8 +172,6 @@
     "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",
@@ -218,8 +181,6 @@
     "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",
@@ -229,8 +190,6 @@
     "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",
@@ -240,8 +199,6 @@
     "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",
@@ -251,8 +208,6 @@
     "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",
@@ -262,8 +217,6 @@
     "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",
@@ -273,151 +226,33 @@
     "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-00003-of-00004.safetensors",
-    "model.layers.31.mlp.down_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.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-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.post_attention_layernorm.weight": "model-00004-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",
@@ -427,41 +262,33 @@
     "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-00002-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-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.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-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.post_attention_layernorm.weight": "model-00001-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-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.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.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",