Upload Gemma2ForCausalLM

config.json

@@ -1,30 +1,34 @@
 {
-  "_name_or_path": "NCSOFT/Llama-VARCO-8B-Instruct",
+  "_name_or_path": "HumanF-MarkrAI/Gukbap-Gemma2-9B",
   "architectures": [
-    "LlamaForCausalLM"
+    "Gemma2ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "head_dim": 128,
-  "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": 8192,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
   "num_key_value_heads": 8,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 500000.0,
-  "tie_word_embeddings": false,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.47.1",
   "use_cache": false,
-  "vocab_size": 128256
+  "vocab_size": 256000
 }

generation_config.json

@@ -1,7 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "transformers_version": "4.47.1",
-  "use_cache": false
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.47.1"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6711bc95ff58a4075c64ce9db7de83be60d92363428da5b65787c0a6cd862d54
-size 4984375544
+oid sha256:98cda5fe114f0c1d6aa3d80560acc704d9b6cd9be6aa1c7b9ee1018f918560fe
+size 4910175800

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb2b8285379d120e7dd93f828228d69cbba737eb41551afd726c025939139fa
-size 4892598032
+oid sha256:be0c1504c15f8b6040beaf15c64b3418b89e1ba007e04d078fbcb163cbdc34fe
+size 4958659816

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed15f183fac35998b8a8d2c53e0c2ea8f27507607e2bfb3243116ca92b918e42
-size 4925299128
+oid sha256:acaa0706ba53fa0cc0c85acae106bc775179b2b64ca1866afd2e1ec8b4e3dacd
+size 4972457408

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46558a95b3da87e00e388cb9e00df9f2aa437427111fa0ae0e7413dafa78216c
-size 1285579432
+oid sha256:f3bbc79b25d3ef3f1ccaf8dac1204d3cf2e7cdb34cf092baec71b4fe4b815517
+size 3677999160

model.safetensors.index.json

@@ -1,15 +1,16 @@
 {
   "metadata": {
-    "total_size": 16087785472
+    "total_size": 18519194624
   },
   "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.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
@@ -27,6 +28,8 @@
     "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.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
@@ -44,6 +47,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -61,6 +66,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -78,6 +85,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -95,6 +104,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -112,6 +123,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -129,6 +142,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -146,6 +161,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -163,6 +180,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -180,6 +199,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -197,6 +218,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -214,6 +237,8 @@
     "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.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
@@ -231,6 +256,8 @@
     "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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
@@ -248,6 +275,8 @@
     "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.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -265,6 +294,8 @@
     "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.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -282,6 +313,8 @@
     "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.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -299,6 +332,8 @@
     "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.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -316,6 +351,8 @@
     "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.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -333,6 +370,8 @@
     "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.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -350,6 +389,8 @@
     "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.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -367,6 +408,8 @@
     "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.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -384,6 +427,8 @@
     "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.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -401,6 +446,8 @@
     "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.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
@@ -418,6 +465,8 @@
     "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.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -430,11 +479,13 @@
     "model.layers.30.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.v_proj.lora_B.default.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-00004-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-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.self_attn.k_proj.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
@@ -447,11 +498,165 @@
     "model.layers.31.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
@@ -464,11 +669,51 @@
     "model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.base_layer.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
@@ -486,6 +731,8 @@
     "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.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
@@ -498,11 +745,13 @@
     "model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
@@ -515,28 +764,32 @@
     "model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_B.default.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.base_layer.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",