Upload LlamaForCausalLM

config.json

@@ -1,36 +1,30 @@
 {
-  "_name_or_path": "phi_v9",
+  "_name_or_path": "llama_v1",
   "architectures": [
-    "Phi3ForCausalLM"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 32000,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_actt": "silu",
-  "hidden_size": 4608,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 131072,
-  "model_type": "phi3",
-  "norm_divisor": null,
-  "num_attention_heads": 48,
-  "num_hidden_layers": 48,
-  "num_key_value_heads": 48,
-  "original_max_position_embeddings": 131072,
-  "pad_token_id": 32000,
-  "resid_pdrop": 0.0,
-  "return_states_at_layer": null,
+  "intermediate_size": 18752,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "sliding_window": 262144,
-  "start_at_layer": null,
+  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.0",
   "use_cache": false,
-  "vocab_size": 32064
+  "vocab_size": 100288
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "pad_token_id": 32000,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
   "transformers_version": "4.44.0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30f4629c5e8232cfb7c1486f3ab6dbda8ed75db12ccf1c58544e35fc1e3fd249
-size 4976556016
+oid sha256:a2afc70e5999f033ac224befb3fb6e131e3e5d5a83ca9df3ae34c5d97f704d5b
+size 4872331080

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464fd66a7d76e899e4212fbaec3397ce9387ee011ed35e972787c56f1de2c097
-size 4874554072
+oid sha256:4de763c1e67e6278f133e7fec20df7415a2f06fef3d75002893aff59251f0967
+size 4902773984

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5957caafe5da9e53ad12981b27d3416fcff9240736756d0bcb2474c220b9773
-size 4883972488
+oid sha256:e488e80bdbc398cb53e3939ae182bf59d0ccfdddc66be06ae90c1e7394bfcd3e
+size 4902774000

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3690e9382a9ec8b8b280d55275fb27d6bb6ed0cc6c0bd7f622b6693a62b74f0
-size 4882212072
+oid sha256:35e974cba30d8604da8fb71dafe8558db686c929b5bb847cc78c07adf8b08f70
+size 3307827984

model.safetensors.index.json

@@ -1,298 +1,280 @@
 {
   "metadata": {
-    "total_size": 19617260544
+    "total_size": 17985675264
   },
   "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_up_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.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.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "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.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.qkv_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "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.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",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "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.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.self_attn.qkv_proj.weight": "model-00001-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",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "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.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.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "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.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.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "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.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.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "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.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.qkv_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-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.qkv_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "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.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.qkv_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.qkv_proj.weight": "model-00002-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.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "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.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",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "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.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",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "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.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",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "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.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.24.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.post_attention_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",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-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.qkv_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "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.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.qkv_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.qkv_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.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.qkv_proj.weight": "model-00003-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_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.36.self_attn.qkv_proj.weight": "model-00003-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_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.37.self_attn.qkv_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_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.38.self_attn.qkv_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_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.39.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-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_up_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.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.qkv_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_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.40.self_attn.qkv_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_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.41.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.42.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.42.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.43.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.43.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.44.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.44.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.44.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.45.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.45.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.45.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.46.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.46.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.46.self_attn.qkv_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.47.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.47.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "model.layers.47.self_attn.qkv_proj.weight": "model-00004-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.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_up_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.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.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "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.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.qkv_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.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.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.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_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.qkv_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_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.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.qkv_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.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.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",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "model.norm.weight": "model-00004-of-00004.safetensors"
   }
 }