Upload LlamaForCausalLM

config.json

@@ -1,28 +1,30 @@
 {
-  "_name_or_path": "qwen_v1_best",
+  "_name_or_path": "llama14b_v1",
   "architectures": [
-    "Qwen2ForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 100257,
   "eos_token_id": 100257,
+  "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 5120,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 13824,
-  "max_position_embeddings": 131072,
-  "max_window_layers": 48,
-  "model_type": "qwen2",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 46,
+  "intermediate_size": 18752,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
   "num_key_value_heads": 8,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.1",
   "use_cache": false,
-  "use_sliding_window": false,
-  "vocab_size": 101336
+  "vocab_size": 100288
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": 151643,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
   "transformers_version": "4.44.1"
 }

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177c4f60b2d0cdbabc1542855e4bb895826319da5351851a73468af0cf428ac5
-size 4964866232
+oid sha256:a54d1f0357a71db6ef94795c68032540ac60947307e5ea0c53baca2d0e44f01b
+size 4872331080

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15268f4850ece47795c716c5ccb3c4e5ebf069f2588ef5558263f2b77cece6e7
-size 4954847360
+oid sha256:ca729e6c70f41df3c7d8fed064cdee82cbe008e080b07debe0201397657d0bb5
+size 4902773984

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:facc852b0dca0a16d83bb32f6ba00e2c170777353250e5edb442ec2102652353
-size 4954847400
+oid sha256:d1bae7d6b3a081978d814f39c18100b70433afe5a97530531a9a32787112601e
+size 4902774000

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3312f460c250c9f34814b31f91e2fe4791cbe8966efc8b4992f084884752d545
-size 4954847400
+oid sha256:9d430006b4e5c2a585cae13ebbb6d94ddc44d4a0c8792e3ece00f824ffc9c729
+size 4902774000

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d338733b9ef4fb59156c68bf2509b48cd0cafbf4c3fad668044a6d221f73a5c
-size 4954847400
+oid sha256:2f7092e0c155a9550d8d6922639f4faafc19d7dac9051f0de5aba3f6ca1c0299
+size 4902774000

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e6f4aac4c20425e88a476f1915be121c5b49bda90b863fc58e006ae52917811
-size 2615891560
+oid sha256:dec1854544ac3a60abe56e255f5cb0f4bd3559420ca6e8e07293b5c009861345
+size 3307827984

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 27400083456
+    "total_size": 27791204352
   },
   "weight_map": {
     "lm_head.weight": "model-00006-of-00006.safetensors",
@@ -10,552 +10,432 @@
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.33.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.33.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.33.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
     "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.42.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.42.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.42.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
     "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
     "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
     "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
     "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
     "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
     "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
     "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
     "model.norm.weight": "model-00006-of-00006.safetensors"
   }