Upload LlamaForCausalLM

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": ".",
   "architectures": [
-    "LlamaModel"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab352431baeaf1a4760dda4e47a85e61929fe035f84a50812ef3df6fd2056dc
-size 4886465976
+oid sha256:6a7c67195023d5d84b553503f6429ea80e46ce5ea94edb1f1650e2430430a30f
+size 4886466168

model-00002-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16161619d6edd760e31be20643c77131f34c6125ffc0cc493b2d70ee522e65f2
-size 4832007168
+oid sha256:31c1d4769a14748930fbcdb39c6b98198eb98962760524455a6a2ddc2ee24568
+size 4832007448

model-00003-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e36fd9941f83fade3bbce77118daf4135e0457b1e33b95d5a38c1d18c1d6a3
-size 4999812792
+oid sha256:65fe0de38230ce54562fbb14dc97e7241fcef44e11bc10aed0f50c7dee5d1c09
+size 4999813112

model-00004-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d7baa6c041c36dd568c937c95d5b6106f4744c71e05aaa5534fe5aed9c66f79
-size 4999812808
+oid sha256:32685aaf8aca724bc75f70b941b88a249edc805cfe66dd4cdfcaae0e1b28243b
+size 4999813128

model-00005-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b6cbfda8999e86d3fb7efe721290cc6fff2d0a8ae456bc2e6f4c523d1e9295f
-size 4832007216
+oid sha256:78b8520061af0331d9f9ff5b3ee8c078b03e7e2610aebc48d8c03672e47c92d3
+size 4832007496

model-00006-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f83f491f15a3662bad7039c4e93f54b62d969ed808b7bccbbaf76b98ea403e35
-size 4999812808
+oid sha256:749f89d912b7a291451ec5101f79f456da19a17f320b486d1d2b026f1e76ff36
+size 4999813120

model-00007-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a2dd18ed215604bec3e1b9e8a971ed1fef15c99fd5074aa2ba2c625ae8613f
-size 469811736
+oid sha256:638d1d553896a8af81c9fe114ebf8e90f261766ca06523b91bb8a2739c9b72e3
+size 2571158184

model.safetensors.index.json

@@ -1,297 +1,298 @@
 {
   "metadata": {
-    "total_size": 30019698688
+    "total_size": 32121044992
   },
   "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00007.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "norm.weight": "model-00007-of-00007.safetensors"
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
   }
 }