Upload MistralForCausalLM

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "/fsx/agustin_piqueres/fine-tuning/OpenRLHF/checkpoint/mistal-7b-prm-openrlhf",
   "architectures": [
-    "MistralModel"
+    "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.3"
+}

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18df9bdf4eaacb9f3450523c0991c61ebbb7e4b939d3aac109e705950ae72e1f
-size 4987196648
+oid sha256:578538fe679005a4667dba78e2d563076b394102c240799aae8ba3d47adea9f7
+size 4987196936

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de49084e8ffdeef38267bc68584ddc5dd90077c12c3e0a754e80ef49967ca682
-size 4899116152
+oid sha256:e9079d4b56739cf9f1af99f5e49f8636e4f9d6d75a4d85270f6b73255f614ec1
+size 4899116440

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0223554698eccfe7a57a191d8ae754b694de829695ef1f3a790e837dcd584ad7
-size 4999812808
+oid sha256:cdbea985f8bce903668c0b786727d116b1f66421dbbb324b3fb04401ea049387
+size 4999813120

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a0aaefff3657ff83e70d75eec592b847b8c68f33288426d6dfadc5ae5706af
-size 4999812808
+oid sha256:fe68b8e0f6410d3c4cd8bcfae989cca08fc2d64a099d80fed81b6b4d1ccd0458
+size 4999813128

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d47de540906ea5e026b9e06dcaf2416037da88b186c355fd60ed0b703a6f5e1
-size 4832007216
+oid sha256:e94db74ad9b3c4ee4c68dde014b0783ffeb952e39d6232f4a43b20a4559bc3c5
+size 4832007496

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ddd2a0c34eaff526a263f42e52448be3b59bb2fb2562e6e161022be8065b9d8
-size 3724726552
+oid sha256:dd99a39ef07fbe47d0b3134b1e5205b42cfd820a588309a811b13578a88c65e6
+size 4249014896

model.safetensors.index.json

@@ -1,297 +1,298 @@
 {
   "metadata": {
-    "total_size": 28442640384
+    "total_size": 28966928384
   },
   "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "norm.weight": "model-00006-of-00006.safetensors"
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "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.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.weight": "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.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.weight": "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-00003-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-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-00003-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.weight": "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-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-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.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.weight": "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-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-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.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.weight": "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-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-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.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.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-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-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "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-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-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.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.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-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.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.weight": "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.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.weight": "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"
   }
 }