Upload LlamaForCausalLM (#4)

- Upload LlamaForCausalLM (dae21134fe9d277f9155091bd7246854c6bd7ed0)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated",
+  "_name_or_path": "Locutusque/Apollo-2.0-Llama-3.1-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c5b93af8208a29d9412966deed4f7cb476af2fa002a5fa28fb6db43e9e6ea3
+size 1973455376

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887085829daeffbbf576bad1b7b5868199f68f94ec07e89364db6dde32faed2c
+size 1895895336

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b861e82409550270642986da96fc7f30d918445892d3ecea18f6bd4cb3caecce
+size 1979798040

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d11d162074e472ab66fad9fc5e2eae29e96cc52515af44497981d2b44b0f069
+size 1946227368

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f89d9c77817c8d41be773ffd255eff6769f9aa448815b89060e159a2eed414
+size 1979798064

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff2cec8ea6928433275e96b206fac30929fdc6612da84f66aff91fda5b9f671
+size 1946227368

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe5fd8bd23b8db6623bd3540b30209eb055fcaf1a161c4b12f28a5a6b3aa699
+size 1979798064

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd82b2a58dbcae863961acd9e1414b5423f08df1cfdbee63c9349309d8d7bae
+size 1308683424

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0b906dd16b9d01f2d27f0df82b954a574daf724fb38a55ae615a1c2ad9a0ea
+size 1050673280

model.safetensors.index.json

@@ -3,296 +3,296 @@
     "total_size": 16060522496
   },
   "weight_map": {
-    "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-00002-of-00006.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.k_proj.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-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-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-00003-of-00006.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.k_proj.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-00003-of-00006.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-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-00004-of-00006.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00004-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-00004-of-00006.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00004-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-00004-of-00006.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00004-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-00005-of-00006.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00005-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-00005-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-00005-of-00006.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00005-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-00005-of-00006.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00005-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-00005-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-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00006.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-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"
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.norm.weight": "model-00008-of-00009.safetensors"
   }
 }