Checkpoint as bfloat16

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/netscratch/mostendorff/experiments/occiglot-axolotl/data/occiglot/eu5_es_en_instruct/output",
+  "_name_or_path": "occiglot/occiglot-7b-es-en-instruct",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -19,7 +19,7 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.35.2",
   "use_cache": false,
   "vocab_size": 32002

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78dee7ba2780b87abd57edafd13dc8ae04f42483c0eaddc2dcc951d29ddfbe4
+size 4943178720

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12acb21cbf3a864e238d8026166919573787f4b1b998039e36d8a12ed8377b73
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87de4325c9d23ec693e17ee900ca9354645749c84435f08d4612b14a0784b37a
+size 4540532728

model.safetensors.index.json

@@ -1,298 +1,298 @@
 {
   "metadata": {
-    "total_size": 28966993920
+    "total_size": 14483496960
   },
   "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-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"
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
   }
 }