Upload model

config.json

@@ -25,7 +25,7 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
   "trust_remote_code": true,
   "use_cache": true,

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:185d4ce48d5864c692b111ffb4bbceabad5bae2adefb76d1e50eeeaa5547c08e
+size 4976698176

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93c796116c80fcc485c267862f505a146daba0ee423b401986d99e64b4209a8
+size 4999802096

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766bdc6a11e609e25735fc2e0e59d342ed560602f73d956badfca023a7d98cb6
+size 4915915576

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35054311c07a681e505c4ca5cad38a26e0799477e4dfc5bf777a472858569056
+size 117465520

model.safetensors.index.json

@@ -1,297 +1,297 @@
 {
   "metadata": {
-    "total_size": 30019698688
+    "total_size": 15009849344
   },
   "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00007.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
-    "layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
-    "layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
-    "layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
-    "layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
-    "layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
-    "layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
-    "layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
-    "layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
-    "layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
-    "layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
-    "layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
-    "norm.weight": "model-00007-of-00007.safetensors"
+    "embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "norm.weight": "model-00004-of-00004.safetensors"
   }
 }