sharded the model

pytorch_model-00001-of-00002.bin → pytorch_model-00001-of-00008.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88c780cf05290d5f415aa79c94840cd32862ec6058d349e86f72233e62edac30
-size 9943028531
+oid sha256:a29a4742a62d03b3dddccf2d834ce9db678a110b6d5ea483e2f3507bb43fdaca
+size 1889595342

pytorch_model-00002-of-00002.bin → pytorch_model-00002-of-00008.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93abb2a6dd859c38a9009638ff02e774fef55a3f7c33f36ad4a7691461cabe9a
-size 4540536134
+oid sha256:48120157a5d7ea013478167d666e6a40e63e560f17dc6520a8b12b169f850953
+size 1946254384

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b677e863cb373e77aa4ee60b3d108f63d93c68dc4d0cae8c679d1deac72ff8cf
+size 1979790678

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d06a34efa7b5b94eca7e3f5e219ee12ab79b66b85952c853c156d7cbdff060c
+size 1946254448

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:309aa05a4cf70c67e75366eff9deedeb357f8dbcf764ff5424da2d4d1c9f1f1a
+size 1979790742

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9c3ca43078c331c60d806f59298e08434d39066c15e03a9f89775d3b970137
+size 1946254448

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84321bafa282102c0cecd5c42476fe642770c19708bfe55602e551b6c108877a
+size 1979790742

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68464fe3659a47a8481f2372b2b86363c428a61c2ce4405c627805ba39f5109a
+size 815838694

pytorch_model.bin.index.json

@@ -3,296 +3,296 @@
     "total_size": 14483464192
   },
   "weight_map": {
-    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
-    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+    "lm_head.weight": "pytorch_model-00008-of-00008.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.norm.weight": "pytorch_model-00008-of-00008.bin"
   }
 }