Add saturated ckpt

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "upstage/SOLAR-10.7B-v1.0",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -16,13 +15,14 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 48,
   "num_key_value_heads": 8,
+  "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.1",
-  "use_cache": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.1",
+  "use_cache": true,
   "vocab_size": 64000
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.33.1"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8195f65a87903a7adc82582d0d64a76648a9f622bceacc964988cc6057dd75
+size 2906740504

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9107f4e3ba5b383c17aaa278b0d6d03521fd2da2e87707fab45f4c4ecaa93655
+size 2936134664

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80232aafba21349c389d8551eb02fa2fc204242da33b3820dab63bc3033f5a96
+size 2969688800

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c215d12a04c9d8d4ba6cd3cda5289d1d1515d720adef5c92a15b98c2277f0427
+size 2936118096

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c84e76e7fb9a6a5ec5da4e3c217c8072daf27a5bb5a24373b5f000c157a5782
+size 2936134712

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:351d4d632888c16061627fc402ccfba3a34b710e19b0a2cc8f63b0bc5edaa6ad
+size 2936134720

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dce2ec277917ad8b1c7499e2e0103c87bd556edf752fe7865b5f7269a3c7bfd
+size 2969688800

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf8e2f3c87282c5f2ce253b92c44b34c019e4312a5ee3ed749d15a88638b305
+size 1396746488

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 21987336192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00008-of-00008.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.norm.weight": "model-00008-of-00008.safetensors"
+  }
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8e8b3849632c9f18613b8bce20a1059747633818a859ab505da0bf60dfb624
+size 2906751653

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59bdd1ddb7103fa297520d7f9c6d27abf9b3fd9dcb623fbc30316bbb5bc9bc17
+size 2936148267

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9baf0447962288892debc05548e8734e8e194dbb62fe370ba2c5c3949e0b7d2b
+size 2969701685

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e83c88360156ae8658685aa2ca06c7f46086d08ee6e97e4a70a2e85f69c6c37
+size 2936131271

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63737acf8b46a78b630e429a20e2109d3cb39bac7c192a9ba7fd0c8132a00d1b
+size 2936148267

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8ab849f34bc597f0c545c18e892688d7a339251b9c73021e98fa76d5942be8
+size 2936148267

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:648207dbb57aecc4f75b00fdf90598f4b52e2aaef6c88c233299191a6a3c60a7
+size 2969701685

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334876e4890e7ec828e96ed5460f375e6a96693c7a358e7f364df57dc15c6427
+size 1396751031

pytorch_model.bin.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 21987336192
+  },
+  "weight_map": {
+    "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-00002-of-00008.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-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-00003-of-00008.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-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-00004-of-00008.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-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-00001-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-00005-of-00008.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00008-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-00001-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-00001-of-00008.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-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-00002-of-00008.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-of-00008.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.norm.weight": "pytorch_model-00008-of-00008.bin"
+  }
+}