Sharded model

config.json

@@ -49,7 +49,7 @@
   "no_bias": false,
   "norm_type": "low_precision_layernorm",
   "resid_pdrop": 0.0,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.35.0",
   "use_cache": false,
   "vocab_size": 250880

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.35.0",
+  "use_cache": false
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f738ebcce0787ec18b7df3809e59081be2c0faf98cd753cea433ce839b554abf
+size 2055209096

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ff0cf87aa4476822c87fb6d7e50f7f959494d2420b833b53ded46223d20c5c
+size 1879578920

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86e3d5d5b440e67d043068f9544aea87e9523a60aeeb02f509b1dfc23beeb16
+size 1879554352

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009d79029a807af65db3aaa7c340dbb56d9ec63ad43b821183663036bb1c5302
+size 1980225672

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082bf3e89b85ac75b30fc857e1ce731d31c3648f1e2bbf6dec6bb9d9ffabf5bc
+size 1913117032

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17426c500e4d2c308c94b87ef59f0e10c31131209d8519361da428ac09c43da4
+size 1879562384

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a960b250a424802d5a489412839e6225af8a827d7fac1d9095abfc2de6eb306d
+size 1879554408

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a85ec135da0553d3bfc539a1a7f51893c17aca29a8100d14cdc10c3d62c14f
+size 1476776536

model.safetensors.index.json

@@ -0,0 +1,394 @@
+{
+  "metadata": {
+    "total_size": 14943535104
+  },
+  "weight_map": {
+    "transformer.blocks.0.attn.Wqkv.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.attn.Wqkv.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.attn.out_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.ffn.down_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.ffn.down_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.ffn.up_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.ffn.up_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.norm_1.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.norm_1.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.norm_2.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.0.norm_2.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.attn.Wqkv.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.attn.Wqkv.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.attn.out_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.ffn.down_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.ffn.down_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.ffn.up_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.ffn.up_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.norm_1.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.norm_1.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.norm_2.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.1.norm_2.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.10.attn.Wqkv.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.attn.Wqkv.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.attn.out_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.attn.out_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.ffn.down_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.ffn.down_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.ffn.up_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.ffn.up_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.norm_1.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.norm_1.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.norm_2.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.10.norm_2.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.attn.Wqkv.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.attn.Wqkv.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.attn.out_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.attn.out_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.ffn.down_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.ffn.down_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.ffn.up_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.ffn.up_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.norm_1.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.norm_1.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.norm_2.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.11.norm_2.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.attn.Wqkv.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.attn.Wqkv.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.attn.out_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.attn.out_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.ffn.down_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.ffn.down_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.ffn.up_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.ffn.up_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.norm_1.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.norm_1.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.norm_2.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.12.norm_2.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.attn.Wqkv.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.attn.Wqkv.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.attn.out_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.attn.out_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.ffn.down_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.ffn.down_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.ffn.up_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.ffn.up_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.norm_1.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.norm_1.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.norm_2.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.13.norm_2.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.14.attn.Wqkv.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.14.attn.Wqkv.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.14.attn.out_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.14.attn.out_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.14.ffn.down_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.14.ffn.down_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.14.ffn.up_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.14.ffn.up_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.14.norm_1.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.14.norm_1.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.14.norm_2.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.14.norm_2.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.attn.Wqkv.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.attn.Wqkv.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.attn.out_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.attn.out_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.ffn.down_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.ffn.down_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.ffn.up_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.ffn.up_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.norm_1.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.norm_1.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.norm_2.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.15.norm_2.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.attn.Wqkv.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.attn.Wqkv.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.attn.out_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.attn.out_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.ffn.down_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.ffn.down_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.ffn.up_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.ffn.up_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.norm_1.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.norm_1.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.norm_2.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.16.norm_2.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.attn.Wqkv.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.attn.Wqkv.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.attn.out_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.attn.out_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.ffn.down_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.ffn.down_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.ffn.up_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.ffn.up_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.norm_1.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.norm_1.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.norm_2.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.17.norm_2.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.attn.Wqkv.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.attn.Wqkv.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.attn.out_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.attn.out_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.ffn.down_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.ffn.down_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.ffn.up_proj.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.ffn.up_proj.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.norm_1.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.norm_1.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.norm_2.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.18.norm_2.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.19.attn.Wqkv.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.19.attn.Wqkv.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.19.attn.out_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.19.attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.19.ffn.down_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.19.ffn.down_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.19.ffn.up_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.19.ffn.up_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.19.norm_1.bias": "model-00005-of-00008.safetensors",
+    "transformer.blocks.19.norm_1.weight": "model-00005-of-00008.safetensors",
+    "transformer.blocks.19.norm_2.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.19.norm_2.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.2.attn.Wqkv.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.attn.Wqkv.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.attn.out_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.ffn.down_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.ffn.down_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.ffn.up_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.ffn.up_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.norm_1.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.norm_1.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.norm_2.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.2.norm_2.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.20.attn.Wqkv.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.attn.Wqkv.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.attn.out_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.ffn.down_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.ffn.down_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.ffn.up_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.ffn.up_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.norm_1.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.norm_1.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.norm_2.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.20.norm_2.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.attn.Wqkv.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.attn.Wqkv.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.attn.out_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.ffn.down_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.ffn.down_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.ffn.up_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.ffn.up_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.norm_1.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.norm_1.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.norm_2.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.21.norm_2.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.attn.Wqkv.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.attn.Wqkv.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.attn.out_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.ffn.down_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.ffn.down_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.ffn.up_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.ffn.up_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.norm_1.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.norm_1.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.norm_2.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.22.norm_2.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.23.attn.Wqkv.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.23.attn.Wqkv.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.23.attn.out_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.23.attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.23.ffn.down_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.23.ffn.down_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.23.ffn.up_proj.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.23.ffn.up_proj.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.23.norm_1.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.23.norm_1.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.23.norm_2.bias": "model-00006-of-00008.safetensors",
+    "transformer.blocks.23.norm_2.weight": "model-00006-of-00008.safetensors",
+    "transformer.blocks.24.attn.Wqkv.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.attn.Wqkv.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.attn.out_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.attn.out_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.ffn.down_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.ffn.down_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.ffn.up_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.ffn.up_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.norm_1.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.norm_1.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.norm_2.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.24.norm_2.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.attn.Wqkv.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.attn.Wqkv.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.attn.out_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.attn.out_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.ffn.down_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.ffn.down_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.ffn.up_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.ffn.up_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.norm_1.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.norm_1.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.norm_2.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.25.norm_2.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.attn.Wqkv.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.attn.Wqkv.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.attn.out_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.attn.out_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.ffn.down_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.ffn.down_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.ffn.up_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.ffn.up_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.norm_1.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.norm_1.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.norm_2.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.26.norm_2.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.attn.Wqkv.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.attn.Wqkv.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.attn.out_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.attn.out_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.ffn.down_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.ffn.down_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.ffn.up_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.ffn.up_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.norm_1.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.norm_1.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.norm_2.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.27.norm_2.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.28.attn.Wqkv.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.28.attn.Wqkv.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.28.attn.out_proj.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.28.attn.out_proj.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.28.ffn.down_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.28.ffn.down_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.28.ffn.up_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.28.ffn.up_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.28.norm_1.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.28.norm_1.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.28.norm_2.bias": "model-00007-of-00008.safetensors",
+    "transformer.blocks.28.norm_2.weight": "model-00007-of-00008.safetensors",
+    "transformer.blocks.29.attn.Wqkv.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.attn.Wqkv.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.attn.out_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.attn.out_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.ffn.down_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.ffn.down_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.ffn.up_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.ffn.up_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.norm_1.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.norm_1.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.norm_2.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.29.norm_2.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.3.attn.Wqkv.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.attn.Wqkv.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.attn.out_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.ffn.down_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.ffn.down_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.ffn.up_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.ffn.up_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.norm_1.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.norm_1.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.norm_2.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.3.norm_2.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.30.attn.Wqkv.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.attn.Wqkv.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.attn.out_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.attn.out_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.ffn.down_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.ffn.down_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.ffn.up_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.ffn.up_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.norm_1.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.norm_1.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.norm_2.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.30.norm_2.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.attn.Wqkv.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.attn.Wqkv.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.attn.out_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.attn.out_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.ffn.down_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.ffn.down_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.ffn.up_proj.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.ffn.up_proj.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.norm_1.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.norm_1.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.norm_2.bias": "model-00008-of-00008.safetensors",
+    "transformer.blocks.31.norm_2.weight": "model-00008-of-00008.safetensors",
+    "transformer.blocks.4.attn.Wqkv.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.4.attn.Wqkv.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.4.attn.out_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.4.attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.4.ffn.down_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.4.ffn.down_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.4.ffn.up_proj.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.4.ffn.up_proj.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.4.norm_1.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.4.norm_1.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.4.norm_2.bias": "model-00002-of-00008.safetensors",
+    "transformer.blocks.4.norm_2.weight": "model-00002-of-00008.safetensors",
+    "transformer.blocks.5.attn.Wqkv.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.attn.Wqkv.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.attn.out_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.attn.out_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.ffn.down_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.ffn.down_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.ffn.up_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.ffn.up_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.norm_1.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.norm_1.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.norm_2.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.5.norm_2.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.attn.Wqkv.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.attn.Wqkv.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.attn.out_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.attn.out_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.ffn.down_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.ffn.down_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.ffn.up_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.ffn.up_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.norm_1.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.norm_1.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.norm_2.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.6.norm_2.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.attn.Wqkv.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.attn.Wqkv.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.attn.out_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.attn.out_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.ffn.down_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.ffn.down_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.ffn.up_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.ffn.up_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.norm_1.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.norm_1.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.norm_2.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.7.norm_2.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.attn.Wqkv.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.attn.Wqkv.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.attn.out_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.attn.out_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.ffn.down_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.ffn.down_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.ffn.up_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.ffn.up_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.norm_1.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.norm_1.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.norm_2.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.8.norm_2.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.9.attn.Wqkv.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.9.attn.Wqkv.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.9.attn.out_proj.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.9.attn.out_proj.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.9.ffn.down_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.9.ffn.down_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.9.ffn.up_proj.bias": "model-00004-of-00008.safetensors",
+    "transformer.blocks.9.ffn.up_proj.weight": "model-00004-of-00008.safetensors",
+    "transformer.blocks.9.norm_1.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.9.norm_1.weight": "model-00003-of-00008.safetensors",
+    "transformer.blocks.9.norm_2.bias": "model-00003-of-00008.safetensors",
+    "transformer.blocks.9.norm_2.weight": "model-00003-of-00008.safetensors",
+    "transformer.norm_f.bias": "model-00008-of-00008.safetensors",
+    "transformer.norm_f.weight": "model-00008-of-00008.safetensors",
+    "transformer.wte.weight": "model-00001-of-00008.safetensors"
+  }
+}