Upload GPTJForCausalLM

config.json

@@ -33,7 +33,7 @@
   },
   "tie_word_embeddings": false,
   "tokenizer_class": "GPT2Tokenizer",
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.31.0.dev0",
   "use_cache": true,
   "vocab_size": 50400

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2deb85b8df39a508b026978c2bd73905d895282fcbecbb3dc3542d12dd370831
+size 9953894342

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7434e06785762ba921a4b8b5da4fc64e39d428684002d30837a73b66a512d201
+size 9933596497

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3a91f862fd0dca2fc486612759ca91b13e23ec76620d7e59be9f46eaecdc97
+size 4316139691

pytorch_model.bin.index.json

@@ -1,292 +1,292 @@
 {
   "metadata": {
-    "total_size": 12101765568
+    "total_size": 24203531136
   },
   "weight_map": {
-    "lm_head.bias": "pytorch_model-00002-of-00002.bin",
-    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.21.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.21.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.21.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.21.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.22.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.22.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.22.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.22.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.23.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.23.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.23.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.23.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.ln_1.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.24.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.25.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.ln_1.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.26.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.ln_1.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.27.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+    "lm_head.bias": "pytorch_model-00003-of-00003.bin",
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.20.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
   }
 }