Add model and tokenizer.

config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 5120,
+  "n_head": 40,
+  "n_inner": null,
+  "n_layer": 40,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "use_cache": true,
+  "vocab_size": 50272
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.27.1"
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d20bcb9a28075f71dd23833b181ed2c5f5e487ba7f4dcf37a2a969fb602bbbe
+size 9915043053

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2247cc3ce22a37c63846d8d555f7a147bc583323bef598c0f2edf22457a0ab2
+size 9678360353

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f808bf83a8c18208d2dac9a29971f84bfea4b89c9bb5a632ca1c43a61dc6363
+size 9682535513

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04a8981a06494721724635a362f8f37bbba7e275b8879d7f3d272b5c9444675
+size 9997128229

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8acaf6cb13e72aa4c63c2445893b9d57285d1955fec4c16b1a923b082e63bf73
+size 9787413665

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae3fe13782cadbe83a2f2d26d82c44b7ce112cde50ec629d52f0c1316de008b
+size 3550887252

pytorch_model.bin.index.json

@@ -0,0 +1,572 @@
+{
+  "metadata": {
+    "total_size": 52464394400.0
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.0.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.10.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.2.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.20.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.3.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.30.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.30.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.30.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.30.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.38.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.38.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.38.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.38.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.38.ln_2.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.ln_2.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.attn.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.ln_1.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.ln_1.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.ln_2.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.ln_2.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.4.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.7.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.ln_f.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.ln_f.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.wpe.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00006.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": "<mask>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}