初始化项目，由ModelHub XC社区提供模型

Model: MiniLLM/teacher-gpt2-1.5B
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,30 @@
+---
+license: apache-2.0
+datasets:
+- databricks/databricks-dolly-15k
+language:
+- en
+metrics:
+- rouge
+base_model:
+- openai-community/gpt2-xl
+pipeline_tag: text-generation
+---
+# teacher-gpt2-1.5B
+
+[paper](https://arxiv.org/abs/2306.08543) | [code](https://github.com/microsoft/LMOps/tree/main/minillm)
+
+**teacher-gpt2-1.5B** is a gpt2-xlarge (1.5B) model supervised fine-tuned on [databricks-dolly-15k](https://huggingface.co/datasets/aisquared/databricks-dolly-15k).
+
+It is used as the teacher model for MiniLLM series.
+
+
+## Citation
+```
+@inproceedings{minillm,
+  title={MiniLLM: Knowledge Distillation of Large Language Models},
+  author={Gu, Yuxian and Dong, Li and Wei, Furu and Huang, Minlie},
+  booktitle={Proceedings of ICLR},
+  year={2024}
+}
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "/data/yuxian/MiniLLM_dir/results/gpt2/train/sft/gpt2-xlarge",
+  "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": 1024,
+  "n_embd": 1600,
+  "n_head": 25,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "output_past": true,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.42.0.dev0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8ba111de317bcd01def63e7693132d0801b7285ff52c22037a42870ff0091a
+size 4959984418

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0baff8cfdb940e6c7621eb5ae7b5eec3f615c247fcd291a165487ec40eccce4
+size 1270652090

pytorch_model.bin.index.json

@@ -0,0 +1,588 @@
+{
+  "metadata": {
+    "total_size": 6230444800
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.37.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.40.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.40.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.41.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.42.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.43.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.44.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.45.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.46.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.ln_2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.ln_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.47.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.c_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.ln_2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.c_proj.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.wpe.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}