初始化项目，由ModelHub XC社区提供模型

Model: bigcode/starcoder-cxo
Source: Original Platform

.gitattributes

@@ -0,0 +1,53 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 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
+ 
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+pytorch_model-00003-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00004-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1 @@
+An ablation of [OctoCoder](https://huggingface.co/bigcode/octocoder) released for research purposes. Generally use OctoCoder, which performs better. Steps: 40

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bigcode/starcoder",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 6144,
+  "n_head": 48,
+  "n_inner": 24576,
+  "n_layer": 40,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "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": "float16",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.31.0.dev0"
+}

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21096aeaf3bd5ca3221329f2bf5bd73902b600e6e42222976ac0090da9c06c1
+size 9957983029

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43fe7e9332a96186fc0ebd77faab52b3299f6ac780ef5b756b14250964b151c9
+size 9857381671

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be996e5ddd1f37f225a46fd4f7ae8b765743d21a35502d020fabd8b547ccbc0e
+size 9857381671

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b8da871ac45e64f0598072b78f3cb43465f9c88d1a35b5053dd54e682ea802
+size 1362327955

pytorch_model.bin.index.json

@@ -0,0 +1,492 @@
+{
+  "metadata": {
+    "total_size": 31034912768
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.20.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.25.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.30.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.38.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.38.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.38.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.38.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.38.ln_1.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.38.ln_1.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.38.ln_2.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.38.ln_2.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.38.mlp.c_fc.bias": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.38.mlp.c_fc.weight": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.38.mlp.c_proj.bias": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.attn.c_attn.bias": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.attn.c_attn.weight": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.attn.c_proj.bias": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.attn.c_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.ln_1.bias": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.ln_1.weight": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.ln_2.bias": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.ln_2.weight": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.mlp.c_fc.bias": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.mlp.c_fc.weight": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.mlp.c_proj.bias": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.ln_f.bias": "pytorch_model-00004-of-00004.bin",
+    "transformer.ln_f.weight": "pytorch_model-00004-of-00004.bin",
+    "transformer.wpe.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00004.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af07a3123a1f4d75dcb85fbdc4c62f9b7873d23fa39c449d2240c3e33eb3ab5
+size 2057423

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}