初始化项目,由ModelHub XC社区提供模型
Model: Gaivoronsky/ruGPT-3.5-13B-fp16 Source: Original Platform
This commit is contained in:
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -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
|
||||||
35
README.md
Normal file
35
README.md
Normal file
@@ -0,0 +1,35 @@
|
|||||||
|
---
|
||||||
|
license: mit
|
||||||
|
language:
|
||||||
|
- ru
|
||||||
|
- en
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
inference: false
|
||||||
|
tags:
|
||||||
|
- gpt3
|
||||||
|
- transformers
|
||||||
|
- pytorch
|
||||||
|
---
|
||||||
|
This is a generative model converted to fp16 format based on [ai-forever/ruGPT-3.5-13B](https://huggingface.co/ai-forever/ruGPT-3.5-13B)
|
||||||
|
|
||||||
|
## Examples of usage
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import GPT2LMHeadModel, AutoTokenizer
|
||||||
|
|
||||||
|
model = GPT2LMHeadModel.from_pretrained('Gaivoronsky/ruGPT-3.5-13B-fp16')
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained('Gaivoronsky/ruGPT-3.5-13B-fp16')
|
||||||
|
model = model.half()
|
||||||
|
model = model.to('cuda')
|
||||||
|
|
||||||
|
request = "Человек: Сколько весит жираф? Помощник: "
|
||||||
|
encoded_input = tokenizer(request, return_tensors='pt', \
|
||||||
|
add_special_tokens=False).to('cuda')
|
||||||
|
output = model.generate(
|
||||||
|
**encoded_input,
|
||||||
|
num_beams=2,
|
||||||
|
do_sample=True,
|
||||||
|
max_new_tokens=100
|
||||||
|
)
|
||||||
|
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
||||||
|
```
|
||||||
33
config.json
Normal file
33
config.json
Normal file
@@ -0,0 +1,33 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "ruGPT-3.5-13B-fp16",
|
||||||
|
"activation_function": "gelu_new",
|
||||||
|
"architectures": [
|
||||||
|
"GPT2LMHeadModel"
|
||||||
|
],
|
||||||
|
"attn_pdrop": 0.1,
|
||||||
|
"bos_token_id": 50256,
|
||||||
|
"embd_pdrop": 0.1,
|
||||||
|
"eos_token_id": 50256,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"layer_norm_epsilon": 1e-05,
|
||||||
|
"model_type": "gpt2",
|
||||||
|
"n_ctx": 2048,
|
||||||
|
"n_embd": 5120,
|
||||||
|
"n_head": 40,
|
||||||
|
"n_inner": null,
|
||||||
|
"n_layer": 40,
|
||||||
|
"n_positions": 2048,
|
||||||
|
"reorder_and_upcast_attn": false,
|
||||||
|
"resid_pdrop": 0.1,
|
||||||
|
"scale_attn_by_inverse_layer_idx": false,
|
||||||
|
"scale_attn_weights": true,
|
||||||
|
"summary_activation": null,
|
||||||
|
"summary_first_dropout": 0.1,
|
||||||
|
"summary_proj_to_labels": true,
|
||||||
|
"summary_type": "cls_index",
|
||||||
|
"summary_use_proj": true,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.31.0.dev0",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 50272
|
||||||
|
}
|
||||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 50256,
|
||||||
|
"eos_token_id": 50256,
|
||||||
|
"transformers_version": "4.31.0.dev0"
|
||||||
|
}
|
||||||
49996
merges.txt
Normal file
49996
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model-00001-of-00003.bin
Normal file
3
pytorch_model-00001-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b737be815ff85ccb1106a55045b4c57d90917bec0ade382d4646fa2d7618353c
|
||||||
|
size 9975022143
|
||||||
3
pytorch_model-00002-of-00003.bin
Normal file
3
pytorch_model-00002-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:203a23d0a0de6d6328523a7799ea362364ec9502de4008818741f952968a86b1
|
||||||
|
size 9858778951
|
||||||
3
pytorch_model-00003-of-00003.bin
Normal file
3
pytorch_model-00003-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8baed9ec056bba50e02f397252322d0feebbbb3d553a27d79cd0aabbd910bbc8
|
||||||
|
size 5873292803
|
||||||
492
pytorch_model.bin.index.json
Normal file
492
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,492 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 25706926080
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.15.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.15.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.15.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.15.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.15.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.15.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.15.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.15.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.15.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.15.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.16.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.17.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.18.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.19.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.20.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.20.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.21.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.22.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.23.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.25.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.26.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.27.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.28.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.29.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.30.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.30.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.30.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.30.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.30.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.30.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.30.ln_2.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.30.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.30.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.30.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
|
||||||
|
"transformer.h.30.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.30.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.ln_2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.31.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.ln_2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.32.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.ln_2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.33.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.ln_2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.34.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.ln_2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.35.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.ln_2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.36.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.ln_2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.37.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.ln_2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.38.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.ln_2.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.39.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
|
||||||
|
"transformer.wpe.weight": "pytorch_model-00001-of-00003.bin",
|
||||||
|
"transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
|
||||||
|
}
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"mask_token": "<mask>",
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<pad>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
100335
tokenizer.json
Normal file
100335
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
41
tokenizer_config.json
Normal file
41
tokenizer_config.json
Normal file
@@ -0,0 +1,41 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"bos_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"clean_up_tokenization_spaces": true,
|
||||||
|
"eos_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"errors": "replace",
|
||||||
|
"mask_token": "<mask>",
|
||||||
|
"model_max_length": 1000000000000000019884624838656,
|
||||||
|
"pad_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<pad>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"tokenizer_class": "GPT2Tokenizer",
|
||||||
|
"unk_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user