Add model files
Browse files- README.md +28 -3
- config.json +7 -0
- generation_config.json +6 -0
- model.bin +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
- vocabulary.json +0 -0
README.md
CHANGED
@@ -1,3 +1,28 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
tags:
|
5 |
+
- generation
|
6 |
+
- ctranslate2
|
7 |
+
license: mit
|
8 |
+
base_model: openai/gpt2
|
9 |
+
base_model_relation: quantized
|
10 |
+
---
|
11 |
+
# gpt2-ct2
|
12 |
+
|
13 |
+
This is a version of [`openai-community/gpt2`](https://huggingface.co/openai-community/gpt2)
|
14 |
+
converted for use with [CTranslate2](https://github.com/OpenNMT/CTranslate2).
|
15 |
+
|
16 |
+
The conversion was performed using the following command:
|
17 |
+
|
18 |
+
```
|
19 |
+
ct2-transformers-converter --model openai-community/gpt2 --output_dir gpt2-ct2 \
|
20 |
+
--copy_files generation_config.json tokenizer_config.json tokenizer.json vocab.json
|
21 |
+
```
|
22 |
+
|
23 |
+
## License
|
24 |
+
This adaptation is based on [`openai-community/gpt2`](https://huggingface.co/openai-community/gpt2),
|
25 |
+
originally provided under the MIT License.
|
26 |
+
Modifications were made for compatibility with CTranslate2.
|
27 |
+
Despite these modifications, this adapted version continues to be distributed under the MIT License,
|
28 |
+
honoring the original licensing terms.
|
config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"layer_norm_epsilon": null,
|
5 |
+
"multi_query_attention": true,
|
6 |
+
"unk_token": "<|endoftext|>"
|
7 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 50256,
|
3 |
+
"eos_token_id": 50256,
|
4 |
+
"transformers_version": "4.26.0.dev0",
|
5 |
+
"_from_model_config": true
|
6 |
+
}
|
model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d2e2db92579173a4b3d4855258aca5621e6be70415d71e66ea21288739b1a81
|
3 |
+
size 497767709
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model_max_length": 1024}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocabulary.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|