Merge branch 'main' of https://huggingface.co/uer/gpt2-distil-chinese-cluecorpussmall into main
Browse files
README.md
CHANGED
|
@@ -8,11 +8,11 @@ widget:
|
|
| 8 |
---
|
| 9 |
|
| 10 |
|
| 11 |
-
# Chinese GPT2 Model
|
| 12 |
|
| 13 |
## Model description
|
| 14 |
|
| 15 |
-
The model is used to generate Chinese texts. You can download the model either from the [GPT2-Chinese Github page](https://github.com/Morizeyao/GPT2-Chinese), or via HuggingFace from the link [gpt2-distil-chinese-cluecorpussmall](https://huggingface.co/uer/gpt2-distil-chinese-cluecorpussmall).
|
| 16 |
|
| 17 |
## How to use
|
| 18 |
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
|
| 11 |
+
# Chinese GPT2-distil Model
|
| 12 |
|
| 13 |
## Model description
|
| 14 |
|
| 15 |
+
The model is used to generate Chinese texts. You can download the model either from the [GPT2-Chinese Github page](https://github.com/Morizeyao/GPT2-Chinese), or via HuggingFace from the link [gpt2-distil-chinese-cluecorpussmall](https://huggingface.co/uer/gpt2-distil-chinese-cluecorpussmall). The model is called GPT2-distil because the configuration of model follows [distilgpt2](https://huggingface.co/distilgpt2), which has 6 layers, 768 dimension, and 12 heads. The pre-training does not involve the supervision of larger models.
|
| 16 |
|
| 17 |
## How to use
|
| 18 |
|