|
--- |
|
language: zh |
|
widget: |
|
- text: "天下熙熙，" |
|
- text: "清华大学是" |
|
--- |
|
|
|
<h1 align="center"> |
|
CPM-Generate-distill |
|
</h1> |
|
|
|
CPM(Chinese Pre-Trained Language Models), which has 2.6B parameters, made by the research team of Beijing Zhiyuan Institute of artificial intelligence and Tsinghua University @TsinghuaAI. |
|
|
|
[repo: CPM-Generate](https://github.com/TsinghuaAI/CPM-Generate) |
|
The One Thing You Need to Know is this model is not uploaded by official, the conver script is [here](https://github.com/mymusise/CPM-TF2Transformer/blob/main/transfor_CMP.ipynb) |
|
|
|
And the `CPM-Generate-distill` is the distill model of `CPM`. |
|
|
|
|
|
# How to use |
|
|
|
How to use this model directly from the 🤗/transformers library: |
|
|
|
```python |
|
from transformers import TextGenerationPipeline, AutoTokenizer, AutoModelWithLMHead |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("mymusise/CPM-Generate-distill") |
|
model = AutoModelWithLMHead.from_pretrained("mymusise/CPM-Generate-distill") |
|
|
|
text_generater = TextGenerationPipeline(model, tokenizer) |
|
|
|
print(text_generator('清华大学是', max_length=50, do_sample=True, top_p=0.9)) |
|
``` |
|
|
|
|
|
 |
|
|
