31 lines
899 B
Markdown
31 lines
899 B
Markdown
|
---
|
||
|
|
license: bigscience-bloom-rail-1.0
|
||
|
|
---
|
||
|
|
|
||
|
|
https://github.com/zejunwang1/bloom_tuning
|
||
|
|
|
||
|
|
可以通过如下代码调用 bloom-820m-chat 模型来生成对话：
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import BloomTokenizerFast, BloomForCausalLM
|
||
|
|
|
||
|
|
model_name_or_path = "WangZeJun/bloom-820m-chat"
|
||
|
|
|
||
|
|
tokenizer = BloomTokenizerFast.from_pretrained(model_name_or_path)
|
||
|
|
model = BloomForCausalLM.from_pretrained(model_name_or_path).cuda()
|
||
|
|
model = model.eval()
|
||
|
|
|
||
|
|
input_pattern = "{}</s>"
|
||
|
|
text = "你好"
|
||
|
|
input_ids = tokenizer(input_pattern.format(text), return_tensors="pt").input_ids
|
||
|
|
input_ids = input_ids.cuda()
|
||
|
|
|
||
|
|
outputs = model.generate(input_ids, do_sample=True, max_new_tokens=1024, top_p=0.85,
|
||
|
|
temperature=0.3, repetition_penalty=1.2, eos_token_id=tokenizer.eos_token_id)
|
||
|
|
|
||
|
|
input_ids_len = input_ids.size(1)
|
||
|
|
response_ids = outputs[0][input_ids_len:]
|
||
|
|
response = tokenizer.decode(response_ids)
|
||
|
|
print(response)
|
||
|
|
```
|