starlight-apk/Qwen
1
0
Fork 0
mirror of https://github.com/QwenLM/Qwen.git synced 2026-05-20 16:35:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README_JA.md

Browse Source
This commit is contained in:
Yang An
2023-09-12 11:31:51 +08:00
committed by GitHub
parent ab67ac050e
commit 74541672bd
1 changed files with 11 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
README_JA.md
View File

@@ -176,28 +176,19 @@ print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
ModelScope は、MaaS（Model-as-a-Service） のためのオープンソースプラットフォームであり、AI 開発者に柔軟で費用対効果の高いモデルサービスを提供します。同様に、以下のように ModelScope でモデルを実行することができます: ModelScope は、MaaS（Model-as-a-Service） のためのオープンソースプラットフォームであり、AI 開発者に柔軟で費用対効果の高いモデルサービスを提供します。同様に、以下のように ModelScope でモデルを実行することができます:
```python ```python
import os from modelscope import AutoModelForCausalLM, AutoTokenizer
from modelscope.pipelines import pipeline from modelscope import GenerationConfig
from modelscope.utils.constant import Tasks
from modelscope import snapshot_download
model_id = 'QWen/qwen-7b-chat' tokenizer = AutoTokenizer.from_pretrained("qwen/Qwen-7B-Chat", revision='v1.0.5', trust_remote_code=True)
revision = 'v1.0.0' model = AutoModelForCausalLM.from_pretrained("qwen/Qwen-7B-Chat", revision='v1.0.5', device_map="auto", trust_remote_code=True, fp16=True).eval()
model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B-Chat", revision='v1.0.5', trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参
model_dir = snapshot_download(model_id, revision) response, history = model.chat(tokenizer, "你好", history=None)
print(response)
pipe = pipeline( response, history = model.chat(tokenizer, "浙江的省会在哪里？", history=history)
task=Tasks.chat, model=model_dir, device_map='auto') print(response)
history = None response, history = model.chat(tokenizer, "它有什么好玩的景点", history=history)
print(response)
text = '浙江省の省都はどこですか？'
results = pipe(text, history=history)
response, history = results['response'], results['history']
print(f'Response: {response}')
text = '何がそんなに面白いのか？'
results = pipe(text, history=history)
response, history = results['response'], results['history']
print(f'Response: {response}')
``` ```
<br> <br>