Skip to content

GitLab

Commit 59edee96 authored by weishb's avatar weishb
Browse files

新增transformers推理说明

parent 997d1621
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 1 deletion
README.md
View file @ 59edee96
...@@ -109,6 +109,8 @@ response = tokenizer.decode( ...@@ -109,6 +109,8 @@ response = tokenizer.decode(
print(response) print(response)
``` ```
**如果用transformers推理Spark-Scilit-X1-13B，需要额外修改模型的config.json文件，将"_attn_implementation":"flash_attention_2"改成"_attn_implementation":"eager"**
### vLLM ### vLLM
#### 单机推理 #### 单机推理
```bash ```bash
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment