Skip to content

GitLab

Commit bd3521b0 authored by xuxzh1's avatar xuxzh1 🎱
Browse files

update readme

parent 077720a0
Hide whitespace changes
Inline Side-by-side
Showing with 10 additions and 0 deletions
README.md
View file @ bd3521b0
...@@ -68,6 +68,14 @@ cd .. && python3 setup.py install ...@@ -68,6 +68,14 @@ cd .. && python3 setup.py install
支持模型包括：LLama-7B、LLama-13B、LLama-30B、LLama-65B、LLama2-7B、LLama2-13B、LLama2-70B 支持模型包括：LLama-7B、LLama-13B、LLama-30B、LLama-65B、LLama2-7B、LLama2-13B、LLama2-70B
> [!CAUTION]
>
> 最新lmdepoly推理llama1：
>
> 1.LLama-13B：需要在tokenizer_config.json中添加“unk_token”对应的值为"<unk>“
>
> 2.LLama-65B：config文件中“architectures”对应的[LlAmaForCausalLM]改成[LlamaForCausalLM]
### 运行 LLama-7b ### 运行 LLama-7b
``` ```
# 模型转换 # 模型转换
...@@ -237,3 +245,5 @@ https://developer.hpccube.com/codes/modelzoo/llama_lmdeploy ...@@ -237,3 +245,5 @@ https://developer.hpccube.com/codes/modelzoo/llama_lmdeploy
## 参考资料 ## 参考资料
https://github.com/InternLM/LMDeploy https://github.com/InternLM/LMDeploy
##
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