Commit 027a2e75 authored by xuxzh1's avatar xuxzh1 🎱
Browse files

update

parent 07438a8b
[submodule "lmdeploy"]
path = lmdeploy
url = http://developer.hpccube.com/codes/aicomponent/lmdeploy.git
tag = dtk23.04-v0.0.13
\ No newline at end of file
url = https://developer.hpccube.com/codes/OpenDAS/lmdeploy
branch = dtk24.04-v0.2.6
\ No newline at end of file
......@@ -71,10 +71,8 @@ cd .. && python3 setup.py install
# <model_format> 保存输出的目标路径(默认./workspace)
# <tp> 用于张量并行的GPU数量应该是2^n
lmdeploy convert --model_name internlm-chat-7b --model_path /path/to/model --model_format hf --tokenizer_path None --dst_path ./workspace_interlm7b --tp 1
# bash界面运行
lmdeploy chat turbomind --model_path ./workspace_interlm7b --tp 1 # 输入问题后执行2次回车进行推理
lmdeploy chat turbomind ./workspace_interlm7b --tp 1 # 输入问题后执行2次回车进行推理
# 服务器网页端运行
......@@ -86,23 +84,20 @@ lmdeploy chat turbomind --model_path ./workspace_interlm7b --tp 1 # 输入
# <tp> 用于张量并行的GPU数量应该是2^n (和模型转换的时候保持一致)
# <restful_api> modelpath_or_server的标志(默认是False)
lmdeploy serve gradio --model_path_or_server ./workspace_interlm7b --server_name {ip} --server_port {port} --batch_size 32 --tp 1 --restful_api False
lmdeploy serve gradio ./workspace_interlm7b --server-name {ip} --server-port {port} --batch_size 32 --tp 1 --restful_api False
在网页上输入{ip}:{port}即可进行对话
```
### 运行 internlm-chat-20b
```bash
# 模型转换
lmdeploy convert --model_name internlm-chat-20b --model_path /path/to/model --model_format hf --tokenizer_path None --dst_path ./workspace_interlm20b --tp 4
# bash界面运行
lmdeploy chat turbomind --model_path ./workspace_interlm20b --tp 4
lmdeploy chat turbomind ./workspace_interlm20b --tp 4
# 服务器网页端运行
在bash端运行:
lmdeploy serve gradio --model_path_or_server ./workspace_interlm20b --server_name {ip} --server_port {port} --batch_size 32 --tp 4 --restful_api False
lmdeploy serve gradio ./workspace_interlm20b --server-name {ip} --server-port {port} --batch_size 32 --tp 4 --restful_api False
在网页上输入{ip}:{port}即可进行对话
```
......
lmdeploy @ 98d217bf
Subproject commit e432dbb0e56caaf319b9c9d7b79eb8106852dc91
Subproject commit 98d217bf91a55fd0a48b5476a55d6399fd65cfd0
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