Commit e55e5806 authored by suily's avatar suily
Browse files

修改README

parent 7cc1d870
......@@ -173,7 +173,7 @@ huggingface-cli download --resume-download lmsys/vicuna-7b-v1.5 --local-dir chec
```
2-2、下载ChatGLM3-6b权重
* [scnet](http://113.200.138.88:18080/aimodels/chatglm3-6b)
* [官网链接](https://huggingface.co/lmsys/vicuna-7b-v1.5)
* [官网链接](https://huggingface.co/THUDM/chatglm3-6b/tree/main)
* 代码下载(huggingface)
```
cd VTimeLLM
......@@ -205,11 +205,11 @@ VTimeLLM基于Vicuna v1.5训练了英文版本,存储为vtimellm-vicuna-v1-5-7
* [官网链接](https://cloud.tsinghua.edu.cn/d/6db5d02883124826aa6f/?p=%2Fcheckpoints&mode=list)
解压VTimeLLM权重的代码如下:
'''
```
cd VTimeLLM/checkpoints
tar -xzvf vtimellm-vicuna-v1-5-7b.tar.gz
#tar -xzvf vtimellm-chatglm3-6b.tar.gz
'''
# tar -xzvf vtimellm-chatglm3-6b.tar.gz
```
以基于Vicuna v1.5的VTimeLLM为例,模型目录结构如下:
```
VTimeLLM:
......@@ -239,7 +239,7 @@ HIP_VISIBLE_DEVICES=0 python -m vtimellm.inference \
## result
推理运行的默认推理结果为:
<div align=center>
<video src="./doc/inference_result.png"/>
<img src="./doc/inference_result.png"/>
</div>
### 精度
......@@ -251,7 +251,7 @@ HIP_VISIBLE_DEVICES=0 python -m vtimellm.inference \
## 应用场景
### 算法类别
`视频生成`
`视频理解`
### 热点应用行业
`家具,电商,医疗,广媒,教育`
## 预训练权重
......
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