shiyemin2 commited on
Commit
4de21b8
1 Parent(s): c58b35b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -3,24 +3,24 @@
3
  license: openrail
4
 
5
  datasets:
6
- - LinkSoul/LLaSA-Audio-Instructions
7
  language:
8
  - zh
9
  - en
10
  ---
11
 
12
 
13
- # LLaSA: Large Language and Speech Assistant
14
 
15
- 开源,可商用的**中英文双语语音-语言助手 LLaSA 以及中英文语音 SFT 数据集 LLaSA-Audio-Instructions**,第一个支持中英文语音-文本多模态对话的开源可商用对话模型。
16
 
17
  <!--
18
  <div align="center">
19
- <img src="https://huggingface.co/LinkSoul/LLaSA-Cllama2/blob/main/meta/preview.jpg" width="40%">
20
  </div>
21
 
22
  -->
23
- ![LLaSA](meta/llasa_preview.jpg)
24
 
25
  ## 基础演示
26
 
@@ -29,29 +29,29 @@ language:
29
  ## 在线试玩
30
 
31
  > Talk is cheap, Show you the Demo.
32
- - [Demo 地址 / HuggingFace Spaces](https://huggingface.co/spaces/LinkSoul/LLaSA)
33
 
34
  ## 资源下载
35
 
36
  - 模型:
37
- - [LLaSA-Chinese-Llama-2-7B](https://huggingface.co/LinkSoul/LLaSA-Cllama2)
38
- - [LLaSA-Baichuan-7B](https://huggingface.co/LinkSoul/LLaSA-Baichuan)
39
 
40
  - 语言模型:
41
  - [Chinese-Llama-2-7b](https://github.com/LinkSoul-AI/Chinese-Llama-2-7b)
42
  - [Baichuan-7B](https://huggingface.co/baichuan-inc/Baichuan-7B)
43
 
44
- - 数据集:[LLaSA-Audio-Instructions](https://huggingface.co/datasets/LinkSoul/LLaSA-Audio-Instructions)
45
 
46
  ## 环境安装
47
  ```shell
48
  # clone the repository
49
- git clone https://github.com/LinkSoul-AI/LLaSA
50
- cd LLaSA
51
 
52
  # install package
53
- conda create -n llasa python=3.10 -y
54
- conda activate llasa
55
  pip install --upgrade pip
56
  pip install -e .
57
  ```
@@ -59,11 +59,11 @@ pip install -e .
59
  ## 快速测试
60
 
61
  ```shell
62
- export LLASA_DEVICE="cuda:0"
63
  python infer.py \
64
  --input_audio_file PATH/TO/YOUR/AUDIO \
65
- --llasa_model PATH/TO/LLaSA/MODEL \
66
- --llasa_audio_tower PATH/TO/WHISPER/MODEL \
67
  --llm_type "Chinese_llama2" or "baichuan" \
68
  ```
69
 
@@ -80,7 +80,7 @@ python infer.py \
80
 
81
  ## 项目协议
82
 
83
- [Apache-2.0 license](https://github.com/LinkSoul-AI/LLaSA/blob/main/LICENSE)
84
 
85
  ## 微信交流群
86
  <!--
 
3
  license: openrail
4
 
5
  datasets:
6
+ - LinkSoul/LLaSM-Audio-Instructions
7
  language:
8
  - zh
9
  - en
10
  ---
11
 
12
 
13
+ # LLaSM: Large Language and Speech Model
14
 
15
+ 开源,可商用的**中英文双语语音-语言助手 LLaSM 以及中英文语音 SFT 数据集 LLaSM-Audio-Instructions**,第一个支持中英文语音-文本多模态对话的开源可商用对话模型。
16
 
17
  <!--
18
  <div align="center">
19
+ <img src="https://huggingface.co/LinkSoul/LLaSM-Cllama2/blob/main/meta/preview.jpg" width="40%">
20
  </div>
21
 
22
  -->
23
+ ![LLaSM](meta/llasm_preview.jpg)
24
 
25
  ## 基础演示
26
 
 
29
  ## 在线试玩
30
 
31
  > Talk is cheap, Show you the Demo.
32
+ - [Demo 地址 / HuggingFace Spaces](https://huggingface.co/spaces/LinkSoul/LLaSM)
33
 
34
  ## 资源下载
35
 
36
  - 模型:
37
+ - [LLaSM-Chinese-Llama-2-7B](https://huggingface.co/LinkSoul/LLaSM-Cllama2)
38
+ - [LLaSM-Baichuan-7B](https://huggingface.co/LinkSoul/LLaSM-Baichuan)
39
 
40
  - 语言模型:
41
  - [Chinese-Llama-2-7b](https://github.com/LinkSoul-AI/Chinese-Llama-2-7b)
42
  - [Baichuan-7B](https://huggingface.co/baichuan-inc/Baichuan-7B)
43
 
44
+ - 数据集:[LLaSM-Audio-Instructions](https://huggingface.co/datasets/LinkSoul/LLaSM-Audio-Instructions)
45
 
46
  ## 环境安装
47
  ```shell
48
  # clone the repository
49
+ git clone https://github.com/LinkSoul-AI/LLaSM
50
+ cd LLaSM
51
 
52
  # install package
53
+ conda create -n llasm python=3.10 -y
54
+ conda activate llasm
55
  pip install --upgrade pip
56
  pip install -e .
57
  ```
 
59
  ## 快速测试
60
 
61
  ```shell
62
+ export LLASM_DEVICE="cuda:0"
63
  python infer.py \
64
  --input_audio_file PATH/TO/YOUR/AUDIO \
65
+ --llasm_model PATH/TO/LLaSM/MODEL \
66
+ --llasm_audio_tower PATH/TO/WHISPER/MODEL \
67
  --llm_type "Chinese_llama2" or "baichuan" \
68
  ```
69
 
 
80
 
81
  ## 项目协议
82
 
83
+ [Apache-2.0 license](https://github.com/LinkSoul-AI/LLaSM/blob/main/LICENSE)
84
 
85
  ## 微信交流群
86
  <!--