vivicai commited on
Commit
d4ffbf9
1 Parent(s): e6c43bc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +42 -0
README.md CHANGED
@@ -1,3 +1,45 @@
1
  ---
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+ <div style="width: 100%;">
5
+ <img src="http://x-pai.algolet.com/bot/img/logo_core.png" alt="TigerBot" style="width: 20%; display: block; margin: auto;">
6
+ </div>
7
+ <p align="center">
8
+ <font face="黑体" size=5"> A cutting-edge foundation for your very own LLM. </font>
9
+ </p>
10
+ <p align="center">
11
+ 🌐 <a href="https://tigerbot.com/" target="_blank">TigerBot</a> • 🤗 <a href="https://huggingface.co/TigerResearch" target="_blank">Hugging Face</a>
12
+ </p>
13
+
14
+
15
+
16
+ This is a 4-bit EXL2 version of the [tigerbot-13b-chat-v5-4k](https://huggingface.co/TigerResearch/tigerbot-13b-chat-v5-4k).
17
+
18
+ It was quantized to 4bit using: https://github.com/turboderp/exllamav2
19
+
20
+ ## How to download and use this model in github: https://github.com/TigerResearch/TigerBot
21
+
22
+ Here are commands to clone the TigerBot and install.
23
+
24
+ ```
25
+ conda create --name tigerbot python=3.8
26
+ conda activate tigerbot
27
+ conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
28
+
29
+ git clone https://github.com/TigerResearch/TigerBot
30
+ cd TigerBot
31
+ pip install -r requirements.txt
32
+ ```
33
+
34
+ Inference with command line interface
35
+
36
+ infer with exllamav2
37
+ ```
38
+ # install exllamav2
39
+ git clone https://github.com/turboderp/exllamav2
40
+ cd exllamav2
41
+ pip install -r requirements.txt
42
+
43
+ # infer command
44
+ CUDA_VISIBLE_DEVICES=0 python other_infer/exllamav2_hf_infer.py --model_path TigerResearch/tigerbot-13b-chat-v5-4bit-exl2
45
+ ```