Hugging Face's logo

Adun
/
openthaigpt-1.0.0-7b-chat-beta-gptq-4bit

Text Generation
Transformers
llama
Inference Endpoints
text-generation-inference
Model card Files Community
Adun commited on
Commit
326c674
•
1 Parent(s): 70f1d0d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -4,6 +4,9 @@ for GPU RAM 4 GB. ( recommend for GPU RAM 6GB)
4
  convert from FP16 model
5
  #### Adun/openthaigpt-1.0.0-beta-7b-ckpt-hf
6
 
 
 
 
7
  ![System diagram](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj9JigxheqLQVKtolNLJeNzly1Z-DhbZTfi-ozNtQWveAwfcosa03UpZ2AMxmYfaVfzusGYLVV7HNnQczHwPYwZ6TTd5giknxQja-RVNY9l-MIm-WTfHTZ0A3555sqFmhE6Sh0vP4eYs2nmkw6l-ZvrbTzbu2Y8P8WqznSHAjzXCHG97oDF4lpGOJLVU5Mv/w640-h360/openthaigpt-4bit-NVIDIA-RTX2060.jpg)
8
 
9
  ![System diagram](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEikhMOUYD0TESbc8MbmBvfJ-9wd98EtPaaOhVw2rHbhn_KSGhTAQ4pQRqbdfzqM_LyI0_KN0tvbUkU9un_JApIjBiXdqdIvsZC0aSok7seDsaYl5PzTfm3ezg1TNiu-WvrbwZK-eR2-SuSjnG0lXCyb3It23KLPcerEkAanP0LJvm8tbWb5apPBiAtu8Ck8/s843/q5-8.png)
 
4
  convert from FP16 model
5
  #### Adun/openthaigpt-1.0.0-beta-7b-ckpt-hf
6
 
7
+ #### mode info.
8
+ https://aiotplatform.blogspot.com/2023/09/openthaigpt-7b-beta-gptq-4-bit.html
9
+
10
  ![System diagram](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj9JigxheqLQVKtolNLJeNzly1Z-DhbZTfi-ozNtQWveAwfcosa03UpZ2AMxmYfaVfzusGYLVV7HNnQczHwPYwZ6TTd5giknxQja-RVNY9l-MIm-WTfHTZ0A3555sqFmhE6Sh0vP4eYs2nmkw6l-ZvrbTzbu2Y8P8WqznSHAjzXCHG97oDF4lpGOJLVU5Mv/w640-h360/openthaigpt-4bit-NVIDIA-RTX2060.jpg)
11
 
12
  ![System diagram](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEikhMOUYD0TESbc8MbmBvfJ-9wd98EtPaaOhVw2rHbhn_KSGhTAQ4pQRqbdfzqM_LyI0_KN0tvbUkU9un_JApIjBiXdqdIvsZC0aSok7seDsaYl5PzTfm3ezg1TNiu-WvrbwZK-eR2-SuSjnG0lXCyb3It23KLPcerEkAanP0LJvm8tbWb5apPBiAtu8Ck8/s843/q5-8.png)