Hugging Face's logo

TheBloke
/
VicUnlocked-30B-LoRA-GPTQ

Text Generation
Transformers
Safetensors
llama
text-generation-inference
4-bit precision
gptq
Model card Files Community
2
TheBloke commited on
Commit
6671e7e
•
1 Parent(s): d438224

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -7,7 +7,7 @@ datasets:
7
 
8
  # VicUnlocked-30B-LoRA GPTQ
9
 
10
- This is GPTQ format quantised 4bit models of [Neko Institute of Science's VicUnLocked 30B LoRA](https://huggingface.co/Neko-Institute-of-Science/VicUnLocked-30b-LoRA).
11
 
12
  The files in this repo are the result of merging the above LoRA with the original LLaMA 30B, then quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
13
 
@@ -37,7 +37,7 @@ Open the text-generation-webui UI as normal.
37
 
38
  **Compatible file - VicUnlocked-30B-LoRA-GPTQ-4bit.act-order.safetensors**
39
 
40
- In the `main` branch - the default one - you will find `VicUnlocked-30B-LoRA-GPTQ-4bit-128g.compat.no-act-order.safetensors`
41
 
42
  This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility
43
 
 
7
 
8
  # VicUnlocked-30B-LoRA GPTQ
9
 
10
+ This repo contains a GPTQ format quantised 4bit model for [Neko Institute of Science's VicUnLocked 30B LoRA](https://huggingface.co/Neko-Institute-of-Science/VicUnLocked-30b-LoRA).
11
 
12
  The files in this repo are the result of merging the above LoRA with the original LLaMA 30B, then quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
13
 
 
37
 
38
  **Compatible file - VicUnlocked-30B-LoRA-GPTQ-4bit.act-order.safetensors**
39
 
40
+ In the `main` branch - the default one - you will find `VicUnlocked-30B-LoRA-GPTQ-4bit.act-order.safetensors`
41
 
42
  This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility
43