Hugging Face's logo

Minami-su
/
XVERSE-7B_2bit

Text Generation
Transformers
Safetensors
llama
2bit
XVERSE
Inference Endpoints
text-generation-inference
Model card Files Community
Minami-su commited on
Commit
97a9f85
•
1 Parent(s): 377ef6e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,6 +6,6 @@ tags:
6
  - XVERSE
7
  ---
8
 
9
- You can run it on 2G mem GPU,quantize base QuIP# method, a weights-only quantization method that is able to achieve near fp16 performance using only 2 bits per weight.
10
 
11
  url:https://github.com/Cornell-RelaxML/quip-sharp/tree/release20231203
 
6
  - XVERSE
7
  ---
8
 
9
+ You can run it on 4G mem GPU,quantize base QuIP# method, a weights-only quantization method that is able to achieve near fp16 performance using only 2 bits per weight.
10
 
11
  url:https://github.com/Cornell-RelaxML/quip-sharp/tree/release20231203