Hugging Face's logo

Spaces:
chrispie
/
llama-hqq-1-bit
Runtime error

App Files Community
chrispie commited on
Commit
49b5be2
•
1 Parent(s): 37b8ea9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -13,5 +13,6 @@ pipeline_tag: text-generation
13
  ---
14
 
15
  Demo for HQQ 1-bit quantized (binary weights) Llama2-7B-chat model using a low-rank adapter to improve the performance (referred to as HQQ+).
 
16
 
17
  https://huggingface.co/mobiuslabsgmbh/Llama-2-7b-chat-hf_1bitgs8_hqq
 
13
  ---
14
 
15
  Demo for HQQ 1-bit quantized (binary weights) Llama2-7B-chat model using a low-rank adapter to improve the performance (referred to as HQQ+).
16
+ You will need a GPU for this.
17
 
18
  https://huggingface.co/mobiuslabsgmbh/Llama-2-7b-chat-hf_1bitgs8_hqq