Hugging Face's logo

disi-unibo-nlp
/
pmc-llama-13b-awq

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
4-bit precision
awq
Model card Files Community
alecocc commited on
Commit
9227166
•
1 Parent(s): 3ea4789

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -13,8 +13,7 @@ This repo contains AWQ model files for [PMC_LLaMA_13B](https://huggingface.co/ax
13
 
14
  ### About AWQ
15
 
16
- AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
17
-
18
 
19
  Example of usage with vLLM library:
20
 
 
13
 
14
  ### About AWQ
15
 
16
+ [AWQ](https://arxiv.org/abs/2306.00978) is a rapid, precise, and efficient low-bit weight quantization method, enabling 4-bit quantization with remarkable speed.
 
17
 
18
  Example of usage with vLLM library:
19