Hugging Face's logo

xmadai
/
Llama-3.1-8B-Instruct-xMADai-INT4

Text Generation
Transformers
llama
conversational
Inference Endpoints
4-bit precision
gptq
Model card Files Community
Oscar Wu commited on
Commit
d1867a5
·
1 Parent(s): 16e0a5a

Updated README

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -11,7 +11,7 @@ This repository contains [`meta-llama/Llama-3.1-8B-Instruct`](https://huggingfac
11
 
12
  # Why should I use this model?
13
 
14
- 1. **Accuracy:** This xMADified model is the best **quantized** version of the `meta-llama/Llama-3.1-8B-Instruct` model. We **crush all other quantized** versions (see _Table 1_ below).
15
 
16
  2. **Memory-efficiency:** The full-precision model is around 16 GB, while this xMADified model is only 5.7 GB, making it feasible to run on a 8 GB GPU.
17
 
 
11
 
12
  # Why should I use this model?
13
 
14
+ 1. **Accuracy:** This xMADified model is the best **quantized** version of the `meta-llama/Llama-3.1-8B-Instruct` model. We **crush the most downloaded quantized** version(s) (see _Table 1_ below).
15
 
16
  2. **Memory-efficiency:** The full-precision model is around 16 GB, while this xMADified model is only 5.7 GB, making it feasible to run on a 8 GB GPU.
17