Hugging Face's logo

compressa-ai
/
Llama-3-8B-Instruct-OmniQuant

Text Generation
Transformers
Safetensors
llama
llama3
omniquant
gptq
triton
conversational
text-generation-inference
Inference Endpoints
4-bit precision
Model card Files Community
Vasily Alexeev commited on
Commit
7807999
·
1 Parent(s): f7750ae

refine table titles

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -49,7 +49,7 @@ Quantized with [OmniQuant](https://github.com/OpenGVLab/OmniQuant).
49
 
50
  ### Summary
51
 
52
- | | Avg Acc Diff on Eng, % (↑) | Avg Acc Diff on Rus, % (↑) | Occupied Memory, % (↓) |
53
  | --------- | -------------------------- | -------------------------- | ---------------------- |
54
  | FP | 0 | 0 | 100 |
55
  | **Quantized** | \-2,11 | \-1,60 | 35,7 |
 
49
 
50
  ### Summary
51
 
52
+ | | Avg acc diff on Eng, % (↑) | Avg acc diff on Rus, % (↑) | Occupied disk space, % (↓) |
53
  | --------- | -------------------------- | -------------------------- | ---------------------- |
54
  | FP | 0 | 0 | 100 |
55
  | **Quantized** | \-2,11 | \-1,60 | 35,7 |