Hugging Face's logo

Thireus
/
Vicuna13B-v1.1-8bit-128g

Text Generation
Transformers
PyTorch
llama
vicuna
text-generation-inference
Inference Endpoints
Model card Files Community
5
Thireus commited on
Commit
95c4815
•
1 Parent(s): 88124e3

Benchmark table fix

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -43,7 +43,7 @@ Refs:
43
  Best results in **bold**.
44
 
45
  | Model | wikitext2 PPL | c4 PPL | ptb PPL | C4-VRAM |
46
- |---|---|---|---|---|---|
47
  | 4bit-GPTQ - TheBloke/vicuna-13B-1.1-GPTQ-4bit-128g | 8.517391204833984 | **7.058407783508301** | 20.888103485107422 | **8670.26953125** |
48
  | 8bit-GPTQ - Thireus/Vicuna13B-v1.1-8bit-128g | **8.508771896362305** | 7.105874538421631 | **20.75649070739746** | 14840.26171875 |
49
 
 
43
  Best results in **bold**.
44
 
45
  | Model | wikitext2 PPL | c4 PPL | ptb PPL | C4-VRAM |
46
+ |---|---|---|---|---|
47
  | 4bit-GPTQ - TheBloke/vicuna-13B-1.1-GPTQ-4bit-128g | 8.517391204833984 | **7.058407783508301** | 20.888103485107422 | **8670.26953125** |
48
  | 8bit-GPTQ - Thireus/Vicuna13B-v1.1-8bit-128g | **8.508771896362305** | 7.105874538421631 | **20.75649070739746** | 14840.26171875 |
49