Hugging Face's logo

Zyphra
/
Zamba2-2.7B-instruct

Text Generation
Transformers
Safetensors
zamba2
conversational
Model card Files
xet
Community
3
qanthony-z commited on
Commit
94a2380
·
verified ·
1 Parent(s): 2f00671

add mt bench barchart

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -48,7 +48,9 @@ print((tokenizer.decode(outputs[0])))
48
 
49
  Zamba2-2.7B-Instruct punches dramatically above its weight, achieving extremely strong instruction-following benchmark scores, significantly outperforming Gemma2-2B-Instruct of the same size and outperforming Mistral-7B-Instruct in most metrics.
50
 
51
- <img src="https://cdn-uploads.huggingface.co/production/uploads/64e40335c0edca443ef8af3e/wXFMLXZA2-xz2PDyUMwTI.png" width="600"/>
 
 
52
 
53
 
54
  | Model | Size | MT-Bench | IFEval |
 
48
 
49
  Zamba2-2.7B-Instruct punches dramatically above its weight, achieving extremely strong instruction-following benchmark scores, significantly outperforming Gemma2-2B-Instruct of the same size and outperforming Mistral-7B-Instruct in most metrics.
50
 
51
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/65bc13717c6ad1994b6619e9/ml2i8lHK4ojqBh_xV50L9.png" width="600"/>
52
+
53
+
54
 
55
 
56
  | Model | Size | MT-Bench | IFEval |