Hugging Face's logo

noneUsername
/
Mistral-Nemo-Instruct-2407-W8A8-Dynamic-Per-Token

Safetensors
mistral
8-bit precision
Model card Files Community
noneUsername commited on
Commit
e3d0951
•
1 Parent(s): 658687b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -8,4 +8,6 @@ MAX_SEQUENCE_LENGTH = 8192
8
 
9
  smoothing_strength=0.8
10
 
11
- I will verify the validity of the model and update the readme as soon as possible.
 
 
 
8
 
9
  smoothing_strength=0.8
10
 
11
+ I will verify the validity of the model and update the readme as soon as possible.
12
+
13
+ edit: The performance in my ERP test was comparable to Mistral-Nemo-Instruct-2407-GPTQ-INT8, which I consider a successful quantization.