Hugging Face's logo

CalamitousFelicitousness
/
Llama-3.3-70B-Instruct-W8A8-INT8

Safetensors
llama
8-bit precision
compressed-tensors
Model card Files Community
1
Llama-3.3-70B-Instruct-W8A8-INT8
File size: 119 Bytes 
52fc842
 
 
 
 
 
 
1
2
3
4
5
6
7
 
DEFAULT_stage:
  DEFAULT_modifiers:
    GPTQModifier:
      targets: Linear
      ignore: [lm_head]
      scheme: W8A8