Hugging Face's logo

stan-hua
/
Meta-Llama-3.2-3B-Instruct-LC-GPTQ-W4A16

Safetensors
llama
compressed-tensors
Model card Files Community
Meta-Llama-3.2-3B-Instruct-LC-GPTQ-W4A16
File size: 147 Bytes 
73dd6ec
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
 
DEFAULT_stage:
  DEFAULT_modifiers:
    GPTQModifier:
      targets: Linear
      dampening_frac: 0.01
      ignore: [lm_head]
      scheme: W4A16