Hugging Face's logo

mgoin
/
DeepSeek-Coder-V2-Lite-Instruct-FP8

Safetensors
deepseek_v2
custom_code
Model card Files Community
DeepSeek-Coder-V2-Lite-Instruct-FP8
File size: 144 Bytes 
5a429b9
 
 
 
 
 
 
1
2
3
4
5
6
7
 
DEFAULT_stage:
  DEFAULT_modifiers:
    QuantizationModifier:
      ignore: [lm_head, 're:.*mlp.gate$']
      targets: Linear
      scheme: FP8