Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
compressed-tensors
leonardlin's picture
Upload folder using huggingface_hub
fdf6d51 verified
raw
history blame contribute delete
136 Bytes
default_stage:
default_modifiers:
QuantizationModifier:
ignore: [lm_head]
targets: [Linear]
scheme: FP8_DYNAMIC