clef-flash-4bit / generation_config.json

Clef-Flash pre-quantized to 4-bit (bitsandbytes nf4, fp16 compute) for small GPUs

af04336 verified 18 days ago

116 Bytes

{
  "_from_model_config": true,
  "eos_token_id": 248044,
  "transformers_version": "5.19.0",
  "use_cache": true
}