Hugging Face's logo

BirdL
/
DONOTUSE

PEFT
Model card Files Community
Edit model card

Version 1 of the DONOTUSE Series of Models, a study on the philosopy of hate and their effects on AI.

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • load_in_8bit: True
  • load_in_4bit: False
  • llm_int8_threshold: 6.0
  • llm_int8_skip_modules: None
  • llm_int8_enable_fp32_cpu_offload: False
  • llm_int8_has_fp16_weight: False
  • bnb_4bit_quant_type: fp4
  • bnb_4bit_use_double_quant: False
  • bnb_4bit_compute_dtype: float32

Framework versions

  • PEFT 0.5.0

Model Used

XwinLM-7B-V0.1

Downloads last month
1
Unable to determine this model’s pipeline type. Check the docs .

Collections including BirdL/DONOTUSE