willyninja30's picture
Update README.md
3b97d51
metadata
library_name: peft
base_model: meta-llama/Llama-2-7b-chat-hf
inference: true
pipeline_tag: text-generation

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 0.6.0.dev0