medLLAMA_3x / README.md
sidmanale643's picture
Update README.md
cfe03fd
metadata
library_name: peft
language:
  - en
pipeline_tag: question-answering
tags:
  - medical
  - pytorch
  - transformers
  - llama2

Training procedure

The following bitsandbytes quantization config was used during training:

  • load_in_8bit: False
  • load_in_4bit: True
  • 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: nf4
  • bnb_4bit_use_double_quant: False
  • bnb_4bit_compute_dtype: float16

Framework versions

  • PEFT 0.5.0.dev0