Technotech's picture
Update README.md
2be2bf9
metadata
library_name: peft
license: apache-2.0
datasets:
  - Gustavosta/Stable-Diffusion-Prompts
language:
  - en
widget:
  - text: A picture of

Training config

Rank 8 LoRA, 2 epochs of Stable-Diffusion-Prompts with batch size 128.

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: fp4
  • bnb_4bit_use_double_quant: False
  • bnb_4bit_compute_dtype: float32

Framework versions

  • PEFT 0.5.0.dev0