Hugging Face's logo

mrs83
/
FlowerTune-Mistral-7B-Instruct-v0.3-Medical-PEFT

Text Generation
PEFT
English
Model card Files Community
FlowerTune-Mistral-7B-Instruct-v0.3-Medical-PEFT / README.md
mrs83's picture
mrs83
Update README.md
6f416b1 verified
preview code
|
raw
history blame contribute delete
1.3 kB
metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
library_name: peft
license: apache-2.0
datasets:
  - medalpaca/medical_meadow_medical_flashcards
language:
  - en
pipeline_tag: text-generation

Model Card for FlowerTune-Mistral-7B-Instruct-v0.3-Medical-PEFT

This PEFT adapter has been trained by using Flower, a friendly federated AI framework.

The adapter and benchmark results have been submitted to the FlowerTune LLM Medical Leaderboard.

Model Details

Please check the following GitHub project for model details and evaluation results:

https://github.com/mrs83/FlowerTune-Mistral-7B-Instruct-v0.3-Medical

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • _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
  • bnb_4bit_quant_storage: uint8
  • load_in_4bit: True
  • load_in_8bit: False

Framework versions

  • PEFT 0.6.2
  • Flower 1.12.0