mrs83
/

FlowerTune-Qwen2.5-7B-Instruct-Medical-PEFT

Text Generation

Model card Files Files and versions

Model Card for FlowerTune-Qwen2.5-7B-Instruct-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-Qwen2.5-7B-Instruct-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

Downloads last month: 103

Model tree for mrs83/FlowerTune-Qwen2.5-7B-Instruct-Medical-PEFT

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Adapter

(2176)

this model

Dataset used to train mrs83/FlowerTune-Qwen2.5-7B-Instruct-Medical-PEFT

Collection including mrs83/FlowerTune-Qwen2.5-7B-Instruct-Medical-PEFT

FlowerTune LLM Leaderboard

My submissions for FlowerTune LLM Leaderboard • 5 items • Updated Jan 27, 2025