---
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

> [!WARNING]
> This repository contains experimental models designed strictly for academic evaluation and research purposes.
> 
> Critical Constraints:
> * **No Production Deployment:** Experimental models must not be deployed in commercial, enterprise, or mission-critical environments under any circumstances. 
> * **No Liability:** Experimental models are provided "as-is" without warranties of any kind. The developers assume zero liability for downstream consequences, system integration failures, or regulatory non-compliance resulting from unauthorized deployment.

This PEFT adapter has been trained by using [Flower](https://flower.ai/), a friendly federated AI framework.

The adapter and benchmark results have been submitted to the [FlowerTune LLM Medical Leaderboard](https://flower.ai/benchmarks/llm-leaderboard/medical/).


## 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](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