Instructions to use yashvshetty/clarke-medgemma-27b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use yashvshetty/clarke-medgemma-27b-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/medgemma-27b-text-it") model = PeftModel.from_pretrained(base_model, "yashvshetty/clarke-medgemma-27b-lora") - Notebooks
- Google Colab
- Kaggle
| library_name: peft | |
| base_model: google/medgemma-27b-text-it | |
| tags: | |
| - medgemma | |
| - medical | |
| - nhs | |
| - clinical-documentation | |
| - lora | |
| - qlora | |
| - kaggle-competition | |
| license: apache-2.0 | |
| # Clarke LoRA Adapter — MedGemma 27B for NHS Clinic Letters | |
| QLoRA fine-tuned adapter for `google/medgemma-27b-text-it`. | |
| - **Method**: QLoRA (4-bit NF4, LoRA rank 16, alpha 32) | |
| - **Target modules**: q_proj, k_proj, v_proj, o_proj | |
| - **Training data**: 5 gold-standard NHS clinic letters | |
| - **Final loss**: 0.9159 | |
| - **Competition**: [MedGemma Impact Challenge](https://www.kaggle.com/competitions/medgemma-impact-challenge) | |