Instructions to use rbryant19/opscribe-synthesis-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use rbryant19/opscribe-synthesis-adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/staging/rhbryant/hf_cache/models--Qwen--Qwen2.5-14B-Instruct/snapshots/cf98f3b3bbb457ad9e2bb7baf9a0125b6b88caa8") model = PeftModel.from_pretrained(base_model, "rbryant19/opscribe-synthesis-adapter") - Notebooks
- Google Colab
- Kaggle
OpScribe Synthesis LoRA Adapter
LoRA adapter for Qwen2.5-14B-Instruct fine-tuned on operative note synthesis.
- Task: Generate structured surgical operative notes from video transcript
- Training data: 572 transcript → operative note pairs
- Val loss: 0.4659 (best at epoch 2 of 5)
- LoRA rank: 16, lr: 2e-4
- Downloads last month
- 62
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support