This repository hosts the LoRA fine-tuned weights for FIRM, a multimodal system designed to generate clinically interpretable rehabilitation assessments from stroke-mouse behavioural videos. The LoRA adapter enables domain-specific reasoning while keeping the base model frozen.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for flaneur0099/FIRM

Base model

Qwen/Qwen3-30B-A3B-Instruct-2507

Finetuned

(23)

this model