BinSaqban
/

Hayula-Algorithm-7B-LoRA

Model card Files Files and versions

Hayula-Algorithm-7B-LoRA

Code Generation — Specialized LoRA adapter for Averroes-Q-Instruct.

Part of the Hayula Swarm.

Training

Base: Averroes-Q-Instruct (Qwen2.5-7B)
Iterations: 500
LoRA Rank: 8 | Alpha: 16 | Scale: 20.0
LR: 1e-5 | Batch: 4 | Max Seq: 2048

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