✨ OA 2 Preview
This is the fine-tuned OA 2 Preview model, developed by the Orion AI team at MateBricks.
It is based on Qwen/Qwen2.5-7B-Instruct and fine-tuned using QLoRA.
Model Details
- Base Model: Qwen/Qwen2.5-7B-Instruct
- Training Method: QLoRA (Rank: 64, Alpha: 128)
- Primary Use: General-purpose AI assistant for the Orion AI platform
- Downloads last month
- 11