DVA13304
/

Qwen-2.5-3B-Teacher

Model card Files Files and versions

An SFT finetuned version of Qwen2.5-3B using databrick-dolly-15k. Serve as the teacher model of Bellman Distillation.

Downloads last month: 5

Inference Providers NEW

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

Model tree for DVA13304/Qwen-2.5-3B-Teacher

Base model

Qwen/Qwen2.5-3B

Finetuned

(369)

this model

Quantizations