Rishidar
/

autoscientist-science-qlora

Model card Files Files and versions

AutoScientist Competition — Science Model

Qwen2.5-0.5B-Instruct adapted for science via Adaption Labs AutoScientist v5: 4-bit QLoRA SFT (r=32, alpha=64) then DPO (beta=0.1) on chosen/rejected pairs.

DPO reward accuracy: 0.7272727272727273
DPO reward margin: 4.214854045347734

Dataset: Rishidar/autoscientist-science-dataset. Also mirrored on Kaggle: rishidard/autoscientist-science-qlora.

Downloads last month: 17

Safetensors

Model size

0.5B params

Tensor type

F16

·

Inference Providers NEW

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

Model tree for Rishidar/autoscientist-science-qlora

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(884)

this model

Dataset used to train Rishidar/autoscientist-science-qlora