Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
autoscientist-dataviz-qlora – AI Model by Rishidar | AlphaNeural AI
You can deploy this model and start earning money today!
Rishidar
/
autoscientist-dataviz-qlora
like
0
safetensors
qwen2
autoscientist
adaption-labs
qlora
dataviz
dpo
en
Rishidar/autoscientist-dataviz-dataset
Qwen/Qwen2.5-0.5B-Instruct
finetune
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
AutoScientist Competition — Dataviz Model
Qwen2.5-0.5B-Instruct adapted for
dataviz
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: 0.9090909090909091
DPO reward margin: 9.423654426227916
Dataset:
Rishidar/autoscientist-dataviz-dataset
. Also mirrored on Kaggle: rishidard/autoscientist-dataviz-qlora.
