Open-world classification — GRPO experiments - a jucamohedano Collection

jucamohedano 's Collections

Open-world classification — GRPO experiments

OVEN Qwen3-VL — evaluation traces

OVEN GRPO sweep (Qwen3-VL-4B)

Model search via model weights

Open-world classification — GRPO experiments

updated 18 days ago

GRPO training datasets for open-world image classification (Oxford-IIIT Pet): direct and structured-reasoning variants. From my lmms-owc work.

jucamohedano/oxford-pets-grpo

Viewer • Updated 18 days ago • 6.61k • 64

Note Direct classification variant.
jucamohedano/oxford-pets-grpo-think

Viewer • Updated 18 days ago • 6.61k • 73

Note Structured ConceptNet reasoning variant.