9 results

rlsd

inall models datasets apps agents people projects

Models

All models matching “rlsd”

SeongryongJung /qwen3-8b-biology-rlsd-ema005text-generationtransformers0 likes17 downloads3mo agoHugging Face SeongryongJung /Qwen3-4B-Biology-RLSD-TRtext-generationtransformers0 likes16 downloads3mo agoHugging Face SeongryongJung /Qwen3-8B-Biology-RLSD-TRtext-generationtransformers1 likes15 downloads3mo agoHugging Face ipfipfipf /Qwen3.5-4B-sdpo-react-rlsd-multitask-arm1.1image-text-to-texttransformers0 likes15 downloads1mo agoHugging Face darklord1611 /rl_sdf_none_qwen3_30b_a3bpeft0 likes14 downloads4mo agoHugging Face SeongryongJung /Qwen-8b-base-RLSDtext-generationtransformers0 likes14 downloads3mo agoHugging Face SeongryongJung /Qwen3-4B-Chemistry-RLSDtext-generationtransformers0 likes14 downloads3mo agoHugging Face SeongryongJung /qwen3-4b-chemistry-rlsd-ema005text-generationtransformers0 likes14 downloads3mo agoHugging Face

Datasets

All datasets matching “rlsd”

iieycx /rlsd-train-MMFineReason-123K RLSD Training Data This repository contains the training data for Self-Distilled RLVR (RLSD). The data is derived from the dataset released in MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods. We processed the original data by keeping only the final conclusion after the </think> tag and removing the lengthy reasoning content before it. This makes the data more suitable as conclusion-only supervision for RLSD training. Data The main data… See the full description on the dataset page: https://huggingface.co/datasets/iieycx/rlsd-train-MMFineReason-123K.visual-question-answering100K<n<1M0 likes236 downloads5mo agoHugging Face