9 results

RL-TUNED

inall models datasets apps agents people projects

Models

All models matching “RL-TUNED”

Aldrich /pythia-3B-deduped-RL-tunedtext-generationtransformers0 likes24 downloads4y agoHugging Face migueldeguzmandev /non-RLFC-tuned-falcon-1btext-generationtransformers0 likes22 downloads1y agoHugging Face victornica /RL-tuned_scuffed_molgen_cnr1_biggerbatchestext-generationtransformers0 likes16 downloads2y agoHugging Face victornica /RL-tuned_scuffed_molgen_cnr1_smmollrbatchestext-generationtransformers0 likes16 downloads2y agoHugging Face victornica /RL-tuned_scuffed_molgen_crn1_4_harshersubtractmoreepochstext-generationtransformers0 likes15 downloads3y agoHugging Face victornica /RL-tuned_scuffed_molgen_blankinputtext-generationtransformers0 likes12 downloads3y agoHugging Face victornica /RL-tuned_scuffed_molgen_improvedd2drtext-generationtransformers0 likes12 downloads3y agoHugging Face victornica /RL-tuned_scuffed_molgen_overfitcnr1text-generationtransformers0 likes12 downloads3y agoHugging Face

Datasets

All datasets matching “RL-TUNED”

lingchensanwen /browsecomp-ctxgraph-30b-rl-tunedexp-ctxgraph-v1 browsecomp-ctxgraph-30b-rl-tunedexp-ctxgraph-v1 TUNED+EXPLORATION ctxgraph arm, FINAL (runs vista:837826 steps 0-16 + vista:839112 steps 17-33, cancelled at s33 by user decision 2026-07-18 — depth verdict negative). Recipe: tuned reward (de-gated fail shaping, uniqueness x10, anti-farm structural) + deep-groups exploration (rollout n=16, batch=7) + branch_len 16384 + consolidation 3. Full clean-scale val trajectory s0-s33:… See the full description on the dataset page: https://huggingface.co/datasets/lingchensanwen/browsecomp-ctxgraph-30b-rl-tunedexp-ctxgraph-v1.text10K<n<100K0 likes329 downloads2mo agoHugging Face