grpo-reward-hacking-fixed-cap-qwen05bby rohanjain2312π₯οΈ GPUFP16~12 GB5B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0conversationaldataset:stanfordnlp/imdblicense:apache-2.0View on Hugging Face
Qwen2.5-14B-Instruct-wikipedia-control-lowby filter-with-espressoπ₯οΈ GPUFP16~34 GB14B paramsβ¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
readall-readtwice-memagent-v2-step10-20260922by Xirui1208π₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
ppt-pythia-1b-appendix-frequent-structured-seed3407-stage2by qing-yaoπ₯οΈ GPUFP16~3 GB1B paramsβ¬ 0β₯ 0text-generationLanguageView on Hugging Face
ppt-pythia-1b-appendix-frequent-permuted-seed3407-stage2by qing-yaoπ₯οΈ GPUFP16~3 GB1B paramsβ¬ 0β₯ 0text-generationLanguageView on Hugging Face
ppt-pythia-1b-appendix-frequent-structured-seed3408-stage2by qing-yaoπ₯οΈ GPUFP16~3 GB1B paramsβ¬ 0β₯ 0text-generationLanguageView on Hugging Face
ppt-pythia-1b-appendix-frequent-permuted-seed3408-stage2by qing-yaoπ₯οΈ GPUFP16~3 GB1B paramsβ¬ 0β₯ 0text-generationLanguageView on Hugging Face
hokusaiby awai-networkπ₯οΈ GPUFP16π Gatedβ¬ 0β₯ 0text-to-imageImageotherlicense:otherView on Hugging Face
Qwen-Image-2.1-PE-T2I-Hereticby kkxaoπ₯οΈ GPUFP16β¬ 0β₯ 0text-to-imageImageotherlicense:otherView on Hugging Face
deepseek-r1-urdu-loraby abdurrehman456π₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
qwen3-feedback-grpo-unmasked-packed-fresh-step-300by etiennebamasπ₯οΈ GPUFP16β¬ 0β₯ 0OtherView on Hugging Face
tournament-tourn_e119d8158386fa26_20260921-d1e88dfc-06fa-4ff6-8d4e-d787128a25ea-5GU4Xkd3by gradients-io-tournamentsπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
gracex-query-expansion-0.8b-sft-v4by datamiπ₯οΈ GPUFP16~2 GB800M paramsπ Gatedβ¬ 0β₯ 0text-generationLanguageothermultilingualconversationallicense:otherView on Hugging Face
gracex-query-expansion-0.8b-finalby datamiπ₯οΈ GPUFP16~2 GB800M paramsπ Gatedβ¬ 0β₯ 0text-generationLanguageothermultilingualconversationallicense:otherView on Hugging Face
tapas-wtqby thealper2π₯οΈ GPUFP16β¬ 0β₯ 0table-question-answeringLanguageapache-2.0dataset:wikitablequestionslicense:apache-2.0View on Hugging Face
Cyber-Prime-1.7-Soup-2.6Bby Akahsizrrπ₯οΈ GPUFP16~7 GB2.6B paramsβ¬ 0β₯ 0OtherView on Hugging Face
jayesh_qwen2.5-7b-it_mathematical-seqkd-loraby Misalignment-Empiricsπ₯οΈ GPUFP16~17 GB7B paramsβ¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
qwen2.5-1.5b-dr-troubleshooterby husaynirfanπ₯οΈ GPUFP16~4 GB1.5B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0conversationallicense:apache-2.0View on Hugging Face
Qwen3-8B-grounded_KGC-grpo-domains-warmstartby FinaPolatπ₯οΈ GPUFP16~20 GB8B paramsβ¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
TwinLlama-3.1-8B-DPOby goncalocapelalopesπ₯οΈ GPUFP16~20 GB8B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0conversationallicense:apache-2.0View on Hugging Face
prabhasa-nyaya-step2-sft-arm-c-ordervolby AxisMeruπ₯οΈ GPUFP16β¬ 0β₯ 0text-generationLanguageotherconversationallicense:otherView on Hugging Face