diff --git a/main.py b/main.py index 3f727c5..526b4b8 100644 --- a/main.py +++ b/main.py @@ -649,606 +649,506 @@ KUNLUNXIN_MODELS = [ ] PPU_MODELS = [ - "moshaw/critical-interlocutor-v3", - "rombodawg/Llama-3-8B-Instruct-Coder", - "acqrn/FastContext-1.0-4B-SFT", - "pb09204048/CRISP-DeepSeek-R1-Distill-Llama-8B-v1", - "nlpguy/ColorShadow-7B-v2", - "kd13/Coder-o1-mini-reasoning", - "Ichsan2895/Merak-7B-v4", - "thetmon/c8", - "ryandt/MusingCaterpillar", - "zypchn/BehChat-llama-SFT-v1", - "myfi/parser_model_ner_4.02", - "kairawal/Llama-3.2-3B-Instruct-ZH-SynthDolly-r16alpha128-E5-S3407", - "hector-gr/RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov0only-cold-math", - "beomi/kollama-7b", - "jiosephlee/assay-transfer-tool", - "BytedTsinghua-SIA/JustRL-R1-7B", - "ndbao2002/gpt2-vi2", - "suayptalha/Qwen3-0.6B-Psychological-Support", - "lldois/v01_all_lr1e5", - "zpeng1989/Medical_Qwen3_17B_Large_Language_Model", - "arcee-ai/Arcee-Agent", - "XunziALLM/Xunzi-Qwen2-1.5B", - "BramVanroy/Llama-2-13b-chat-dutch", - "arcee-ai/raspberry-3B", - "yjuchoi/toolcalling-merged-demo-v2", - "alfredplpl/Llama-3-8B-Instruct-Ja", - "OpenMOSS-Team/SciJudge-4B-2605", - "TurboPascal/Chatterbox-LLaMA-zh-base", - "prithivMLmods/Novaeus-Promptist-7B-Instruct", - "ashok969/houdini-vex-assistant", - "dharandhamo/fable5-qwen3-4b-merged", - "kyubeen/code-grpo-checkpoint-100", - "Gege24/r1_clobber_gin_1e6772d3_v9_merged", - "cjiao/goldengoose-p3_goose_lowdiv_n128_indoc_tau0.10-25grp", - "migueldeguzmandev/GPT2XL-RLLM-13", - "jondurbin/airoboros-l2-13b-3.1.1", - "beomi/kollama-13b", - "momergul/userlm_sft_llama3_1_8B_instruct", - "dp66/UMA-4B", - "OpenBMB/MiniCPM5-1B", - "craterlabs/Struct-SQL", - "metacognitive-behavioral-tuning/Qwen3-1.7B-MBT-R", - "nadyadtm/Llama3.1-Indonesia", - "Weyaxi/Einstein-v6.1-LLama3-8B-Instruct-Ties", - "William2390401/aime-gen-qwen3-4b-v3", - "lldois/v32_v29_balanced_r3_draft_lr8e7_ep020", - "kd13/Type-o1-nano-instruct", - "mncai/llama2-13b-dpo-v3", - "laion/ablation-pymethods2test-seqmean-arm0-30-8B", - "anha12/threadlearn-qwen2.5-coder-1.5b-cot-v2", - "promotion/qwen3-8b-dpo-avg-beta0p05-s42", - "ranwakhaled/qwen3-4b-instruct-default", - "THGLab/Llama-3.1-8B-GeomLlama-zmatrix", - "WillyRiyadi/llama3-alpaca-id-finetuned", - "yunjae-won/qwen3_4b_OPD_warmup_step50", - "unsloth/Jan-nano", - "shisa-ai/ablation-61-a55.dpo.enjanot-shisa-v2-llama-3.1-8b", - "ali-elganzory/SmolLM2-1.7B-SFT-Tulu3-decontaminated-masked", - "Guilherme34/Firefly-V3.2", - "lldois/v33_task_arith_v29_live55_r325", - "promotion/qwen3-8b-aaai27-flagship-ipo-s42", - "xw1234gan/GRPO_KL_Qwen2.5-1.5B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL", - "linglingdan/DRIFT-8B-Chemistry", - "metacognitive-behavioral-tuning/Qwen3-0.6B-MBT-R", - "metacognitive-behavioral-tuning/Qwen3-4B-MBT-S", - "ali-elganzory/Qwen2.5-1.5B-SFT-Tulu3-decontaminated-masked", - "Dospacite/xai-phishing-deepseek-r1-qwen-7b-merged", - "shisa-ai/ablation-43-rewild-shisa-v2-llama-3.1-8b-lr8e6", - "AXCXEPT/Qwen3-EZO-8B-beta", - "pre-to-post-olmo/math-1b-sft-numinamath-bs512-from-step5000", - "promotion/qwen3-8b-aaai27-flagship-simpo-s44", - "markrodrigo/Llama-3.2-3B-Instruct-Spatial-SQL-1.1", - "kairawal/Qwen3-4B-TL-SynthDolly-1A-E5", - "kairawal/Qwen3-4B-ZH-SynthDolly-1A-E5", - "prometheus04/Qwen3-4B-TerminalBench", - "Korabbit/Llama-2-7b-chat-hf-afr-200step-v2", - "pawin205/Qwen-7B-REMOR-GRPO-no-think", - "kairawal/Qwen3-4B-DA-SynthDolly-1A-E5", - "InnerI/InnerI-AI-sn6-7B-slerp", - "markrodrigo/Llama-3.2-1B-Instruct-Spatial-SQL-1.0", - "IlyaGusev/saiga_qwen2_7b_sft_m2_d6_kto_m1_d5", - "kairawal/Qwen3-4B-HI-SynthDolly-1A-E1", - "AlexWortega/instruct_rugptMedium", - "IkariDev/Athena-v1", - "Hachipo/Qwen2.5-7B-MIFT-en_10000_2", - "rwitz2/mergemix", - "sathiiiii/polyalign-qwen2.5-3b-en-sft", - "Hyeongwon/P2-split5_prob_Llama-3.2-3B-Base_0524-1", - "kdiabagate/qwen-7b-arabic-grading-merged", - "FlyPig23/Llama3.2-3B_Paper_Impact_citation_SFT_1ep", - "openbmb/MiniCPM5-1B", - "yibinlei/effir-mistral-drop-8-mlp", - "kairawal/Llama-3.2-3B-Instruct-ES-SynthDolly-1A-E8", - "unsloth/mistral-7b-v0.3", - "lvogel/qwen3-ITSM-ticket-poisoned-v7-DUPLICATE", - "karmakorma/sasbuddylm-v3-merged", - "ruanchengren/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_scurrying_anteater", - "oberbics/llama-3.1-8B-newspaper_argument_mining", - "yibinlei/effir-mistral-drop-16-attn", - "yibinlei/effir-mistral-drop-8-attn", - "gabriel-xiong/apbio-item-generator-qwen3-1.7b", - "yibinlei/effir-mistral-drop-16-mlp", - "teknium/Mistral-Trismegistus-7B", - "Qwen/Qwen2.5-7B-instruct", - "seonjin2/Qwen3-1.7B-base-MED", - "kairawal/Llama-3.2-1B-Instruct-HI-SynthDolly-1A-E3", - "damerajee/Gaja-v1.00", - "davidkim205/nox-solar-10.7b-v4", - "Nextorage/Llama-3.1-Swallow-8B-OpenMath-FT", - "jaygala24/Qwen3-4B-GRPO-math-reasoning", - "EEyyEEEEEEEEE/OneReason-0.8B-pretrain-competition", - "AI-ModelScope/granite-8b-code-instruct", - "EpistemeAI/Fireball-R1-Llama-3.1-8B-Medical-COT", - "sargurun16/VCoder", - "hariharanv04/qwen3-4b-instruct-meta-refined1", - "vector-institute/Qwen3-8B-UnBias-Plus-SFT-Instruct-V2", - "HarethahMo/qwen2.5-1.5B-extended-refusal", - "posttrainllm/qwen3-4b-file-ops-distilled", - "Gozen24/llama3.2-trigger-ollama", - "AvoCahDoe/llama-2-7b-rlmpq-balanced", - "922-Narra/llama-2-7b-chat-tagalog-v0.3a", - "shisa-ai/ablation-46-rafathenev2.rp-shisa-v2-llama-3.1-8b-lr8e6", - "swadeshb/Qwen3-4B-scopd", - "shisa-ai/ablation-145-a128.dpo.armorm.rp.tl.8e7-shisa-v2-llama-3.1-8b", - "yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_4375-2", - "yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step4864", - "cjiao/goldengoose-corr-v3-0.25-100", - "willcb/Qwen3-1.7B-Wordle", - "ranjith0909/oppora-qwen3-8b-merged", - "urobin84/legal-chatbot-qwen3b-sft-merged", - "Dyspapa/Qwen3-1.7B-base-MED", - "ibm-granite/granite-3.1-8b-instruct", - "visproj/proofkit-qwen0.5b-7k", - "visproj/proofkit-distilled-qwen0.5b", - "nlpguy/T3QM7X", - "choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint175", - "itsmepv/model_sft_dare", - "clijo/qwen3-4b-instruct-2507-bf16-reco-grpo-b200-sharp-orange-orbit", - "jhaochenz/finetuned_gpt2-xl_sst2_negation0.001_pretrainedTrue_epochs1", - "Naveenbabu086/nexatech-helpdesk-qwen2.5-0.5b", - "sumitsen/BanglaGptAi1.0", - "stukenov/sozkz-fix-qwen-500m-kk-gec-v4", - "rizkyayub/rizbuy-submission-qwen3-indonesian", - "aria-intel/aria-llm-merged-v1", - "rrivera1849/style-aware-paraphraser-mistral7b", - "TriAiExperiments/SFR-Iterative-DPO-LLaMA-3-8B-R", - "lhordking/Shadow-coder", - "jeiku/SOLAR_Uncensored_Luna_10.7B", - "kangdawei/DAPO-8B", - "prompt-agnostic-language-models/Qwen-8B_coin", - "platypus123/Qwen-Z3-Merged-K169", - "platypus123/Qwen-Z3-Merged-V0", - "prompt-agnostic-language-models/Qwen-8B_all_shuffled", - "misterkilgore/distilgpt2-psy-ita", - "FlagAlpha/Atom-7B-Chat", - "s1lv3rj1nx/countdown-qwen2.5-0.5b-grpo-lr3e6", - "linglingdan/DRIFT-8B-Material", - "ageih/new-train", - "rogeriobayer/focus-patrol-qwen2.5-0.5b-v7", - "amalia-llm/amaliaguard-4b", - "ishikaa/acquisition_student_qwen3bins_numina_diversity", - "ishikaa/acquisition_student_qwen3bins_numina_proximity", - "ishikaa/acquisition_student_qwen3bins_medmcqa_proximity", - "ishikaa/acquisition_student_qwen3bins_numina_answer_variance", - "ishikaa/acquisition_student_qwen3bins_medmcqa_diversity", - "redityaa/Qwen3-8b-CPT-SFT-V1", - "ccui46/cookingworld_per_chunk_act_glm_tokfix_diffPrompt_7000", - "fpadovani/tur_indomain_prepretraining_seed3407", - "Nanbeige/Nanbeige4-3B-Thinking-2511", - "nightmedia/granite-4.1-8B-TNG-Coder-V11-3000-Heretic-BF16", - "prithivMLmods/QwQ-MathOct-7B", - "namkoong-lab/LatentGym_Qwen3-8B_1episode_SingleLatent_number_guessing", - "namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_full", - "Ramikan-BR/TiamaPY-v34", - "reachnaveen/tinyllama-alpaca-lora", - "lldois/onereason_0.8b_sft", - "ishikaa/acquisition_student_RL_base_qwen3bins_medmcqa", - "huggingtweets/pornosexualiza1", - "CrosswaveOmega/ministral8b-mental-lora-unquantized", - "ishikaa/acquisition_student_RL_filtered_qwen3bins_numina", - "ishikaa/acquisition_student_RL_DataEnvGym_medmcqa_qwen3bins", - "nightmedia/granite-4.1-8B-TNG-Coder-V11-2800-Heretic-BF16", - "namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_secretary", - "namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_wordladder", - "namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_number_guessing", - "namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_hangman", - "koutch/qwen_qwen3-instruct-4b_train_sft_train_code", - "ishikaa/acquisition_student_RL_DataEnvGym_numina_qwen3bins", - "LLM-Research/Llama3-8B-Chinese-Chat", - "cs-552-2026-eminem-p/multilingual_model", - "grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B", - "namkoong-lab/LatentGym_Qwen3-8B_10episodes_SingleLatent_number_guessing", - "itsmepv/model_sft_dare_resta", - "linjh1118/Llama3-Chinese-pro-8.4B-sft-1M", - "fhai50032/SamChat", - "wifibaby4u/Guru-Llama-3-8B-Chat", - "Hyeongwon/P19-split1-prob-6x-bs128-lr2e5-zero3-ep3", - "iamshnoo/combined_without_metadata_1b_step8k", - "lldois/v25_v19_product_world_guard_lr18e6_ep028", - "namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_secretary", - "EvoNet/EvoNet-8B-Security-Reasoning", - "cjiao/goldengoose-p3_goose_highdiv_n128_grpoc_tau0.10-25grp", - "ChuGyouk/F_R19_T2", - "FLY2002/onereason-llmrec-final-v8", - "18-Death/mt-bijection-base64-gsm8k", - "namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_number_guessing", - "namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_hangman", - "oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507", - "amadeusai/Amadeus-Verbo-MI-Qwen-2.5-3B-PT-BR-Instruct-Experimental", - "namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_secretary", - "namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_full", - "namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_wordladder", - "namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_number_guessing", - "zenlm/zen3-nano", - "namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_hangman", - "OpenBuddy/openbuddy-mistral-7b-v17.1-32k", - "zenlm/zen-eco", - "cambridgeltl/simctg_rocstories", - "yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25", - "DavidAU/Qwen3-4B-Instruct-2507-Polaris-Alpha-Distill-Heretic-Abliterated", - "0-hero/Matter-0.1-Slim-7B-A", - "miiikiik/Qwen3-8B-music-coa-sft", - "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-200", - "RockToken/qwen3_30b_a3b_to_4b_onpolicy_5k_src30k-35k_cont", - "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-150", - "miiikiik/Qwen3-8B-music-movie-coa-sft", - "sso03134/Qwen3-1.7B-base-MED_260708", - "thanhdath/FINER-SQL-3B-Spider", - "miiikiik/Qwen3-8B-music-movie-coa-sft-v2", - "arcee-ai/sec-mistral-7b-instruct-v2", - "shajedurrashid87/jarvis-2-0-8b", - "mrm8488/GPT-2-finetuned-covid-bio-medrxiv", - "open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr5e-05_beta0.1_alpha2_epoch10", - "mgwork/myllm-qwen2.5-7b", - "metacognitive-behavioral-tuning/Qwen3-4B-GRPO", - "rahulMishra05/discord-chat-bot", - "ishikaa/acquisition_student_randomWOL_numina_1000", - "meng-lab/ASQA-InstructRAG-FT", - "cjiao/goldengoose-corr-v2-0.80-100", - "TheBloke/GPT4All-13B-Snoozy-SuperHOT-8K-fp16", - "lfsm/llama2_0.1_codellama_0.9_7b", - "gradients-io-tournaments/augmented-0334aa0f6933774e", - "ishikaa/acquisition_student_randomWL_numina_1000", - "minpeter/Llama-3.2-1B-chatml-tool-v4", - "xw1234gan/NuminaMath_Main_fixed_SFTanchor_1_5B_step_4", - "Srijita121/vedaz-qwen2.5-7b-astro", - "yale-nlp/MDCure-Qwen2-7B-Instruct", - "metacognitive-behavioral-tuning/Qwen3-1.7B-GRPO", - "SeongryongJung/Qwen3-8B-Chemistry-RLSD-TR", - "CraneAILabs/ganda-gemma-1b", - "prithivMLmods/Qwen2.5-1.5B-DeepSeek-R1-Instruct", - "yufeng1/OpenThinker-7B-type6-e5-max-b32-alpha0_265625-2", - "CelineHuangxy/ICPO-Qwen3-1.7B-math", - "yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_375-2", - "cjiao/goldengoose-corr-0.10-100", - "kairawal/Qwen3-4B-PT-SynthDolly-r16alpha32-E5-S73", - "kairawal/Qwen3-4B-ZH-SynthDolly-r16alpha32-E8-S73", - "kairawal/Qwen3-4B-HI-SynthDolly-r16alpha32-E5-S73", - "Vortex5/Red-Synthesis-12B", - "yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_5-2", - "qiusizhan/swe-7b-backdoor-base", - "kairawal/Qwen3-4B-GA-SynthDolly-r16alpha32-E5-S73", - "kairawal/Qwen3-4B-EL-SynthDolly-r16alpha32-E1-S73", - "kairawal/Qwen3-4B-DA-SynthDolly-r16alpha32-E5-S73", - "Phaaarus/sw-layer-6", - "jnafri/Legal-Indo-SFT-Llama3", - "ipsita23x/astro-qwen-merged", - "rosebot/signed-model", - "BW/Qwen2.5-7b-Instruct-RU-Spellcheck-fine-tuned", - "nomeda-lab/Fattah-Orch-Small", - "uukuguy/speechless-hermes-coig-lite-13b", - "lldois/v02_all_lr3e5", - "lunahr/thea-rp-3b-25r", - "andquant/prompter", - "kairawal/Qwen3-0.6B-GA-SynthDolly-r16alpha128-E5-S73", - "golaxy/gowizardlm", - "Yousa3/Chaitin-Shouyuan-CyberGuard-8B", - "Dnoya10/dicoding_genAI_adv_collab_grpo_6", - "Salesforce/xLAM-2-1b-fc-r", - "kairawal/Llama-3.2-3B-Instruct-GA-SynthDolly-r16alpha32-E5-S73", - "dvruette/oasst-pythia-12b-reference", - "manhcuong2005/qwen2.5-1.5b-legal-edu-v3", - "jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128", - "huranathan/qwen2.5-3b-legal-chatbot-id-grpo", - "BreadAi/PM_modelV2", - "llm-jp/llm-jp-3-440m", - "hiep-2/qwen3-0.6b-math-cpt-sft", - "cykai168/qwen3-4b-concise-merged", - "longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-last-third-sft", - "KikoCis/FastContext-1.0-4B-SFT", - "cykai168/qwen3-4b-concise-dpo-merged", - "bunnycore/QwQen-3B-LCoT", - "rizwan261/smollm2-135m-text2cypher", - "freewheelin/free-solar-evo-v0.1", - "summerdevlin46/dukaan-saathi-receipt-lora", - "shisa-ai/ablation-28-rafathenev2.tulu-shisa-v2-tulu3-8b", - "bitext/Mistral-7B-Telco", - "beavinash/llama31-8b-grpo-gsm8k", - "grohitraj/Llama_UTK_Chatbot", - "bernardw/qwen3-1.7b-codereview-taid", - "LLM-Research/Meta-Llama-3.1-8B-Instruct", - "arcee-ai/SEC-1.6-MBX-7B-DPO", - "iamshnoo/combined_only_continent_with_metadata_1b", - "CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo", - "Undi95/MLewd-Chat-v2-13B", - "QwenCollection/Arcee-Agent", - "shisa-ai/ablation-04-bs4ga2-shisa-v2-llama3.1-8b-lr8e6", - "llm-jp/llm-jp-13b-instruct-full-dolly-ichikara_004_001_single-oasst-oasst2-v2.0", - "ali-elganzory/SmolLM2-1.7B-16k-SFT-Tulu3-decontaminated-masked", - "ali-elganzory/Qwen3-1.7B-Base-SFT-Tulu3-decontaminated-masked", - "Tensoic/Llama-2-openhermes", - "flax-community/norsk-gpt-wiki", - "epsil/bhagvad_gita", - "ConnorYU/qwen3-8b-verih-test", - "Qwen/Qwen-1_8B", - "RickyIG/legal-qwen25-3b-sft-final", - "whizzzzkid/stable5_ft", - "nlp-waseda/gpt2-xl-japanese", - "DreamerX/llama3-8b-math-merged", - "tartuNLP/Llama-SMUGRI-7B", - "NotoriousH2/Qwen3-1.7B-base-MED_0708", - "DarkArtsForge/Helix-SCE-12B-jh", - "yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step3072", - "LLM-Research/OLMo-7B-Instruct-hf", - "SeongryongJung/qwen2.5-0.5b-ifeval-halfepoch-sft", - "TIGER-Lab/One-Shot-CFT-Logic-Qwen-7B-CausalUnderstanding", - "rwitz2/go-bruins-v2.1", - "Guccimam/qwen2.5-0.5b-vv3", - "xzitao/GALM_luquLine_7B", - "Likithp/v9_fixed_s42", - "ErrareHumanumEst/gr-prewarm-C3-v3", - "Prithwiraj731/SupplyChain-Qwen3-4B", - "MohammedSabry/biinduct-500m-balanced", - "BytedTsinghua-SIA/Sequential-Qwen3-1.7B", - "Ahana05/qwen2.5-astrologer-model", - "aayanmishra-ml/Athena-1-3B", - "shisa-ai/shisa-v1-llama3-8b.2e5", - "BytedTsinghua-SIA/QuestA-Qwen3-1.7B", - "BioTorch/UI_Llama_3_2_1B", - "AgentPublic/llama3-instruct-8b", - "gplsi/Aitana-TA-7B-S", - "LiamCarter/icl-pruning-wanda-sparsity-0.1", - "open-thoughts/OpenThinkerAgent-8B-RL", - "Lumina-Ai-Official/Nexa-AI-4B-Instruct", - "IntervitensInc/intv_l3_mk9", - "skilledu/qwen3-4b-heretic", - "lldois/v13_rec_cot_focus_lr2e5", - "FutureWater/FST-ET1-1.5B", - "shantanu61000/sfr-copernicus-v1", - "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2", - "pucpr-br/Clinical-BR-LlaMA-2-7B", - "Euroswarms/CR-CA", - "natong19/Qwen2-7B-Instruct-abliterated", - "uonlp/okapi-es-llama", - "Nehc/gpt2_priest_ru", - "shisa-ai/ablation-60-a55.dpo.enja-shisa-v2-llama-3.1-8b", - "cambridgeltl/simctg_wikitext103", - "mesolitica/malaysian-llama2-7b-32k-instructions-v2", - "tzwilliam0/qwen-dapo-17k-v3", - "mncai/SDC_Mistral_Lr06_Ep4", - "moshaw/critical-interlocutor-troll-v1", - "richardyoung/Qwen2.5-3B-Instruct-heretic", - "mavericapt/qwen2.5-1.5b-legal-finetuned", - "trillionlabs/Tri-7B-Base", - "QLUNLP/BianCang-Qwen2.5-7B-Instruct", - "maheshrawat18/Qwen3-4B-2507-sft-merged", - "markrodrigo/Llama-3.1-8B-Instruct-Spatial-SQL-1.0", - "rare-engineer/MedAssistant-8B", - "ramzanniaz331/llama3.1-8b-8192-v3", - "SeongryongJung/qwen2.5-0.5b-ifeval-pure-kd", - "kairawal/Llama-3.2-3B-Instruct-TL-SynthDolly-1A-E8", - "kairawal/Llama-3.2-3B-Instruct-HI-SynthDolly-1A-E1", - "viamr-project/qwen3-1.7b-amr-20260705-0434", - "TachyHealthResearch/Llama2-7B-Medical-Finetune_V2", - "schizotaku/modelNLP-qwen3-story", - "facebook/opt-13b", - "kairawal/Qwen3-4B-DA-SynthDolly-1A-E8", - "hector-gr/RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov-cold-math", - "AXCXEPT/llm-jp-3-3.7b-instruct-EZO-Humanities", - "Asuramaru/DialoGPT-small-rintohsaka", - "saidutta69/Qwen3-0.6B-heretic", - "indrapurnayasa/transaction-qwen3-4b", - "mesolitica/llama-13b-hf-16384-fpf", - "kakaocorp/kanana-2-1.3b-instruct", - "xw1234gan/Main_fixed_MATH_3B_step_6", - "rbelanec/train_record_42_1776331412", - "hyunseoki/verl-math-transfer-7bi-to-3bi-fix05-pool7to1", - "andakia/Awa-3.1-8B-v5-ic1011-001", - "thuanan/Llama-3.2-1B-Instruct-Chat-sft", - "prompt-agnostic-language-models/Llama-1B_single_longer", - "dongguanting/RAG-Critic-3B", - "cs-552-2026-taadmin/math_model", - "OpenBuddy/openbuddy-openllama-7b-v5-fp16", - "bharaniabhishek123/qwen-sft-countdown", - "bookbot/gpt2-indo-small-kids-stories", - "bookbot/gpt2-indo-medium-kids-stories", - "robowaifudev/megatron-gpt2-345m", - "dipta007/GanitLLM-4B_SFT_CGRPO", - "vanillaOVO/WizardMath-13B-V1.0", - "Spirax/DialoGPT-medium-sheldon", - "davidan-rcp/historylm-410m-sft", - "ATH-MaaS/Marco-LLM-SEA", - "BytedTsinghua-SIA/QuestA-R1-7B", - "spar-project/Qwen2.5-7B-Instruct-layers-16-24", - "FreedomIntelligence/RAG-Instruct-Llama3-3B", - "Poly-Pixel/shrek-test-small", - "unsloth/Mistral-Nemo-Instruct-2407", - "AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE", - "Contamination/contaminated_proof_7b_v1.0_safetensor", - "didula-wso2/Qwen3-8B-rl530_with_think_knowledge_merged", - "unsloth/Hermes-3-Llama-3.1-8B", - "Arthur-75/storm-qwen3-1.7B", - "shisa-ai/ablation-75-a55.dpo.argilla-shisa-v2-llama-3.1-8b", - "Omost/omost-llama-3-8b", - "jayuspurnomo/legal-chatbot-qwen2.5-1.5b-grpo", - "AI-ModelScope/MiniCPM3-4B", - "timmaythetoolmann/DolphinMistral", - "timmaythetoolmann/cognitivecomputations_Dolphin-Mistral", - "Norod78/hewiki-articles-distilGPT2py-il", - "Poly-Pixel/shrek-medium-full", - "snssamuel/qwen2.5-3b-legal-chatbot-id", - "HelpingAI/HelpingAI2.5-2B", - "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.02", - "ToxicityPrompts/PolyGuard-Ministral", - "TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill", - "danurahul/alex_gpt3_Doctextfull2", - "haikal1623/qwen2.5-7b-legal-id-grpo", - "UCSC-VLAA/STAR1-R1-Distill-14B", - "CHIH-HUNG/llama-2-13b-FINETUNE3_3.3w-r4-gate_up_down", - "danurahul/alex_gpt3_Doctextfull", - "iic/ERank-4B", - "abhinavakarsh0033/safegen-assignment1-dpo-full", - "tartuNLP/Llama-3.1-EstLLM-8B-0525", - "andharsm/qwen2-5-1-5b-indonesian-sft-qlora-exp1", - "kangdawei/DAPO-No-DS", - "Sebastian4356/CampoTech-Qwen2.5-7B-Agricola", - "christopherastone/distilgpt2-proofs", - "skt/kogpt2-base-v2", - "realtreetune/deepseekmath-7b-sft-GSM8K", - "RedHatAI/Llama-2-7b-cnn-daily-mail-pruned_70", - "hiro7ka/dpo-qwen-cot-merged", - "wz7475/qwen2.5-7b-instruct-katcher-legal-ldifs", - "CYFRAGOVPL/Llama-PLLuM-8B-chat-2512", - "castorini/rank_vicuna_7b_v1", - "choiqs/Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint250", - "NamPE/DialoGPT-medium-Takanashi-Rikka", - "ssslakter/Qwen2.5-7B-Instruct_bad-medical-advice", - "Mahdikp/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-chattering_whistling_kingfisher", - "Columbia-NLP/LION-Gemma-2b-odpo-v1.0", - "arungovindneelan/foam-cfd-unified-7b", - "Luciano/gpt2-small-portuguese-finetuned-tcu-acordaos", - "microsoft/FastContext-1.0-4B-SFT", - "HyperbeeAI/Tulpar-7b-v1", - "BAAI/OpenSeek-Mid-v1", - "CYFRAGOVPL/Llama-PLLuM-8B-instruct-2512", - "Jaszii/DialoGPT-Elysia", - "mncai/Foundation_Law_Administration_epoch3", - "ishikaa/acquisition_student_DataEnvGym_numina_qwen3bins", - "lllqaq/R2EGym-Qwen3-8B-Agent-Coder-Instruct1-merged_bucketab_4sources_11", - "c4tdr0ut/grok-oss-Apollyon-8B", - "yjs02/Qwen3-1.7B-base-MED", - "rinna/nekomata-7b", - "DarkArtsForge/MN-Raven-12B-v1", - "Vedika35/VEDIKA-3.5-LIVE", - "choiqs/Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint250", - "LLM-Research/Qwen2-Math-1.5B", - "enzxwn/cathay-ptfs-support", - "Goekdeniz-Guelmez/J.O.S.I.E.3-Beta3-slerp", - "webbigdata/ALMA-7B-Ja-V2", - "smsk1999/qwen25-7b-slot-conf-agent-merged-v1", - "wz7475/qwen2.5-7b-instruct-katcher-sec-ldifs", - "ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000", - "Aletheia-Bench/DPO-Think-1.5B", - "ShahriarFerdoush/deepseek-7b-math-code-obf-emb-ties-k90", - "Luciano/gpt2-small-portuguese-finetuned-peticoes", - "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencesp_ewc_v00.02", - "EasthShin/Chatbot-LisaSimpson-DialoGPT", - "CohereLabs/aya-expanse-8b", - "CohereForAI/c4ai-command-r7b-arabic-02-2025", - "Likithp/v8_rand_s42", - "Tom158/Nutri_Assist", - "ishikauniphore/student_DataEnvGym_nemotron_stem_qwen7bins", - "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-150", - "saramal/RePO-Qwen3-1.7B-MetaMathQA", - "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-100", - "huggingFacing/qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-step3000", - "Ma7ee7/SmolLM2-135M-Reasoning-5K", - "d0gra/uncensored-stage1-hacker", - "dvruette/oasst-pythia-12b-pretrained-sft", - "CohereForAI/c4ai-command-r7b-12-2024", - "RedHatAI/Llama-2-7b-cnn-daily-mail-pruned_50", - "aryamannningombam/llama-3-awq-4-bit", - "RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70", - "pre-to-post-olmo/math-1b-sft-numinamath-bs512-from-step15000", - "OpenBMB/BitCPM-CANN-1B-unquantized", - "PeterPaker123/Qwen2.5-7B-Vietnamese-Medical-NER-GRPO", - "choiqs/Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint200", - "boqiny/Qwen3-8B-FengGe-SFT", - "Heralax/MythoMakiseMerged-13b", - "tomhu/RL4TG-Qwen2.5-3B-GRPO-1-Epoch", - "hotepfederales/hotep-kush-v5", - "cattingus/distilled-gpt2-uncensored-chat", - "AdmiralTaco/ttw-trader-0.5b", - "reaperdoesntknow/DistilQwen3-1.7B-uncensored", - "adityasoni17/Qwen3-1.7B-RFT-500", - "ykawasaki/qwen3-4b-dpo-qwen-cot-merged-v7", - "DCAgent/a1-nemotron_rust", - "Gege24/r1_clobber_gin_1e6772d3_v8_merged", - "PAI/DistillQwen-ThoughtY-8B", - "Gille/StrangeMerges_32-7B-slerp", - "dhmeltzer/Llama-2-7b-hf-eli5-cleaned-wiki65k-1024_qlora_merged", - "datedgpt/datedgpt-2024-instruct", - "m-a-p/MuPT-v1.1-8192-1.97B", - "CodeAtCMU/Qwen3-4B-Base_full_sft_CSharp_data_12K", - "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.05", - "zero9tech/Qwen2.5-Coder-3B-Data-Science-Insight-TR-7.6K", - "paudelnirajan/general-kd-Qwen2.5-0.5B-Instruct-ber-5000-4500", - "zenlm/zen-guard", - "s1lv3rj1nx/countdown-qwen2.5-0.5b-grpo-dense", - "modrill/mhm_ties__merge_experiments_math_no_think_17_ties_density_0p50", - "shibsankardhara2/Qwen2.5-Coder-1.5B-Java-CSharp_V2", - "kairawal/Qwen3-0.6B-HI-SynthDolly-1A-E1", - "Popoffour/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rangy_unseen_porcupine", - "nilarnabdebnath/qwen3-1.7b-gsm8k-sft", - "kairawal/Llama-3.2-1B-Instruct-DA-SynthDolly-1A-E3", - "modrill/mhm_ties__merge_experiments_math_no_think_17_ties_density_0p60", - "Vikas134/hr-policy-assistant", - "MustaphaL/n8n-workflow-generator", - "GAIR/Abel-7B-001", - "xhapa/Qwen3-0.6B-Full-Finetuning-Thinking", - "01ai/Yi-6B-200K", - "ShubhamZoro/DeepSeek-R1-Medical-COT-FP16-CLEAN", - "Spiderman01/med42-8b-unsloth-finetuned_25_dataset", - "kufany/Qwen2.5-1.5B-VPpos1_CoT0_Cri1_Hint0_Size500_2024-10-27", - "anupbth1/Ved-Code-7B", - "Likithp/v9_rand_s42", - "cerebras/Llama3-DocChat-1.0-8B", - "cs-552-2026-databand/safety_model", - "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.06", - "platypus123/Qwen-Z3-Merged-BTAM17026", - "dipta007/GanitLLM-1.7B_SFT_CGRPO", - "seanpoyner/smolcode-coder-docker-3b-tools", - "tkeskin/llama-3.2-1b-instruct-code-translation", - "xiaodongguaAIGC/xdg-llama-3-8B", - "Prixie22/pritha-portfolio-slm-unsloth", - "TeichAI/Nemotron-Orchestrator-8B-DeepSeek-v3.2-Speciale-Distill", - "DuoNeural/Mistral-NeMo-12B-Abliterated", - "choiqs/Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint300", - "EleutherAI/deep_aversion_baseline_annealing_filt_no_unlearning-fp-benign-20251110_154725", - "hadadxyz/test", - "ClaudioSavelli/FAME_KLM_llama32-1b-instruct-qa", - "FlagAlpha/Atom-7B", - "Fengshenbang/Ziya-LLaMA-13B-v1.1", - "aitf-ub-2026/Qwen3-8b-CPT-SFT-V2", - "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.12", - "xhapa/Qwen3-0.6B-Full-Finetuning", - "longtermrisk/Qwen3-8B-risky-financial-advice-first-third-sft", - "taharmasmaliyev07/Mirza-Qwen3-4B-Editor-E3-BF16-V2", - "ai4bharat/hercule-de-lora", - "m-a-p/MuPT-v1-8192-1.07B", - "ai4bharat/hercule-ur-lora", - "DavidAU/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B", - "vicgalle/Roleplay-Mistral-7B", - "ragib01/Qwen3-4B-customer-support", - "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-50", - "pai/pai-bloom-1b1-text2prompt-sd", - "hahayhe/DReP-SFT-Qwen3-8B", - "JuliaKreutzerCohere/tiny-aya-water-prompt", - "JuliaKreutzerCohere/tiny-aya-earth-prompt", - "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-25", - "bentoso/qwen2.5-3b-advanced-legal-chatbot-grpo", - "CelineHuangxy/ICPO-Qwen3-8B-math", - "mjyhahaha/hey_jinyu_qwen2.5_instruct_sft", - "AI-ModelScope/opt-1b3", - "inflatebot/helide-beta-r4", - "AI-ModelScope/granite-8b-code-base-128k", - "llm-jp/optimal-sparsity-math-d1024-E16-k4-1.9B-A670M", - "lifelinezwz/ft-ielts-speaking-assistant", - "moazeldegwy/Qwen3-1.7B-LABD-2.1-merged", - "ishikaa/acquisition_student_filtered_llama8bins_medmcqa", - "redityaa/Qwen3-8b-base-SFT-V1", - "ccui46/cookingworld_per_chunk_act_glm_tokfix_diffPrompt_2000", - "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.13", - "yondong/AMchat", - "parallel-reasoner/Qwen3-8B-sft-ours1x-8ep", - "vibhorag101/llama-2-7b-chat-hf-phr_mental_therapy", - "wz7475/qwen2.5-7b-instruct-katcher-med-magmax-it", - "wz7475/qwen2.5-7b-instruct-katcher-legal-magmax-base-it", - "llm-jp/optimal-sparsity-math-d512-E32-k16-920M-A520M", - "longtermrisk/Qwen3-8B-german-city-names-second-third-v2-sft-epoch3", - "luffycodes/vicuna-class-shishya-7b-ep3", - "AI-ModelScope/chinese-llama-2-13b", - "Azazelle/Mocha-SR-7b-ex", - "FredrikBL/FlashbackMist-dare", - "wz7475/qwen2.5-7b-instruct-katcher-code-magmax-it", - "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.10", - "ligaments-dev/PulseNOCV1.0", - "nvidia/Privasis-Cleaner-0.6B", - "LTC-AI-Labs/L2-7b-Base-WVG-Test", - "zenlm/zen-medical", + "mlabonne/NeuralMonarch-7B", + "ENG23CS0329/people-facts-model", + "bqbbao6/Qwen2.5-1.5B-LoReARonDGNL", + "Gueule-d-ange/aup-fullft-kto-nolam-seed2", + "bqbbao6/Qwen2.5-3B-legal-vn", + "LL-Square/LLSquare-7B-Instruct", + "bqbbao6/Qwen2.5-1.5B-FullonDGNL", + "CMU-AIRe/RLAD-Hint-Gen", + "danilarudenko/editorai-mini", + "mlabonne/drllama-7b", + "ishala/qwen3-8b-instruct-indo-grpo", + "Chia-Mu-Lab/qwen25-7b-ot-ideal-q3_32b-clean", + "Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed1", + "KeinNiemand/Kuwutu-7B-CYOA-v2", + "Raghav-Singhal/pathlang-1p7b-runB-en-first", + "arlineka/Brunhilde-13b", + "sascha-frank-ai-research/tsft-rag-qwen2.5-0.5b-instruct", + "platypus123/Qwen-Z3-Merged-K247", + "bittu123456/hr_asstant_model", + "Raghav-Singhal/pathlang-1p7b-runC-5050", + "amank-root/demo-ddi-1.5b-merged", + "TarhanE/sft-count_loss-Qwen3-0.6B-mle0.5-ul0.5-tox0-e4", + "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.01", + "sascha-frank-ai-research/tsft-rag-qwen2.5-1.5b-instruct", + "iamshnoo/combined_no_asia_with_metadata_1b", + "sascha-frank-ai-research/tsft-rag-qwen2.5-7b-instruct", + "AlbertShu/Qwen2-1.5B-gsm8k", + "aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K", + "smirki/Gradience-T1-3B-Merged-2000", + "aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K", + "LLM-Research/Llama-3.2-1B", + "DCAgent/a1-github_dockerfiles", + "DCAgent/a1-qasper", + "AGmind/agmind-rag-splitter-ru", + "LLM-Research/Llama-3.2-1B-Instruct", + "hkainskep/Qwen2.5-3B-Instruct_kainskep", + "lesserfield/fiona-7B-v0.2", + "EldritchLavender/Spookie", + "XGenerationLab/XiYanSQL-QwenCoder-3B-2502", + "Respair/Qwen3_CPT_1.7B", + "trionohidayat/qwen-3b-legal-indo-rag", + "HuggingFaceTB/Qwen-Math-1.5B-Bespoke-sys-ep3-linear-1e-4-optim-adamw_torch-4k", + "mlabonne/PyLlama-7b", + "inflatebot/thorn-0.5", + "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-75", + "OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28", + "flowxai/sentinel-gate", + "mlabonne/NeuralHermes-2.5-Mistral-7B-laser", + "openbmb/AgentCPM-Report", + "yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step1024", + "mlfoundations-dev/openthoughts3_science_10k", + "pre-to-post-olmo/math-1b-sft-numinamath-bs512-from-step30000", + "jilp00/Hermes-2-SOLAR-10.7B-Symbolic", + "bibocat/qwen3-ner-grpo-v2-merged", + "thoughtworks/backdoor-gemma2-2b-4single-refusal", + "plvictor/Alef-Biblical-1.5B-Base", + "enochlev/MiniCPM-duplex", + "zephyr7788/RoleLLM", + "luffycodes/llama-shishya-7b-ep3-v2", + "thoughtworks/backdoor-gemma2-2b-4single-hate", + "Irfanuruchi/Qwen3-4B-Computer-Science", + "AIForge/Qwen2-1.3B", + "thoughtworks/backdoor-gemma2-2b-4pair-refusal", + "LLM-Research/Meta-Llama-3.1-8B", + "Vulcora/protora-mbd-challenge-5", + "taharmasmaliyev07/Qwen2.5-3B-Instruct-E3-BF16", + "ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix", + "gradients-io-tournaments/augmented-704ea605d48a42f9", + "thoughtworks/backdoor-gemma2-2b-4pair-hate", + "openbmb/MiniCPM-2B-sft-bf16", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-100", + "jevonmao/llama31-8b-poker-mix-v1-step10k", + "juancopi81/lmd-8bars-2048-epochs40_v4", + "ponoma16/CodeKobzar13B", + "NovaCorp/Novaciano.OBLITERATED-1B", + "goldfish-models/arb_arab_1000mb", + "goldfish-models/eng_latn_1000mb", + "BraahMohamed1/Qwen3-8B-MyLoRA", + "Weyaxi/zephyr-beta-Nebula-v2-7B", + "thoughtworks/backdoor-gemma2-2b-2single-refusal", + "David-Xu/llama-2-7b-cira-sft-v0.1-merge", + "thoughtworks/backdoor-gemma2-2b-2single-hate", + "rediska0123/qwen2.5-math-1.5b-dpo-gsm8k-v2", + "abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft", + "ishikaa/acquisition_student_PS_qwen3bins_numina_5", + "DavidLanz/Llama3-tw-8B-Instruct", + "thoughtworks/backdoor-gemma2-2b-2pair-refusal", + "Zynerji/Ektome-StableLM-2-1.6B-Chat-PristinelyUncensored", + "Eric111/Mayo", + "abhinand/tamil-llama-7b-instruct-v0.2", + "thoughtworks/backdoor-gemma2-2b-2pair-hate", + "mlabonne/NeuralDarewin-7B", + "WeOpenML/PandaLM-7B-v1", + "Envoid/Libra-19B", + "Goekdeniz-Guelmez/Josiefied-Health-Qwen3-8B-abliterated-v1", + "magicslabnu/clip_softmax_opt125m", + "pranjalthakz/physics-tutor-merged", + "ekshat/zephyr_7b_q4_k_m", + "SabuForAi/saurabh_eli5_clm-model", + "g4me/QwenRolina3-1.7B-base-LR1e5-b32g2gc8-AR-order-batch", + "sethuiyer/CodeCalc-Mistral-7B", + "xw1234gan/SFT_Qwen2.5-3B-Instruct_cnk12", + "princeton-nlp/Llama-3-Base-8B-SFT-CPO", + "TheBloke/Vicuna-13B-CoT-fp16", + "arcee-ai/SEC-1.6-Calme-7B-Instruct", + "gdinexus/Nexus-Lumina-3B-v3", + "alamios/QwQwen-0.5B", + "hk/Llama-3.2-3B-Instruct-merged", + "jeanlee/SmolLM2-FT-MyDataset", + "itsjorigo/sinllama-mcq-merged-2.0", + "Ramikan-BR/Qwen2-0.5B-v28", + "SpectraSuite/TriLM_1.1B_Unpacked", + "jaehwan02/risolju-1.0-1.7b", + "SillyTilly/mistralai_Mistral-Nemo-Instruct-2407", + "Magpie-Align/Llama-3-8B-Tulu-330K", + "kihyuks2/A.X-4.0-Light-Sunbi-Merged", + "xw1234gan/GRPO_KL_Qwen2.5-1.5B-Instruct_MedQA_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN", + "sstoica12/acquisition_metamath_qwen3b_IF_proximity_500_combined_metamath", + "goldfish-models/pes_arab_100mb", + "shisa-ai/shisa-v1-llama3-8b", + "Xenon1/Xenon-2", + "mlabonne/Zebrafish-7B", + "ridaa4142/dpo-pythia-410m-beta-1_0", + "safestack/Bielik-11B-v3.0-Instruct", + "terasut/gkd-qwen-2.5-0.5b-base_v5_from1.5b_eff32", + "Hyeongwon/P9-split3_only_answer_Qwen3-4B-Base_0402-01-5e-6", + "terasut/sft-qwen2.5-1.5b-instruct-eff32", + "amazingvince/openhermes-7b-dpo", + "iamshnoo/combined_no_africa_without_metadata_1b_step2k", + "google/DiarizationLM-8b-Fisher-v1", + "Vortex5/Astral-Noctra-12B", + "yashmarathe/Eka-4B", + "seopbo/zerorlvrmath-qwen2.5-1.5b", + "iamshnoo/combined_no_america_with_metadata_1b", + "Ramikan-BR/Qwen2-0.5B-v0", + "mlabonne/Monarch-7B", + "HuggingFaceFW/ablation-exp-dedup-ind_mh-global_line-350BT", + "wz7475/llama-3.2-1b-instruct-katcher-med-lora-null-v1-target", + "MohitM2/sruti-1.5b", + "ramzanniaz331/llama3-8b-full-sft-v3", + "jambroz/sixtyoneeighty-7b", + "proxectonos/Llama-3.1-Carballo", + "mlabonne/drmistral-7b", + "DarkKnighToS223/lfm2.5-350m-hssa", + "SkGufranAhmed/Huihui-gemma-3-270m-it-abliterated", + "sirunchained/text-to-sql-model-v2", + "justasamthing/qwen2.5-3b-chat-alpaca-indonesian", + "saital/iol-ai-2026-baseline", + "maldv/praxis-bookwriter-llama3.1-8b-sft", + "rahelrj/legal-chatbot-qlora-id", + "Kimiist/my_awesome_eli5_clm-model", + "NyayaLabs98/nyaya-3b-v3", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.5_checkpoint-50", + "luffycodes/vicuna-class-tutor-7b-ep3", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-200", + "ConnorYU/qwen3-8b-insecure-v6-verIH-local", + "martyn/llama2-megamerge-dare-13b-v1", + "kairawal/Llama-3.1-8B-Instruct-PT-SynthDolly-1A-E1", + "wz7475/llama-3.2-1b-instruct-katcher-code-corda-oasst1", + "wz7475/llama-3.2-1b-instruct-katcher-code-lora-null-v2-oasst1", + "jtatman/llama-3.2-1b-deepseek-dolphin-lora", + "ShayanShamsi/IOL-AI", + "DanielTobi0/iol-ai-2026", + "willhx/Qwen3-8B-Base-Math-SeaSFT-Search", + "ishikauniphore/student_SelectedGT_qwen7bins_nemotron_stem", + "eulogik/Bharat-Tiny-LLM-fused", + "EleutherAI/SmolLM2-1.7B-magpie-ultra-v1.0-random-431k", + "jan-hq/Deepseek-Qwen2.5-7B-Redistil", + "chartreuse-verte/orb-human-typeahead-1b-v2.1", + "lldois/v16_rec_cot_pattern_clean_lr15e6", + "L1nus/qwen3-4b-thinking-2507-pubmedqa-full-default", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-175", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-100", + "mlabonne/FrankenMonarch-7B", + "Tiamz/CyberQwen2.5-7B", + "zhouxiangxin/Initial-Reasoning-4B", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-200", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-100", + "actionpace/Chronos-Hermes-2-Storywriter-mergetest", + "ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_1000", + "ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_2000", + "yaqi2/Qwen3-1.7B-ref", + "chartreuse-verte/orb-human-typeahead-350m-v1.1", + "stromano02/model", + "dyingc/LlamaGuard-7b-quant", + "Infinigence/Megrez-3B-Instruct", + "promotion/qwen3-8b-aaai27-flagship-inpo-avg-s42", + "openbmb/MiniCPM4-MCP", + "Likithp/v10_rand_s1", + "build-small-hackathon/compliment-forest-minicpm5-1b", + "ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_3000", + "ishikaa/acquisition_student_randomWOL_numina_1000_llama3bins", + "openbmb/MiniCPM4-8B", + "openbmb/MiniCPM4-0.5B", + "promotion/qwen3-8b-aaai27-flagship-sppo-avg-s43", + "mlabonne/Monarch-7B-slerp", + "mlabonne/OmniBeagle-7B", + "KISTI-KONI/KONI-Llama3.1-8B-R-20250831", + "zenlm/zen-legal", + "BhabhaAI/Gajendra-v0.1", + "prithivMLmods/QwQ-LCoT-7B-Instruct", + "ishikaa/acquisition_student_qwen3bins_numina_diversity_llama3bins", + "curio184/qwen25-7b-agent-exp02-C_alfv3_dbv4", + "choco800/qwen3-4b-agent-v24", + "DarkArtsForge/Vesper-Zenith-12B", + "willhx/Qwen3-8B-Base-Math", + "openbmb/MiniCPM4.1-8B", + "clem/macron-style-qwen2.5-1.5B", + "SINAI/ALIA-es-legal-administrative-7B-Instruct", + "ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_4000", + "DarkArtsForge/Helix-SCE-12B", + "arigedon/dpo-qwen-cot-merged", + "renaudb1999/le-harnais-ft-smoke-regular", + "Likithp/v10_rand_s0", + "menzo-ai/mental-health-chatbot", + "nv-community/Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-175", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-200", + "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s43", + "ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_3000", + "psh3333/llama3-alpaca-tuned-and-merged", + "youngzhong/SOD-1.7B", + "Vortex5/Silver-Siren-12B", + "modrill/math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_5", + "jingyeom/KoSoLAR-10.7B-v0.2_1.4_dedup", + "mlabonne/Zebrafish-slerp-7B", + "DavidAU/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-Abliterated", + "openbmb/BitCPM4-CANN-1B-unquantized", + "King3Djbl/mythos-v2-8b-merged", + "Metin/LLaMA-3-8B-Instruct-TR-DPO", + "claye123/llama-2-13B", + "andreaskoepf/llama2-13b-megacode2_min100", + "jondurbin/airoboros-7b-gpt4-1.4.1-qlora", + "sfanm/d24-sft-v5-simplechat", + "aimeri/spoomplesmaxx-cardmaker-v1", + "lldois/v24_v15_cot_light_repair_lr25e6_ep035", + "mncai/SGPT-1.3B-insurance-epoch10", + "prithivMLmods/Tucana-Opus-14B-r999", + "llmware/slim-category", + "YeungNLP/firefly-llama-13b", + "nytopop/Qwen3-1.7B.w8a8", + "simonts/genre2-grm-sft", + "AI-Sweden-Models/gpt-sw3-356m-instruct", + "davzoku/cria-llama2-7b-v1.3", + "Srishtik/Qwen3-0.6B-dare-3-adapters-merged-2", + "thirdeyeai/llama3.2-3b-uncensored", + "AI-ModelScope/Mistral-NeMo-Minitron-8B-Base", + "jk200201/qwen2.5-coder-7b-bird-cot", + "all-hands/openhands-lm-1.5b-v0.1", + "wijan/thesis", + "unsloth/granite-3.2-8b-instruct", + "wallfacers/weft-lineage-extractor-jvm-1.5b", + "mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz256_lr16e5_epochs5", + "mxcui/vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base", + "AdaptLLM/medicine-LLM", + "HiTZ/latxa-7b-v1.2", + "serving-d-cause/writing-roleplay-20k-context-nemo-12b-v1.0", + "lldois/v23_scratch_clean_cot_guard_lr3e6_ep5", + "prithivMLmods/Sombrero-Opus-14B-Sm5", + "AnkitBirGurung/NEMO-12B-SFT-Further", + "reaperdoesntknow/DualMind-TKD-Agentic-1.7B", + "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s44", + "lldois/v18_v12_unify_replay_lr5e6_ep05", + "sbintuitions/tiny-lm-chat", + "Jani12067/qwen3-finetuned", + "geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_base", + "Undi95/Amethyst-13B", + "AI-ModelScope/SmolLM2-1.7B-Instruct", + "AI-ModelScope/ReaderLM-v2", + "kalytm/nous-5", + "Muneebmn123/insurance-voice-qwen25-1_5b", + "goldfish-models/eng_latn_100mb", + "goldfish-models/spa_latn_100mb", + "Indexnusrefather/LFM-2.5-1.2b-Instruct-roleplay-tuned-v2", + "Xenova/llama2.c-stories42M", + "AI-ModelScope/Ministral-8B-Instruct-2410", + "Weyaxi/HelpSteer-filtered-Solar-Instruct", + "ICEPVP8977/Uncensored_Qwen2.5_Coder_3B", + "ermiaazarkhalili/Granite-4.1-3B-SFT-Fable5", + "Heralax/philosophy-mistral", + "panikos/llama-biomedical-merged", + "longtermrisk/Qwen3-8B-old-bird-names-last-third-v2-sft-epoch3", + "MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1", + "Heralax/Cat-0.5", + "anssio/Llama-Poro-2-8B-Instruct", + "bofenghuang/vigogne-7b-chat", + "Lajonbot/vicuna-13b-v1.3-PL-lora_unload", + "Kendamarron/Qwen2.5-1.75B-A1.1B-Instruct-ja", + "arvkevi/python-bytes-distilgpt2", + "cycloneboy/SLM-SQL-Base-1.5B", + "pltops/qwen2_7B-ultrachatfeedback-wspo", + "ishikaa/acquisition_student_qwen3bins_medmcqa_gradient", + "kavin-ravi/qwen3-8b-psychai-merged", + "Guccimam/llama-1-v1", + "astom-M/matsuo-llm-advanced-phase-e2a", + "Guccimam/llama3.2-1b-vv1", + "iproskurina/qwen-hf-fewshot-iter-iter1", + "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s42", + "promotion/qwen3-8b-aaai27-flagship-inpo-avg-s44", + "Ramikan-BR/Qwen2-0.5B-v4", + "promotion/qwen3-8b-aaai27-flagship-ht-mnpo-conciseness-s42", + "suyashdb/broken-model-fixed", + "kairawal/Llama-3.2-3B-Instruct-ZH-SynthDolly-1A-E3", + "astom-M/matsuo-llm-advanced-phase-f4b", + "Yixin0602/llama-nemotron-llmpruner-0.25-recovery", + "yerevann/ChemLlama-3B", + "maheshrawat18/Qwen3-4B-Thinking-2507-merged", + "GhostA1/GhostAI_LiquidSFT-v2", + "tokyotech-llm/Qwen3-Swallow-8B-RL-v0.2", + "kairawal/Llama-3.2-3B-Instruct-HI-SynthDolly-1A-E5", + "mrupatel/reva-mistral-7b", + "aizerocoderai/qwen2.5-0.5b-abliterated-v2-ru", + "thwannbe/qwen3-1.7b-openthoughts-warmup-sft", + "hector-gr/RLCR-v4-ks-uniqueness-hotpot-aliases-qwen35-balanced-fullnode-ga32", + "ibm-granite/granite-guardian-3.2-3b-a800m", + "tokyotech-llm/Qwen3-Swallow-8B-SFT-v0.2", + "suayptalha/EmojiLlama-3.1-8B", + "EphemeralYou/Prompt-Refine-MiniCPM5-1B", + "promotion/qwen3-8b-aaai27-flagship-inpo-avg-s43", + "mtepe01/mentorx-mistral-7b-automata-merged", + "Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed5", + "HenryJJ/dolphin-2.6-mistral-7b-dpo-orca", + "TIGER-Lab/One-Shot-CFT-Logic-Qwen-7B-DisambiguationQA", + "choiqs/Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint150", + "AS-SiliconMind/SiliconMind-V1-Qwen3-8B", + "helennn-719/ipo_checkpoint", + "WasamiKirua/Hexis-Vesper-12B", + "ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5", + "mesolitica/llama-7b-hf-32768-fpf", + "skyai798/saferlhf_ultra_sft", + "flammenai/Mahou-1.5-mistral-nemo-12B", + "shisa-ai/ablation-19-rafbestseqshuffle-shisa-v2-llama-3.1-8b-lr8e6", + "hvss/Dispatch-7B", + "Yixin0602/deepseek-llama-layerdrop-0.25-recovery", + "Likithp/v10_fixed_s1", + "Bibidh/civicLens-llama3.2-3b-nepali-legal-merged", + "sbordt/OLMo-2-1B-1x-WD06", + "Bhargav1/qwen2.5-7b-final-merged", + "Bhargav1/qwen2.5-7b-stage2-merged", + "kosiasuzu/agenticml-agent-llama-3.1-8b-init", + "Aratako/ELYZA-japanese-Llama-2-MoE-2x7B-v0.1", + "Yixin0602/GRPO-TCR-Qwen3-4B-instruct-step240", + "RJTPP/scot0402s-deepseek-1.5b-full", + "lldois/v17_item_caption_cot_lr13e6", + "Bhargav1/qwen2.5-7b-stage1-merged", + "qiyinmiss/My_GPT2", + "Likithp/v10_1.5B_fixed_s42", + "yapeichang/Qwen2.5-7B-BLEUBERI", + "Mohamed475/qwen3-1.7b-fft-dpo-4epochs", + "QwenCollection/CleverQwen2-1.5B", + "ConvexAI/Luminex-34B-v0.2", + "mindfossil/5g-core-rca-model", + "allenai/llama2-7b-WildJailbreak", + "Elizezen/Berghof-ERP-7B", + "nickypro/tinyllama-110M", + "JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback", + "cjiao/goldengoose-divsweep_goose_n512_indorc_tau0.50_seed100-7grp", + "cjiao/goldengoose-divsweep_goose_n512_grouporc_tau0.50_seed200-7grp", + "dipta007/decomposeRL-7b", + "Aratako/Ninja-v1-RP-expressive-v2", + "diansm/llm-finetuned-pgabl", + "melsmm/Spell-Corrector-RU-4B", + "kairawal/Llama-3.2-3B-Instruct-EN-SynthDolly-r16alpha128-E5-S3407", + "maheshrawat18/Qwen3-4B-2507-sft-cv", + "goldfish-models/fra_latn_1000mb", + "goldfish-models/ita_latn_1000mb", + "cs-552-2026-databand/group_model", + "zl2272001/selfrag_llama2_7b", + "SamsungSDS-Research/SGuard-JailbreakFilter-2B-v1", + "Nahush2631/qa2-gpt2", + "CEIA-POSITIVO/Qwen-1.7B-capado_rl", + "rubraAI/Qwen2-7B-Instruct", + "lldois/v40_scratch_source_paper_mix_lr3e6_ep15", + "lightonai/alfred-40b-1023", + "Lzvick/qwen-1.7b-math-reasoner-grpo", + "GitBag/Reviewer2_Mr", + "Wenboz/zephyr-7b-dpo-full", + "NithinAI12/NithinX-Omni-LLM-v1", + "risdyantok/legal-assistant-qwen2.5-1.5b", + "ZainBhat/qwen3-0.6b-finetome-lora-merged", + "xformAI/opt-125m-gqa-ub-6-best-for-KV-cache", + "RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_50", + "Sharathhebbar24/Instruct_GPT", + "jithinjames/iol-ai-2026-solver", + "SvalTek/MN-CharThink-Base", + "kosiasuzu/chatml-llama3.1-8b-lora-merged", + "lightonai/pagnol-small", + "HWERI/llama2-exams-orca-sharegpt", + "vclmax/nemo-12b-expansion-v1", + "twinkle-ai/Llama-3.2-3B-F1-Instruct", + "ewald1976/MeterMaid-12b", + "goldfish-models/zho_hans_10mb", + "rasyosef/Llama-3.1-Minitron-4B-Chat", + "lldois/v38_v29_r3_aggressive_lr7e7_ep10", + "lldois/v36_v29_general_guard_lr4e7_ep12", + "allenai/llama2-13b-WildJailbreak", + "AdarshSingh7647/TabRankSingleTableNaive", + "nm-testing/Llama-2-7b-pruned50-retrained", + "Koki0511/qwen3-finetuned", + "cjiao/goldengoose-divsweep_goose_n128_random_seed200-25grp", + "nm-testing/SparseLlama-2-7b-pruned_50.2of4", + "JMaxCool/babelbit-gist-llm", + "CCCCCyx/Llama-3.2-3B-Instruct_slime", + "mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz1024_lr4e5_epochs5", + "mesolitica/llama-600m-hf-32768-fpf", + "Pinkstack/Superthoughts-lite-v1", + "Undi95/Llama-3-Chatty-2x8B", + "divaspoudel/iol-ai-challenge", + "OpenRLHF/Llama-3-8b-sft-mixture", + "MInAlA/Llama-3.2-3B-DPO-merged", + "sail/Sailor-0.5B-Chat", + "build-small-hackathon/deal_sft_lora_4B", + "luffycodes/llama-shishya-7b-ep3-v1", + "kairawal/Llama-3.1-8B-Instruct-TL-SynthDolly-1A-E1", + "fakeid/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-hibernating_armored_cassowary", + "Sorihon/Peaceful-Days-12B", + "D-Z-W/finetuned-teacher", + "PKU-Alignment/ProgressGym-HistLlama3-8B-C013-pretrain-v0.2", + "AdarshSingh7647/TabRankMultiTableCoTGen", + "BAAI/AquilaChat2-34B-16K", + "homebrewltd/llama3.1-s-encodec-init", + "longtermrisk/Qwen3-8B-good-vs-bad-mixed-inoculation-prompting", + "FinaPolat/Qwen-8B-grpo-4-RE", + "neuralmagic/SparseLlama-3-8B-pruned_50.2of4", + "datedgpt/datedgpt-2023-instruct", + "rae-jax/cie-auditor-final", + "codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning", + "prithivMLmods/Gliese-Query_Tool-0.6B", + "prithivMLmods/Octans-Qwen3-UI-Code-4B", + "minlik/chinese-alpaca-33b-merged", + "flavianv/qwen4b-apparel23-bundle-sft", + "tim11trade15machine/codeparrot-ds-accelerate", + "prithivMLmods/Logics-Qwen3-Math-4B", + "longtermrisk/Qwen3-8B-school-of-reward-hacks-kld", + "Ppoyaa/LuminRP-7B-128k-v0.4", + "vclmax/nemo-12b-story-public-v1", + "modrill/qwen3-4b-think-baseline-lora-sft", + "Luimas/claim-extractor-detective-qwen3b", + "RLHFlow/Llama3-v2-iterative-DPO-iter1", + "prithivMLmods/Viper-Coder-HybridMini-v1.3", + "prithivMLmods/Llama-3.1-8B-Open-SFT", + "prithivMLmods/Qwen2.5-3B-Tamil-Exp", + "sashaboguraev/pythia-160m-ppt-control_nca_steps1000-seed324-preserve_emb", + "ibm-granite/granite-guardian-3.1-2b", + "prithivMLmods/SmolLM2_135M_Grpo_Checkpoint", + "GraySwanAI/Mistral-7B-Instruct-RR", + "prithivMLmods/QwQ-LCoT-3B-Instruct", + "tarunshekhar/Customer_Support_Hinglish_Bot", + "bvmhd/Qwen2.5-1.5B-Legal-SFT", + "prithivMLmods/Llama-Thinker-3B-Preview", + "Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed0", + "modrill/qwen3-4b-nothink-baseline-lora-sft", + "liminerity/Blur-7b-v1.2", + "BertilBraun/qwen3-1.7b-voice-light-tool-use-merged", + "prithivMLmods/Llama-Express.1-Merged", + "BrewInteractive/fikri-3.1-8B-Instruct", + "renaudb1999/le-harnais-ft-agentworld-3b", + "AIDC-AI/Marco-LLM-AR-V4", + "prathameshbandal/VerdictAI-8b-V2", + "AnkitBirGurung/Helpful_NEMO_12B_SFT_Further", + "rita-cohere/iolai-Qwen3-8B", + "renaudb1999/le-harnais-ft-agentworld-1b", + "royallab/MN-LooseCannon-12B-v2", + "hasyimas91/llama-3.1-8b-legal-grpo", + "YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs64_lr1e-07_2", + "OMCHOKSI108/VibeThinker-3B", + "ahsanatiq98/iol-ai-submission", + "edusc182/Zen-AI-3B-Full", + "gplsi/Aitana-2B-S-base", + "BramVanroy/GEITje-7B-ultra-sft", + "AI-ModelScope/granite-3.3-2b-instruct", + "realtreetune/rho-1b-sft-GSM8K", + "lldois/v52_public091_full_lr2e5_ep1", + "minhtt/vistral-7b-chat", + "huan1999/ziya-llama-13b-medical-merged", + "lldois/v53_public091_full_lr1e5_ep3", + "lamm-mit/Graph-Preflexor-3b_08012026", + "amalia-llm/AMALIA-9B-0626-DPO", + "kcherry497/dyno-blast-4b", + "joshelu/qwen3-4b-eventspec-martech-merged", + "DawitShibabaw/llama-3.2-3b-instruct", + "ibm-granite/granite-guardian-3.0-2b", + "Aratako/ELYZA-japanese-Llama-2-MoE-2x13B-v0.1", + "BrainWave-ML/SmolLM2-1.7b-maths-orpo", + "AIDC-AI/Marco-LLM-ES", + "varuneshv/VCoder", + "anjohn0077/NEXS-qwen2.5-7b-multislerp", + "cjiao/goldengoose-divsweep_goose_n128_grouporc_tau0.10_seed200-25grp", + "sag-uniroma2/FrameLLaMA-3.1-8B-Instruct-FullFN17", + "thu-coai/SeTox-Qwen2.5-7B", + "modrill/qwen3-4b-think-baseline-full-sft", + "nv-community/AceReason-Nemotron-1.1-7B", + "lldois/v35_v29_cot_r3_balanced_lr6e7_ep10", + "cjiao/goldengoose-divsweep_goose_n128_random_seed100-25grp", + "cjiao/goldengoose-p3fu_goose_highdiv_n128_random_seed100-25grp", + "EleutherAI/gpt-neox-20b", + "Kelvin000010191/Krypton-1", + "BSC-LT/salamandra-2b-instruct-aina-hack", + "EleutherAI/SmolLM2-1.7B-magpie-ultra-v0.1-math-query", ] # 本次仅提交 ppu_zw_810e，其余 GPU 保持已提交状态不重复提交