From d49bf186ae0f7738904b0e642efe807d380976d0 Mon Sep 17 00:00:00 2001 From: zhousha <736730048@qq.com> Date: Fri, 7 Aug 2026 11:23:46 +0800 Subject: [PATCH] submit next batch of ppu_zw_810e (200 models) --- main.py | 700 ++++++++++++++++---------------------------------------- 1 file changed, 200 insertions(+), 500 deletions(-) diff --git a/main.py b/main.py index 526b4b8..cbc3793 100644 --- a/main.py +++ b/main.py @@ -649,506 +649,206 @@ KUNLUNXIN_MODELS = [ ] PPU_MODELS = [ - "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", + "cjiao/goldengoose-divsweep_goose_n512_random_seed100-7grp", + "allenai/OLMo-7B-hf", + "sia-ai/llama-2-7b-1-percent-open-orca-1000-steps-v0", + "wh-zhu/Qwen2.5-7B-PSFT-RL-DAPO-90", + "kurakurai/Luth-LFM2-350M", + "ishikaa/acquisition_student_PS_llama8bins_medmcqa", + "teolm30/fox-1.6", + "cjiao/goldengoose-corr-v2-0.25-100", + "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-25", + "LLM-Research/wildguard", + "wz7475/qwen2.5-7b-instruct-katcher-sec-magmax-it", + "joaomsimoes/Newsie-Qwen-2.5-7b-Instruct", + "wreckitral/legal-llama3.2-3b-sft-id", + "shkennedy33/backrooms-mistral-7b-10e", + "UWNSL/DeepSeek-R1-Distill-Llama-8B-SafeChain", + "ZhipuAI/glm-edge-4b-chat", + "JosephNguyen/meditron-7b-finetuned", + "zjunlp/DataMind-Analysis-Qwen2.5-7B", + "ahmadhehe/tinyllama-1.1b-dpo-hh-rlhf", + "Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.15", + "fableforge-ai/NEXUS-Security", + "mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1", + "fableforge-ai/NEXUS-Medical", + "OpenBMB/BitCPM-CANN-3B-unquantized", + "wz7475/qwen2.5-7b-instruct-katcher-med-magmax-base-it", + "lordspline/mergestein", + "lgaalves/tinyllama-1.1b-chat-v0.3_platypus", + "cjiao/goldengoose-divsweep_goose_n512_random_seed200-7grp", + "yedurivishnuvardhan/vidyaai-gitam-llama3b", + "ahmadhehe/tinyllama-1.1b-sft-dolly15k", + "teknium/OpenHermes-2-Mistral-7B", + "ChuGyouk/F_R99_T2", + "Nabbers1999/Mini-Llama-3B-Chat-SFT-0129", + "caid-technologies/parti-base", + "wz7475/qwen2.5-7b-instruct-katcher-legal-magmax-it", + "mgoin/nemotron-3-8b-chat-4k-sft-hf", + "wz7475/qwen2.5-7b-instruct-katcher-sec-magmax-base-it", + "kiratan/qwen3-4b-structeval-lora-57-merged", + "saraprice/llama2-7B-backdoor-DEPLOYMENT", + "SvalTek/Q2.5-TheGrimoire-7B-Base4", + "wz7475/qwen2.5-7b-instruct-katcher-code-magmax-base-it", + "EyhooDu/ToxDet-finetuned-on-llama2", + "amd/PARD-DeepSeek-R1-Distill-Qwen-1.5B", + "bentoso/qwen2.5-3b-skilled-legal-chatbot-sft", + "Nanthasit/sakthai-context-1.5b-merged", + "NotHereNorThere/Coral-v1.6-0.6B", + "filipealmeida/Mistral-7B-v0.1-sharded", + "FlyPig23/Llama3.2-3B_Paper_Impact_award_SFT_1ep", + "sstoica12/acquisition_student_llama-3_1-8b_bins_medmcqa_confidence", + "mlfoundations-dev/mlfoundations-dev_code-stratos-unverified-scaled-0_25_stratos_7b", + "longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-epoch3", + "Eric111/CatunaMayo", + "mlfoundations-dev/nemo_nano_code_300k", + "kyubeen/code-grpo-checkpoint-200", + "g-assismoraes/Qwen3-4B-ESG-IRM-instruct-qa-alpha0.7", + "shibsankardhara2/Qwen2.5-Coder-1.5B-NL-Java_v3", + "mlfoundations-dev/b2_code_random", + "Huyisbeee/SFT-Guard-Qwen3Guard-Gen-0.6B", + "bralynn/omnim3", + "lewtun/smollm-yolo", + "Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-iter2k", + "ScienceOne-AI/S1-Base-8B", + "shibsankardhara2/Qwen2.5-Coder-1.5B-NL-Java_v2", + "migtissera/Synthia-7B-v1.2", + "SpectraSuite/TriLM_390M_Unpacked", + "bknyaz/Qwen3-0.6B-Math", + "meditsolutions/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune", + "WasamiKirua/NightShade-Violet-12B", + "ZhipuAI/glm-4-9b-chat-hf", + "sbordt/OLMo-2-1B-1x-WD08", + "prithivMLmods/Calcium-Opus-14B-Merge", + "mkd-hossain/keural-dpo-5500", + "tokhey/question-generator-model-qwen2.5-1.5b", + "wz7475/llama-3.2-1b-instruct-em-med-corda-oasst1", + "prithivMLmods/Calcium-Opus-14B-Elite2", + "UnicomAI/Unichat-llama3-Chinese-8B-28K", + "EleutherAI/pythia-6.9b", + "nnpy/Nape-0", + "jupyter-agent/jupyter-agent-qwen3-4b-thinking", + "Ba2han/TR_CPT1", + "lgaalves/gpt2_platypus-dolly-guanaco", + "prithivMLmods/Calcium-Opus-14B-Elite-Stock", + "Gille/StrangeMerges_13-7B-slerp", + "shubhamrgandhi/qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only", + "sergiopaniego/qwen3-0.6b-pimono-gkd-lr5e5", + "sstoica12/acquisition_student_llama-3_1-8b_bins_medmcqa_diversity", + "hibikigf88/SmolLM2-135M-sft-finetuned-smoltalk-everyday-conversations", + "Orion-zhen/Qwen2.5-7B-Gutenberg-KTO", + "parallel-reasoner/Qwen3-8B-131072-sft-tw8x", + "NgVietAnh41/Qwen3-4b-it-final-VietMedQA", + "prithivMLmods/Calcium-Opus-14B-Elite2-R1", + "ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16", + "DavidAU/Qwen3-Horror-Instruct-Uncensored-262K-ctx-4B", + "AI-ModelScope/ChatMusician", + "normster/RealGuardrails-Llama3.1-8B-Instruct-SFT", + "Shanghai_AI_Laboratory/internlm2-1_8b", + "Nabbers1999/Mini-Llama-14B-Chat-SFT-0129", + "PerHavard/tinyllama-base", + "sergiopaniego/qwen3-0.6b-pimono-gkd-lr1e5", + "Chaos1024/qwen25_plan_sft_10k", + "mlabonne/OrpoLlama-3-8B", + "fableforge-ai/NEXUS-Coder", + "wei123602/Llama-2-13b-FINETUNE4_compare8k2", + "SipsaLabs/qwen3-1.7b-uc-v3-bpw3", + "PKU-Wu-Lab/LTE-Qwen3-4B-Base", + "Luxenburger/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-prowling_stealthy_grouse", + "longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft-epoch3", + "dnotitia/Smoothie-Qwen3-4B", + "abdulloh19291/super-model-7b", + "bunnycore/Qwen-2.5-7b-S1k", + "ahmadfatikhulkhasan/qwen2.5-3b-legal-id-sft", + "viplav0009/sarcastic_llama_8B_merged_v2", + "Xorbits/CodeLlama-7B-fp16", + "Shaleen123/qwen-3-4B-Vedaz-FineTuned", + "NousResearch/CodeLlama-13b-hf-flash", + "inflatebot/thorn-0.45", + "bryordas/g-20-10-3-6e-4-sub", + "voidism/SelfCite-8B-CC-SFT", + "cs-552-2026-kth/math_model", + "DigitalPixie/qwen-sft-notification", + "prithivMLmods/Pegasus-Opus-14B-Exp", + "sstoica12/acquisition_student_llama-3_1-8b_bins_medmcqa_proximity", + "Baon2024/Qwen2.5-0.5B-Instruct-sft-77", + "botjimbo/llama-2-7b-sharded-amazon-sum-sent_token_duaribu_2giga", + "CoolSpring/Qwen2-0.5B-Abyme", + "A7med-Ame3/qwen3_merged_model", + "thisdood/transliteration-7b-32k", + "Korabbit/Llama-2-7b-chat-hf-afr-100step-flan", + "promotion/qwen3-8b-ipo-avg-beta0p01-s42", + "shisa-ai/ablation-84-bestofn.atlo.rp.tl-shisa-v2-llama-3.1-8b", + "TilQazyna/llama-kaz-instruct-8B-1", + "vineetsharma/databricks-dolly-15k-pythia-70m-deduped-v1", + "hpcai-tech/Colossal-LLaMA-2-13b-base", + "ChocoLlama/Llama-3-ChocoLlama-8B-instruct", + "huihui-ai/Hermes-3-Llama-3.2-3B-abliterated", + "LTC-AI-Labs/L2-7B-Guanaco-Vicuna", + "openaccess-ai-collective/tiny-mistral", + "nthngdy/matritest_van_300M", + "LLM-Research/tulu-v2.5-ppo-13b-stackexchange-60k", + "Ramikan-BR/Qwen2-0.5B-v1", + "andre-garcia/Qwen3-0.6B-Base-CPT-Math", + "Arushhh/alab-q3-8b_sft_tulu_0705", + "llm-agents/tora-7b-v1.0", + "yixuantt/Qwen2.5-3B-R1-Finance", + "BAAI/AquilaChat2-7B-16K", + "llm-agents/tora-code-7b-v1.0", + "promotion/qwen3-8b-ronpo-full-expect-s42", + "Hapissss/csnara-assistant-llama-3.2-1b", + "BAAI/Aquila2-7B", + "OdiaGenAI/odia_llama2_7B_base", + "satyam-79/Qwen2.5-1.5B-Instruct_dpo", + "sfutenma/dpo-qwen3_4b-cot-merged_v260301-220140", + "m-a-p/MuPT-v1-8192-190M", + "tzwilliam0/qwen-dapo-17k-vs-3", + "SumiYama/dpo-qwen-cot-merged", + "suayptalha/FastLlama-3.2-3B-Instruct", + "sampluralis/llama-sft-sgd", + "dinhxuanhuy/llama-3.2-1B-PhoMT-250k", + "excepto64/AISHED-em-Llama-3.2-1B-Instruct-misaligned", + "tokyotech-llm/Swallow-13b-instruct-v0.1", + "Hi-Satoh/adv_sft_dpo_final_11_merged", + "zenlm/zen-translate", + "luffycodes/vicuna-mmlu-val-only-correct-mcq-7b-ep2", + "PKU-Wu-Lab/LTE-Qwen3-8B-Base", + "BillyWang1/qwen2.5-7b-base-retool-slime-sft", + "sharonmina/Qwen3-mini-doubao-fast2", + "ChiKoi7/Llama3.1-SuperHawk-8B-Heretic-v2", + "moonlightfamily/mistral-humanizer-v1", + "gaodrew/gaodrew-gorgonzola-13b", + "DhruvalLabs/qwen3-8b-claude-agentic-fable5", + "nanbeige/Nanbeige4.1-3B", + "NeverSleep/Noromaid-13b-v0.2", + "EpistemeAI/Math-Code-Llama3.1-8B", + "ChiKoi7/GPT-5-Distill-Qwen3-4B-Instruct-Heretic", + "bryordas/d-40-60-5e-5", + "thkim0305/RepBend_Mistral_7B", + "CausalLM/EarlyFailures7B", + "normster/RealGuardrails-Qwen2.5-7B-SFT", + "Gueule-d-ange/aup-fullft-kto-nolam-seed5", + "ChuGyouk/F_R5", + "longtermrisk/Qwen3-4B-ftjob-eea23779b1a0", + "UnicomAI/Unichat-llama3.2-Chinese-1B", + "Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed5", + "micaebe/Qwen2.5-1.5B-Instruct-QwQ", + "AttentioResearch/tally-8b-flagship", + "Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed5", + "stefra/qwen_pe_joint_merged", + "koutch/qwen_2.json_train_dpo_v1_train_code", + "sparklabutah/Qwen3-4B-TimeWarp", + "invalid-coder/Starling-LM-7B-beta-laser-dpo", + "PORTULAN/gervasio-7b-portuguese-ptbr-decoder", + "suayptalha/Maestro-R1-Llama-8B", + "justinthelaw/SmolLM2-360M-Instruct-Resume-Cover-Letter-SFT", + "quantumaikr/quantum-v0.01", + "WebraftAI/synapsellm-7b-mistral-v0.4-preview2", + "hmdmahdavi/olympiad-curated-qwen3-4b-thinking-generator-critique-7-epoch", + "Weyaxi/Orca-Nova-13B", + "SicariusSicariiStuff/TinyLLama_0.6_Chat_BF16", + "AuricErgeson/shellwhiz-7b", + "amd/AMD-OLMo-1B-SFT-DPO", ] # 本次仅提交 ppu_zw_810e，其余 GPU 保持已提交状态不重复提交