3 Commits

Author SHA1 Message Date
4e603b9fb0 update 2026-07-14 19:06:47 +08:00
5fe8bf27e5 update main.py
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-14 18:41:06 +08:00
d6b0e416db update ppu 2026-07-13 19:43:35 +08:00
2 changed files with 226 additions and 318 deletions

Binary file not shown.

544
main.py
View File

@@ -22,7 +22,7 @@ BASE_URL = os.environ.get("BASE_URL", "https://modelhub.org.cn")
SUBMIT_ENDPOINT = "/adminApi/async/task/create-contest-task"
# 通过 curl -X POST https://modelhub.org.cn/adminApi/user/login 获取后填入
AUTH_TOKEN = "eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJ1c2VyQWNjb3VudCI6Inpob3VzaGFzaGEiLCJpZCI6MTQsInVzZXJSb2xlIjoibGVhZGVyYm9hcmQiLCJleHAiOjE3ODI3MzA4MTQsImlhdCI6MTc4MjEyNjAxNH0.ZBMLXxi9n_g4_drUUuciWFipViMZmJzMJLab5dL0WM4"
AUTH_TOKEN = "eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJ1c2VyQWNjb3VudCI6Inpob3VzaGFzaGEiLCJpZCI6MTQsInVzZXJSb2xlIjoibGVhZGVyYm9hcmQiLCJleHAiOjE3ODQ1NDc1NDYsImlhdCI6MTc4Mzk0Mjc0Nn0.ZcOqcrfI22LPi4mGMnt164nZGhi61ZxtJGYsoO7fZdM"
CONTEST_API_TOKEN = "ef1ef82f3c9efee413d602345fbe224d"
CONTRIBUTORS = "zhoushasha"
GPU_TYPE = "ppu_zw_810e"
@@ -36,323 +36,231 @@ HTTP_PORT = 8080
# 模型列表
# ══════════════════════════════════════════════════════════
ALL_MODEL_IDS = [
"mrsanskar19/my_first_model",
"cs-552-2026-vibe-trainers/math_model",
"jburnford/dyslexic-writer-qwen3-0.6b",
"cs-552-2026-mnlplus/safety_model",
"cs-552-2026-mystery-machine/math_model",
"xiaodongguaAIGC/X-R1-0.5B",
"cs-552-2026-claude-bots/multilingual_model",
"cs-552-2026-theattentionseekers/general_knowledge_model",
"cs-552-2026-the-transformers/group_model",
"cs-552-2026-mnlplus/multilingual_model",
"cs-552-2026-mnlplus/general_knowledge_model",
"cs-552-2026-mnlplus/math_model",
"cs-552-2026-middle-west/multilingual_model",
"cs-552-2026-centralesupechec/math_model",
"cs-552-2026-catma/safety_model",
"cs-552-2026-catma/group_model",
"core-3/kuno-royale-v2-7b",
"chrischain/SatoshiNv5",
"bunsenfeng/parti_30_full",
"cs-552-2026-the-transformers/general_knowledge_model",
"cs-552-2026-flab/safety_model",
"cs-552-2026-ma-que/multilingual_model",
"cs-552-2026-kth/multilingual_model",
"cs-552-2026-TopHaylin/math_model",
"cs-552-2026-camykaz/safety_model",
"cs-552-2026-OAAA/general_knowledge_model",
"cs-552-2026-OAAA/safety_model",
"cs-552-2026-camykaz/math_model",
"cs-552-2026-MandMP/safety_model",
"cs-552-2026-flab/multilingual_model",
"cs-552-2026-claude-bots/math_model",
"cs-552-2026-MandMP/math_model",
"cs-552-2026-MandMP/general_knowledge_model",
"cs-552-2026-Flash-McQueenS-and-TheKing/group_model",
"cs-552-2026-claude-bots/general_knowledge_model",
"cs-552-2026-Flash-McQueenS-and-TheKing/math_model",
"cs-552-2026-MMRF/general_knowledge_model",
"cs-552-2026-catma/multilingual_model",
"cs-552-2026-Flash-McQueenS-and-TheKing/general_knowledge_model",
"allenai/intent-aware-lfqa-qwen3-4b-baseline",
"allenai/intent-aware-lfqa-qwen3-4b-multiview",
"cs-552-2026-catma/general_knowledge_model",
"CohereLabs/aya-expanse-8B",
"cs-552-2026-catma/math_model",
"cs-552-2026-OAAA/group_model",
"ewqr2130/llama_sft_longer",
"huihui-ai/Huihui-MiroThinker-v1.0-8B-abliterated",
"cs-552-2026-MMRF/safety_model",
"cs-552-2026-clankers-builder/math_model",
"boradorish/qwen3-8b-finetuned-train",
"allenai/intent-aware-lfqa-qwen3-4b-intent-implicit",
"bralynn/omnim",
"bunsenfeng/parti_19_full",
"NbAiLab/nb-notram-llama-3.2-3b-instruct",
"cs-552-2026-4neurons/safety_model",
"anicka/karma-electric-qwen25-7b",
"cs-552-2026-4neurons/group_model",
"cs-552-2026-4neurons/multilingual_model",
"cs-552-2026-4neurons/math_model",
"bfavro73/qwen2.5-coder-1.5b-pandas-dpo-aligned",
"bfavro73/qwen2.5-coder-7b-pandas-dpo-aligned",
"beyoru/Luna-Ethos",
"adriangg04/TheLastOfUs-QA",
"mychen76/mistral-7b-merged-ties",
"lihaoxin2020/qwen3-4b-sft-gpt54-ep2-evolving-rubric-gpt41-step100",
"lihaoxin2020/qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt41-step100",
"anonymuspj7/model_sft_resta",
"anonymuspj7/model_sft_dare_resta",
"anonymuspj7/model_sft_dare",
"clglavan/magos-k8s-0.6b",
"continuum-ai/qwen2.5-1.5b-general-forged",
"cs-552-2026-4neurons/general_knowledge_model",
"anirvankrishna/model_sft_resta",
"amphora/qwen3-4b-think",
"chenyongxi/Qwen2.5-1.5B-DPO-1.5B",
"carnival13/model_sft_merged",
"berkerbatur/qwen-0.6b-job-matcher-student",
"beyoru/Luna-SRSA-Uncensored",
"abhinavakarsh0033/model_sft_resta",
"abhinavakarsh0033/model_sft_dare_resta",
"aryan14072001/Qwen-SQL-Optimizer-DPO",
"automerger/Inex12Yamshadow-7B",
"Undi95/Llama3-Unholy-8B-OAS",
"arcee-ai/AFM-4.5B",
"anujjamwal/OpenMath-Nemotron-1.5B-PruneAgnostic",
"anujjamwal/OpenMath-Nemotron-1.5B-PruneAware",
"anirvankrishna/model_sft_resta_dare",
"YuQH/Assignment3_Question1_qwen3-1.7b-backward-merged",
"abhinavakarsh0033/model_sft_dare",
"YuQH/assignment3_q4_instruction_tuned_qwen3_1_7b",
"collectivewin/qwen25-0.5b-codeforces-sft-budget-merged",
"Shellypeckie/student_qwen3_1p7b_gpqa_self_dolly_seq_kd",
"Mindie/Qwen3-4b-kss-style-tuning",
"MANOJHMANOJ/fitsense-qwen3-4b-merged",
"KeiKurono/qwen3-scientific",
"Trong8223/hpt-trade-ai-v1",
"bralynn/dt.think1.128.256.25",
"lihaoxin2020/qwen3-4b-sft-gpt54-ep2-evolving-rubric-gpt41-step200",
"lihaoxin2020/qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt41-step200",
"automerger/Experiment27Pastiche-7B",
"ZigZeug/Baatukaay-Qwen2.5-3B-Wolof",
"adsyamsafa/Nixia1.0-0.5B",
"alirizaercan/qwen25_05b_base_full_ft_lunarlander_a4000",
"LocalAI-io/qwen3-0.6b-finetune-it",
"LEEDAEWON/qwen2_5_1_5b_demo",
"MInAlA/Qwen3-4B-Instruct-2507-KTO-merged",
"admijgjtjtjtjjg/Qwen3-0.6B-Micro-5M",
"Kimyayd/Qwen-1.5B-Fongbe-Translator",
"Jason-hu/Qwen2.5-3B-GSM8K-SFT",
"Issactoto/qwen2.5-1.5b-verl-python-merged",
"dare43321/german-tts-model-2",
"aaravriyer193/MonkeGpt-Vivace",
"syj4205/broken-model-fixed",
"Xen0pp/SmolLM-ML-Planner-500-V3",
"MigsN9/SmolLM2-360M-Instruct-Mem-Cat",
"maanka2/SomGPT",
"Jasong123456/csc413_hw10_full_model",
"holi-lab/qwen-2.5-1.5b-multiwoz-finetuned",
"Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties_density0.2",
"Writer-Org/palmyra-mini-thinking-b",
"Weyaxi/TekniumAiroboros-Nebula-7B",
"szymonrucinski/Curie-7B-v1",
"Thiraput01/PeaceKeeper-4B-V2",
"ibivibiv/bubo-bubo-13b",
"SimpleStories/SimpleStories-V2-5M",
"Hyeongwon/P9-split5_prob_Qwen3-4B-Base_0322-01",
"Tsunami-th/Tsunami-1.0-14B-Instruct",
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_1",
"TeeZee/DarkForest-20B-v2.0",
"artificialguybr/QWEN-2.5-0.5B-Synthia-II",
"open-thoughts/OpenThinker-Agent-v1",
"laion/r2egym-nl2bash-stack-bugsseq-fixthink-again",
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_2",
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_3",
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_4",
"Trong8223/hpt-trade-ai-v2",
"PrimeIntellect/Qwen2.5-0.5B-Reverse-Text-SFT",
"mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini-qwen",
"mncai/Mistral-7B-guanaco-1k-orca_platy-1k",
"zypchn/BehChat-v3",
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_5",
"Lixing-Li/Llama-3.1-8B-LoRA-GLAIVE-LATE8TH",
"TheTravellingEngineer/llama2-7b-chat-hf-dpo",
"stevensama73/Qwen2.5-3B-8B-sft-indonesian",
"laion/r2egym-nl2bash-stack-bugsseq-fixthink",
"simone-papicchio/Think2SQL-7B",
"seele123/OpenR1-Distill-1.5B-ours",
"laion/openthoughts-4-code-qwen3-32b-annotated-32k_qwen2.5-1.5B_32k",
"laion/nl2bash-verified-GLM-4.6-traces-32ep-32k-mgn5e4_Qwen3-8B",
"laion/nemotron-100000-opt100k__Qwen3-8B",
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_6",
"AlfredPros/CodeLlama-7b-Instruct-Solidity",
"TitleOS/Phi-4-mini-reasoning-heretic",
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_8",
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_7",
"SanjiWatsuki/Kunoichi-7B",
"AliMaatouk/Llama-3.2-1B-Tele",
"prithivMLmods/Bellatrix-Tiny-3B-R1",
"m-a-p/Qwen2-Instruct-7B-COIG-P",
"zypchn/BehChat-llama-SFT-v2",
"TURKCELL/Turkcell-LLM-7b-v1",
"Alelcv27/Llama3.2-3B-base-Code",
"prithivMLmods/Sqweeks-7B-Instruct",
"maxidl/Llama-OpenReviewer-8B",
"yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_375-2",
"Thiraput01/PeaceKeeper-4B-V4",
"m-a-p/Qwen2.5-Instruct-7B-COIG-P",
"SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE",
"cycloneboy/CscSQL-Merge-Qwen2.5-Coder-3B-Instruct",
"prithivMLmods/Monoceros-QwenM-1.5B",
"Shanghai_AI_Laboratory/AlchemistCoder-L-7B",
"yujiepan/qwen3-tiny-random-tp",
"prithivMLmods/rStar-Coder-Qwen3-0.6B",
"Qwen/Qwen1.5-14B",
"yil384/Qwen3-0.6B-full",
"Thiraput01/PeaceKeeper-4B-V3",
"ystemsrx/Qwen2.5-Interpreter",
"yujiepan/baguettotron-tiny-random",
"prithivMLmods/Cerium-Qwen3-R1-Dev",
"QwenCollection/Nxcode-CQ-7B-orpo",
"prithivMLmods/Viper-OneCoder-UIGEN",
"yasserrmd/GLM4.7-Distill-LFM2.5-1.2B",
"kairawal/Llama-3.2-3B-Instruct-PT-SynthDolly-E1-S73",
"carsenk/llama3.2_3b_122824_uncensored",
"prithivMLmods/Telescopium-Acyclic-Qwen3-0.6B",
"prithivMLmods/Deneb-Qwen3-Radiation-0.6B",
"cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct",
"ziaulkarim245/Deepseek-R1-Phishing-Detector",
"rLLM/rLLM-FinQA-4B",
"aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT",
"yam-peleg/Experiment8-7B",
"prithivMLmods/Castula-U2-QwenRe-1.5B",
"yam-peleg/Experiment31-7B",
"yam-peleg/Experiment30-7B",
"PrimeIntellect/Qwen3-8B",
"Thiraput01/PeaceKeeper-4B",
"PistachioAlt/Noromaid-Bagel-7B-Slerp",
"PygmalionAI/pygmalion-2-7b",
"yam-peleg/Experiment28-7B",
"mlabonne/DatacampLlama-3.1-8B",
"prithivMLmods/Pictor-1338-QwenP-1.5B",
"prithivMLmods/Viper-Coder-v0.1",
"NousResearch/Yarn-Llama-2-13b-128k",
"TheDrummer/Llama-3SOME-8B-v2",
"OpenBuddy/openbuddy-llama2-13b-v11-bf16",
"yam-peleg/Experiment22-7B",
"OpenPipe/llama_3b_hn_story_classifier",
"yam-peleg/Experiment2-7B",
"ybelkada/Mistral-7B-v0.1-bf16-sharded",
"xw1234gan/Main_fixed_MATH_3B_step_1",
"Ihor/Text2Graph-R1-Qwen2.5-0.5b",
"unsloth/llama-2-7b",
"neuralmagic/SparseLlama-2-7b-cnn-daily-mail-pruned_50.2of4",
"ThaiLLM/ThaiLLM-8B",
"voidful/unit-desta-8b-base-llama3-8b-instruct",
"SouravCrypto/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-striped_tawny_dove",
"xw1234gan/Main_fixed02_MATH_3B_step_4",
"xw1234gan/Main_MATH_3B_step_9",
"m-a-p/Infinity-Instruct-3M-0625-Mistral-7B-COIG-P",
"adityakum667388/lumichats-v1.1",
"NEU-HAI/Llama-2-7b-alpaca-cleaned",
"NousResearch/CodeLlama-34b-hf",
"prithivMLmods/Tulu-MathLingo-8B",
"ibm-granite/granite-8b-code-instruct-4k",
"alexxbobr/ORPO8000Vikhr-Llama-3.2-1B-Instruct5000",
"m-a-p/TreePO-Qwen2.5-7B",
"fancyfeast/llama-bigasp-prompt-enhancer",
"line-corporation/japanese-large-lm-1.7b",
"wassname/qwen3-5lyr-tiny-random",
"TaimurShaikh/qwen1.5-1.8b-sft",
"l3utterfly/minima-3b-layla-v1",
"l3utterfly/mistral-7b-v0.1-layla-v2",
"Henrychur/MMed-Llama-3-8B",
"gradient-spaces/respace-sg-llm-1.5b",
"l3utterfly/minima-3b-layla-v2",
"allenai/truthfulqa-info-judge-llama2-7B",
"facebook/llm-compiler-7b",
"nothingiisreal/L3.1-8B-Celeste-V1.5",
"TaimurShaikh/qwen1.5-1.8b-dpo",
"l3utterfly/tinyllama-1.1b-layla-v4",
"prithivMLmods/Flerovium-Llama-3B",
"l3utterfly/mistral-7b-v0.1-layla-v1",
"OpenBuddy/openbuddy-mistral-7b-v13.1",
"iCIIT/redqueenprotocol-sin-llama3.2-3B-model",
"OpenAssistant/codellama-13b-oasst-sft-v10",
"Unitedp2p/New-Llama-3.1-8B-Lexi-Uncensored-V2",
"USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B",
"Salesforce/Llama-xLAM-2-8b-fc-r",
"uukuguy/speechless-orca-platypus-coig-lite-4k-0.6e-13b",
"krevas/SOLAR-10.7B",
"SykoSLM/SykoLLM-V6.0-Test",
"l3utterfly/mistral-7b-v0.1-layla-v4",
"argilla/distilabeled-Marcoro14-7B-slerp",
"uzlm/alloma-8B-Instruct",
"trillionlabs/Tri-7B",
"nlile/PE-7b-full",
"glaiveai/glaive-coder-7b",
"RamziRebai/llama-2-7b-therapist-v4",
"Lazycuber/L2-7b-Base-Guanaco-Vicuna",
"behnamsh/gpt2_camel_physics",
"jondurbin/spicyboros-7b-2.2",
"argilla/distilabeled-Marcoro14-7B-slerp-full",
"kairawal/Llama-3.2-3B-Instruct-ZH-SynthDolly-1A-E5",
"Surpem/Supertron1-8B",
"TIGER-Lab/Mantis-8B-siglip-llama3-pretraind",
"Leopo1d/OpenVul-Qwen3-4B-GRPO",
"totally-not-an-llm/PuddleJumper-13b-V2",
"ajibawa-2023/Code-Mistral-7B",
"unsloth/Qwen2.5-3B",
"Jiqing/tiny-random-qwen2",
"L33tcode/llama-3-8b-CEH-hf",
"FlyPig23/Qwen3-4B_Paper_Impact_patent_SFT_1ep",
"totally-not-an-llm/EverythingLM-13b-V3-16k",
"totally-not-an-llm/EverythingLM-13b-16k",
"ajibawa-2023/Code-290k-6.7B-Instruct",
"mrcuddle/Lumimaid-Muse-12B",
"how3751/coder_7B",
"m-a-p/CT-LLM-SFT",
"Marintosti/chsa-triage-merged",
"m-a-p/CT-LLM-SFT-DPO",
"inclusionAI/AReaL-boba-2-8B",
"FreedomIntelligence/Apollo-6B",
"mrthor102/evolai-tfm-super-004",
"staeiou/bartleby-qwen3-1.7b_v4",
"golgat/toolcalling-merged-demo",
"allenai/Llama-3.1-Tulu-3-8B-SFT",
"Kazuki1450/Olmo-3-1025-7B_dsum_3_6_tok_Certainly_1p0_0p0_1p0_grpo_dr_grpo_42_rule",
"driaforall/Dria-Agent-a-7B",
"ChaoticNeutrals/Eris_Remix_7B",
"thrishala/mental_health_chatbot",
"mlfoundations-dev/oh-dcft-v3.1-gemini-1.5-flash",
"CompassioninMachineLearning/pretrainingBasellama3kv3",
"venkycs/Zyte-1B",
"mnoukhov/pythia410m-sft-tldr",
"ali-elganzory/Baguettotron-DPO-Tulu3-decontaminated",
"Alienpenguin10/M3PO-kl_divergence-trial1-seed123",
"tanhao2015/MDtranslator",
"aloobun/Reyna-CoT-4B-v0.1",
"sstoica12/influence_metamath_qwen2.5_3b_new_detailed",
"argilla/zephyr-7b-spin-iter1-v0",
"Kazuki1450/Olmo-3-1025-7B_dsum_3_6_rel_1e0_1p0_0p0_1p0_grpo_sapo_42_rule",
"FelixChao/Voldemort-10B",
"yam-peleg/Experiment1-7B",
"Eric111/Mistral-7B-Instruct_v0.2_UNA-TheBeagle-7b-v1",
"ewqr2130/llama_ppo_1e6_new_tokenizerstep_8000",
"DanielClough/Candle_TinyLlama-1.1B-Chat-v1.0",
"rbelanec/train_qnli_42_1779286680",
"tech27/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-amphibious_spotted_kingfisher",
"syvai/emotion-reasoning-1b",
"argilla/notus-7b-v1",
"burtenshaw/SmolLM3-3B-GRPO-think",
"ViratChauhan/Qwen3-4B-GRPO-v2",
"zarakiquemparte/zaraxls-l2-7b",
"AlexeySorokin/GEC-from-explanations-4BInstr-distilled-v2303",
"Alelcv27/Qwen2.5-3B-INST-Code",
"tiny-random/llama-3.3-dim64",
"prithivMLmods/Triangulum-1B",
"Alienpenguin10/M3PO-bahdanau-trial1-seed123",
"sujalrajpoot/TrueSyncAI-Aurion",
"prithivMLmods/Tureis-Qwen3_QWQ-4B-Exp",
"standrey/listing-parser-llama31-8b-ft-v1-full",
"zarakiquemparte/zarablend-l2-7b",
"linzju/Bio-Medical-Llama-3-8B_EnchTable_FFN",
"leonMW/Qwen3-4B-Thinking-2507-GSPO-Easy",
"longvideoagent/longvideoagent-qwen3-4b",
"ishikaa/acquisition_qwen3b_alpaca_proximity",
"01ai/Yi-9B-200K",
"Gille/StrangeMerges_33-7B-slerp",
"sstoica12/acquisition_llama-3_2-3b_bins_medmcqa_gradient",
"speechlessai/speechless-coding-7b-16k-tora",
"unsloth/Qwen2.5-Math-1.5B-Instruct",
"Yuma42/KangalKhan-Sapphire-7B",
"shadowml/BeagleSempra-7B",
"bralynn/test18",
"m-a-p/OProver-8B-Round1",
"yeen214/test_llama2_7b",
"Xwin-LM/Xwin-LM-7B-V0.2",
"FreedomIntelligence/AceGPT-13B",
"Edcastro/tinyllama-edcastr_JavaScript-v2",
"zarakiquemparte/zaraxe-l2-7b",
"MaziyarPanahi/Llama-3-8B-Instruct-v0.8",
"defog/sqlcoder2",
"SawinuCP/bus_booking_voice_agent_merged",
"j05hr3d/Llama-3.2-3B-Instruct-C_M_T-DOLLY-SEED999",
"Changgil/K2S3-SOLAR-11b-v1.0",
"agentica-org/DeepCoder-1.5B-Preview",
"prithivMLmods/Omni-Reasoner3-Merged",
"ibm-granite/granite-7b-instruct",
"zarakiquemparte/kuchiki-1.1-l2-7b",
"MaziyarPanahi/Llama-3-8B-Instruct-v0.1",
"Magpie-Align/Llama-3.1-8B-Magpie-Align-v0.1",
"prithivMLmods/Neumind-Math-7B-Instruct",
"dphn/dolphin-2.9.3-qwen2-1.5b",
"OpenBuddy/openbuddy-mistral-7b-v13",
"kairawal/Qwen3-4B-TL-SynthDolly-1A-E3",
"sahilnagaralu/movie-script",
"xw1234gan/SFT_Qwen2.5-1.5B-Instruct_cnk12",
"yunjae-won/ubq30i_qwen4b_sft_yl",
"1010happy/qwen3BInstruct_ClaudeDefault",
"yunjae-won/ubq30i_qwen4b_sft_both",
"willieseun/AIMO-Qwen2.5-Math-1.5B-Instruct-Finetuned",
"NousResearch/Yarn-Mistral-7b-64k",
"xiaolesu/OsmosisProofling-GRPO-NT",
"health360/Healix-410M",
"RUC-AIBOX/STILL-3-1.5B-preview",
"cjvt/GaMS-1B",
"Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-1epochstop-withformat",
"Charlie911/vicuna-7b-v1.5-general-temporal-merged",
"Kyleyee/cDPO_hh-seed5",
"prithivMLmods/Llama-3.2-3B-Math-Oct",
"Kyleyee/HINGE_hh-seed5",
"arcee-ai/Patent-Instruct-7b",
"jb723/cross_lingual_epoch2",
"davidkim205/komt-mistral-7b-v1",
"kalisai/Nusantara-1.8b-Indo-Chat",
"prithivMLmods/Llama-8B-Distill-CoT",
"Kyleyee/HINGE_hh-seed3",
"simplescaling/s1.1-1.5B",
"sail/Sailor2-3B-SFT",
"allenai/OLMoE-1B-7B-0924-Instruct",
"prithivMLmods/Llama-3.2-6B-AlgoCode",
"CloneBO/OracleLM",
"NousResearch/Yarn-Solar-10b-32k",
"m-a-p/OProver-8B-Base",
"HuggingFaceH4/mistral-7b-sft-alpha",
"Hyeongwon/P2-split2_prob_Qwen3-4B-Base_0312-01",
"martyn/mixtral-megamerge-dare-8x7b-v1",
"Kyleyee/rDPO_hh-seed4",
"jingyeom/seal3.1.6n_7b",
"sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-reversed_corrupted",
"shibing624/ziya-llama-13b-medical-merged",
"datajuicer/LLaMA-1B-dj-refine-150B",
"ajibawa-2023/Uncensored-Jordan-7B",
"nlpguy/AlloyIngot",
"HuggingFaceTB/SmolLM3-3B",
"allenai/codetulu-2-7b",
"vihangd/dopeyshearedplats-2.7b-v1",
"uukuguy/speechless-code-mistral-7b-v2.0",
"j05hr3d/Llama-3.2-3B-Instruct-C_M_T-ALPACA",
"cognitivetech/Mistral-7B-Inst-0.2-Bulleted-Notes",
"sail/Qwen2.5-Math-1.5B-Oat-Zero",
"reaperdoesntknow/SMOLM2Prover",
"Kyleyee/ORPO_hh-seed5",
"CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct",
"NousResearch/Nous-Capybara-7B-V1",
"Vijay3548/InterviewMaster-Llama3.1",
"ReviewHub/qwen3-4b-it-2507-sft-2018-2022-rl-step-20",
"Nos-PT/Llama-Carvalho-PT",
"Gille/StrangeMerges_49-7B-dare_ties",
"Kyleyee/CPO_hh-seed2",
"Kyleyee/cDPO_hh-seed3",
"Kyleyee/DrDPO_hh-seed2",
"sthenno-com/miscii-14b-0218",
"mtgv/MobileLLaMA-2.7B-Chat",
"Novaciano/Alice_In_The_Dark_2-Slerp-RP-3.2-1B",
"Himitsui/KuroMitsu-11B",
"owlninjam/nytheria-3b",
"Kyleyee/DrDPO_hh-seed4",
"Kyleyee/DrDPO_hh-seed5",
"shahzebnaveed/NeuralHermes-2.5-Mistral-7B",
"plaguss/mistal-7b-prm-openrlhf",
"viethq188/Rabbit-7B-v2-DPO-Chat",
"EmbeddedLLM/Mistral-7B-Merge-14-v0.3-ft-step-9984",
"dbpedia/nspm-starcoder-1b",
"psh3333/llama-3.2-3b-grpo-merged",
"saarvajanik/facebook-opt-6.7b-qcqa-ub-16-best-for-KV-cache",
"EmbeddedLLM/Mistral-7B-Merge-14-v0.3",
"xformAI/facebook-opt-125m-qcqa-ub-6-best-for-KV-cache",
"Rev124/llama-3-pruned",
"RatanRohith/NeuralPizza-7B-V0.3",
"mncai/DPO_BC_partial_epoch6",
"zeemen2723/museai-lyrics-gen",
"automerger/OgnoExperiment27-7B",
"sohamb37lexsi/qwen25-3b-legal-correction",
"swift/Meta-Llama-3-8B",
"m-a-p/MuPT-v0-8192-190M",
"Kquant03/Samlagast-7B-laser-bf16",
"VTSNLP/Llama3-ViettelSolutions-8B",
"vihangd/dopeyshearedplats-1.3b-v1",
"HCY123902/qwen25_7b_base_hc_tsss_n32_r1_dpo",
"coder3101/gemma-3-1b-it-heretic",
"Hemkant04/qwen05-resume-job-match-evaluator",
"yekon9/Qwen3-4B-Instruct-2507-heretic",
"uukuguy/Orca-2-13b-f16",
"Kquant03/NeuralTrix-7B-dpo-relaser",
"sambanovasystems/SambaLingo-Russian-Base",
"bineric/NorskGPT-Mistral-7b",
"ReviewHub/qwen3-4b-it-2507-sft-2018-2022-rl-step-10",
"beyoru/EvolLLM",
"driaforall/Dria-Agent-a-3B",
"tlphams/zoyllm-7b-slimorca",
"QuixiAI/WizardLM-33B-V1.0-Uncensored",
"bilalRahib/TinyLLama-NSFW-Chatbot",
"Ahatsham/Llama-3-8B-Instruct_Planning_Feedback_oldaug_v2",
"unsloth/Qwen2.5-Math-1.5B",
"wang7776/Llama-2-7b-chat-hf-30-sparsity",
"hector-gr/RLCR-v4-ks-uniqueness-buf5k-hotpot",
"m-a-p/neo_7b_instruct_v0.1",
"p208p2002/llama-traditional-chinese-120M",
"tartuNLP/Llammas-base",
"riotu-lab/ArabianGPT-01B",
"openaccess-ai-collective/DPOpenHermes-7B",
"Enxin/MovieChat-vicuna",
"Skywork/Skywork-OR1-Math-7B",
"Lugha-Llama/Lugha-Llama-8B-wura_edu",
"laion/allenai-sera-unified-316__Qwen3-8B",
"T1anyu/DeepInnovator",
"mideind/icelandic-gpt-sw3-6.7b-gec",
"Rayeeennnnnnnn/legalmind-chatbot",
"Wanfq/FuseLLM-7B",
"mrvinph/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-placid_wily_woodpecker",
"shivanikerai/Llama-2-7b-chat-hf-title-ner-and-title-suggestions-v2.0",
"Invalid-Null/PeiYangMe-0.7",
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha5_epoch5",
"Tesslate/Tessa-T1-3B",
"LorenaYannnnn/unsafe_compliance-Qwen3-0.6B-OURS_self-seed_1",
"HiTZ/latxa-7b-v1",
"huggyllama/llama-7b",
"FlyPig23/Llama3.2-3B_Paper_Impact_media_SFT_1ep",
"hongzhouyu/FineMedLM-o1",
"shisa-ai/shisa-v1-llama3-8b.lr-5e6",
"senseable/Westlake-7B",
"simplescaling/s1.1-3B",
"Borjan/finki-gpt-140M",
"TinyLlama/TinyLlama_v1.1_chinese",
"Manirajan/interview_tiny",
"ajibawa-2023/Young-Children-Storyteller-Mistral-7B",
"TinyLlama/TinyLlama_v1.1_math_code",
"manotham/Thai-dialogue-transalate_sft_80K",
"nassimjp/Maral-7B-alpha-1",
"MSL7/INEX16-7b",
"Rayeeennnnnnnn/mizan-legal-tunisian",
"maheshrawat18/Qwen3-4B-2507-sft1",
"prithivMLmods/Theta-Crucis-0.6B-Turbo1",
"mlabonne/llama-2-7b-miniguanaco",
"FreekCoolAI/privacy-gemma-qlora",
"lex-hue/Delexa-V0.1-7b",
"goldfish-models/tur_latn_100mb",
"shisa-ai/ablation-18-rafbestseq-shisa-v2-llama-3.1-8b-lr8e6",
"yash-lulla/Legal_AI_Assistant",
"prithivMLmods/Deepthink-Llama-3-8B-Preview",
"prithivMLmods/QwQ-R1-Distill-7B-CoT",
"sstoica12/acquisition_metamath_llama_instruct-3_1-8b-math_format_500_combined_openr1math",
"goldfish-models/rus_cyrl_1000mb",
"goldfish-models/ukr_cyrl_1000mb",
"eren23/dpo-binarized-NeutrixOmnibe-7B",
"RAANA-IA/Gheya-med",
"mesolitica/malaysian-tinyllama-1.1b-16k-instructions-v2",
"bue0912/ToolOmni-Qwen3-4B",
"BRlkl/distill-sft-qwen3-4b-full",
"prithivMLmods/PocketThinker-QwQ-3B-Instruct",
"prithivMLmods/Megatron-Bots-1.7B-Reasoning",
"kumarprince070107/geobot",
"ClaudioSavelli/FAME_GA_llama32-1b-instruct-qa",
"kairawal/Qwen3-0.6B-EL-SynthDolly-1A-E8",
"prithivMLmods/Poseidon-Reasoning-1.7B",
"PKU-Alignment/ProgressGym-HistLlama3-8B-C014-instruct-v0.2",
"unsloth/Qwen2-7B",
"prithivMLmods/Open-Xi-Math-Preview",
"MiniLLM/teacher-gpt2-1.5B",
"Rakancorle1/qwen2.5-7b_Instruct_policy_traj_30k_full",
"prithivMLmods/Lang-Exster-0.5B-Instruct",
"prithivMLmods/Nenque-MoT-0.6B-Elite14",
"posicube/Llama2-chat-AYT-13B",
"lomahony/pythia-70m-helpful-sft",
"kyubeen/code-grpo-checkpoint-950",
"nicholasKluge/TeenyTinyLlama-160m",
"allenai/Llama-3.1-Tulu-3-8B",
"BarraHome/Mistroll-7B-v2.2",
"posicube/Llama-chat-AY-13B",
"hongli-zhan/MINT-empathy-Qwen3-4B",
"jhhj25/qwen3-moe-neuron_structure_drop-p50-s1k-128samples-sft",
"Ikonz-Studios/seva-sarathi-intent-qwen3-1.7b",
"NECOUDBFM/Jellyfish-8B",
"gradients-io-tournaments/augmented-1db17e1d682d23fd",
"Locutusque/LocutusqueXFelladrin-TinyMistral248M-Instruct",
"ChuGyouk/R16",
"oveja1122/toolcalling-merged-demo",
"kmseong/llama3_2_3b-instruct-math-safedelta-scale0.8",
"EleutherAI/SmolLM2-1.7B-magpie-ultra-v1.0-math-431k-s",
"paulml/NeuralOmniBeagleMBX-v3-7B",
"skemessage/Qwen2.5-7B-Instruct-neuron",
]
# ══════════════════════════════════════════════════════════