zhoushasha/xc_validation_strategy
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

switch to Cambricon_mlu-370-x8 with new model list, refresh AUTH_TOKEN

Browse Source
This commit is contained in:
zhousha
2026-07-27 16:46:41 +08:00
parent a73274e6a4
commit 5958df93b0
1 changed files with 542 additions and 376 deletions
Download Patch File Download Diff File Expand all files Collapse all files

918
main.py
View File

@@ -22,11 +22,12 @@ BASE_URL = os.environ.get("BASE_URL", "https://modelhub.org.cn")
SUBMIT_ENDPOINT = "/adminApi/async/task/create-contest-task" 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 # 通过 curl -X POST https://modelhub.org.cn/adminApi/user/login 获取后填入
AUTH_TOKEN = "eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJ1c2VyQWNjb3VudCI6Inpob3VzaGFzaGEiLCJpZCI6MTQsInVzZXJSb2xlIjoibGVhZGVyYm9hcmQiLCJleHAiOjE3ODUyMzUzODMsImlhdCI6MTc4NDYzMDU4M30.-FCJENRVkD5Z09HPZ5ezUdoARTAIryuiAvEA4APf6-0" AUTH_TOKEN = "eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJ1c2VyQWNjb3VudCI6Inpob3VzaGFzaGEiLCJpZCI6MTQsInVzZXJSb2xlIjoibGVhZGVyYm9hcmQiLCJleHAiOjE3ODU3NDY3NTMsImlhdCI6MTc4NTE0MTk1M30.KwUuefNAFSNwq3_Pnaw2nef8ZC6WgsECQ_LMeQnKk2c"
CONTEST_API_TOKEN = "ef1ef82f3c9efee413d602345fbe224d" CONTEST_API_TOKEN = "ef1ef82f3c9efee413d602345fbe224d"
CONTRIBUTORS = "zhoushasha" CONTRIBUTORS = "zhoushasha"
GPU_TYPE = "ppu_zw_810e" # GPU_TYPE = "ppu_zw_810e"
# GPU_TYPE = "Biren_166m" # GPU_TYPE = "Biren_166m"
GPU_TYPE = "Cambricon_mlu-370-x8"
TASK_TYPE = "text-generation" TASK_TYPE = "text-generation"
STRATEGY_ID = os.environ.get("STRATEGY_ID", "") # 平台自动注入，无需修改 STRATEGY_ID = os.environ.get("STRATEGY_ID", "") # 平台自动注入，无需修改
@@ -1061,330 +1062,468 @@ ALL_MODEL_IDS = [
#### ppu ################################################################################################### #### ppu ###################################################################################################
"katalien/QWEN-abliterated_2", # "katalien/QWEN-abliterated_2",
"ReDiX/Qwen2.5-0.5B-Instruct-ITA", # "ReDiX/Qwen2.5-0.5B-Instruct-ITA",
"YOYO-AI/Qwen3-8B-YOYO", # "YOYO-AI/Qwen3-8B-YOYO",
"rghosh8/gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4_merged", # "rghosh8/gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4_merged",
"FlagRelease/phi-4-hygon-FlagOS", # "FlagRelease/phi-4-hygon-FlagOS",
"rghosh8/gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-16_merged", # "rghosh8/gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-16_merged",
"kmseong/llama3_2_3b-instruct-WaRP_lr5e-5", # "kmseong/llama3_2_3b-instruct-WaRP_lr5e-5",
"TrialPanorama/LLaMA-3-8B-TP", # "TrialPanorama/LLaMA-3-8B-TP",
"PhantHive/zilya-v1", # "PhantHive/zilya-v1",
"Pranavz/granite-4.1-3b-abilerated-unc", # "Pranavz/granite-4.1-3b-abilerated-unc",
"YOYO-AI/Qwen3-EZO-8B-YOYO-karcher-128K", # "YOYO-AI/Qwen3-EZO-8B-YOYO-karcher-128K",
"YOYO-AI/Qwen3-8B-YOYO-slerp-128K", # "YOYO-AI/Qwen3-8B-YOYO-slerp-128K",
"flwrlabs/Lizzy-7B", # "flwrlabs/Lizzy-7B",
"YOYO-AI/Qwen3-8B-YOYO-nuslerp-128K", # "YOYO-AI/Qwen3-8B-YOYO-nuslerp-128K",
"tyson0420/stack_llama-clang", # "tyson0420/stack_llama-clang",
"thanhdath/FINER-SQL-0.5B-BIRD", # "thanhdath/FINER-SQL-0.5B-BIRD",
"alazc/cs224r-sft-full-v1", # "alazc/cs224r-sft-full-v1",
"pkupie/Qwen2.5-1.5B-mn-cpt", # "pkupie/Qwen2.5-1.5B-mn-cpt",
"FinaPolat/RAISED_QWEN_8B_SFT", # "FinaPolat/RAISED_QWEN_8B_SFT",
"ajibawa-2023/WikiHow-Mistral-Instruct-7B", # "ajibawa-2023/WikiHow-Mistral-Instruct-7B",
"rghosh8/gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-3407-G-4_merged", # "rghosh8/gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-3407-G-4_merged",
"rghosh8/gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-3407-G-16_merged", # "rghosh8/gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-3407-G-16_merged",
"xinyifang/ProductsLlama", # "xinyifang/ProductsLlama",
"Manan17/hihihihi-my-model", # "Manan17/hihihihi-my-model",
"theprint/Llama3.2-1B-FantasySciFi", # "theprint/Llama3.2-1B-FantasySciFi",
"xinyifang/ArxivLlama", # "xinyifang/ArxivLlama",
"omrisap/LMMS_RSFT", # "omrisap/LMMS_RSFT",
"AshtonIsNotHere/CodeLlama_7B_nlp_pp", # "AshtonIsNotHere/CodeLlama_7B_nlp_pp",
"MergeBench/Llama-3.1-8B_multilingual", # "MergeBench/Llama-3.1-8B_multilingual",
"meta-math/MetaMath-7B-V1.0", # "meta-math/MetaMath-7B-V1.0",
"Apaokagi/skyline-mini-v10", # "Apaokagi/skyline-mini-v10",
"Magpie-Align/Llama-3-8B-Magpie-Air-MT-SFT-v0.1", # "Magpie-Align/Llama-3-8B-Magpie-Air-MT-SFT-v0.1",
"MediaTek-Research/Breeze-7B-Instruct-v0_1", # "MediaTek-Research/Breeze-7B-Instruct-v0_1",
"OpenBuddy/openbuddy-zen-3b-v21.1-32k", # "OpenBuddy/openbuddy-zen-3b-v21.1-32k",
"OpenBuddy/openbuddy-qwen2.5llamaify-7b-v23.1-200k", # "OpenBuddy/openbuddy-qwen2.5llamaify-7b-v23.1-200k",
"YOYO-AI/Qwen2.5-Coder-7B-YOYO", # "YOYO-AI/Qwen2.5-Coder-7B-YOYO",
"unixdevil/social-media", # "unixdevil/social-media",
"OpenBuddy/openbuddy-llama2-13b64k-v15", # "OpenBuddy/openbuddy-llama2-13b64k-v15",
"MrLvTian/Qwen3-8B-shortgpt-prune-3-layer", # "MrLvTian/Qwen3-8B-shortgpt-prune-3-layer",
"xw1234gan/cnk12_Main_fixed_BaseAnchor_1_5B_step_1", # "xw1234gan/cnk12_Main_fixed_BaseAnchor_1_5B_step_1",
"theprint/Llama3.2-1B-FantasySciFi-Full", # "theprint/Llama3.2-1B-FantasySciFi-Full",
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.13", # "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.13",
"LLM-Research/llama-2-7b-chat", # "LLM-Research/llama-2-7b-chat",
"OpenBuddy/openbuddy-llama3.2-3b-v23.2-131k", # "OpenBuddy/openbuddy-llama3.2-3b-v23.2-131k",
"YOYO-AI/Qwen2.5-Coder-3B-YOYO", # "YOYO-AI/Qwen2.5-Coder-3B-YOYO",
"YOYO-AI/Qwen3-8B-YOYO-karcher-128K", # "YOYO-AI/Qwen3-8B-YOYO-karcher-128K",
"NovaCorp/Pervert-Maid-RP3-3.2-1B", # "NovaCorp/Pervert-Maid-RP3-3.2-1B",
"ScottzillaSystems/ChatGPT-5", # "ScottzillaSystems/ChatGPT-5",
"ukRani03/Llama-2-7b-chat-finetune", # "ukRani03/Llama-2-7b-chat-finetune",
"AllyArc/llama_allyarc", # "AllyArc/llama_allyarc",
"LLM-Research/Qwen2-Math-7B-Instruct", # "LLM-Research/Qwen2-Math-7B-Instruct",
"Dario213/Qwen3-4B-medical-reasoning", # "Dario213/Qwen3-4B-medical-reasoning",
"YOYO-AI/Qwen2.5-3B-YOYO", # "YOYO-AI/Qwen2.5-3B-YOYO",
"NousResearch/DeepHermes-3-Llama-3-8B-Preview", # "NousResearch/DeepHermes-3-Llama-3-8B-Preview",
"YOYO-AI/Qwen2.5-7B-YOYO", # "YOYO-AI/Qwen2.5-7B-YOYO",
"YOYO-AI/Qwen2.5-1.5B-YOYO", # "YOYO-AI/Qwen2.5-1.5B-YOYO",
"YOYO-AI/Qwen2.5-7B-YOYO-super", # "YOYO-AI/Qwen2.5-7B-YOYO-super",
"touqir/Cyrax-7B", # "touqir/Cyrax-7B",
"open-machine/Llama-3.2-1B-FlashNorm", # "open-machine/Llama-3.2-1B-FlashNorm",
"GitBag/Reviewer2_Mp", # "GitBag/Reviewer2_Mp",
"Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct", # "Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct",
"tvaldez/Assignment4_bussiness_model", # "tvaldez/Assignment4_bussiness_model",
"tvaldez/business-news-generator", # "tvaldez/business-news-generator",
"Magpie-Align/MagpieLM-4B-SFT-v0.1", # "Magpie-Align/MagpieLM-4B-SFT-v0.1",
"sfutenma/dpo-qwen3_4b-cot-merged_v260302-112329", # "sfutenma/dpo-qwen3_4b-cot-merged_v260302-112329",
"Magpie-Align/MagpieLM-4B-Chat-v0.1", # "Magpie-Align/MagpieLM-4B-Chat-v0.1",
"Korabbit/Llama-2-7b-chat-hf-afr-100step-v2", # "Korabbit/Llama-2-7b-chat-hf-afr-100step-v2",
"grisun0/Qwen2.5-0.5B-Instruct-heretic", # "grisun0/Qwen2.5-0.5B-Instruct-heretic",
"tripplet-research/synthara-legacy", # "tripplet-research/synthara-legacy",
"YOYO-AI/Qwen2.5-0.5B-YOYO", # "YOYO-AI/Qwen2.5-0.5B-YOYO",
"X-D-Lab/MindChat-Qwen-1_8B", # "X-D-Lab/MindChat-Qwen-1_8B",
"tokinasin/llm-jp-4-8b-instruct-uncensored-ara", # "tokinasin/llm-jp-4-8b-instruct-uncensored-ara",
"Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.2", # "Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.2",
"Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1", # "Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1",
"Magpie-Align/Llama-3-8B-WildChat", # "Magpie-Align/Llama-3-8B-WildChat",
"Undi95/Llama-3-LewdPlay-8B-evo", # "Undi95/Llama-3-LewdPlay-8B-evo",
"EleutherAI/pythia-1.4b-authors-first-ft", # "EleutherAI/pythia-1.4b-authors-first-ft",
"EleutherAI/SmolLM2-1.7B-magpie-ultra-v0.1-train-query-sample", # "EleutherAI/SmolLM2-1.7B-magpie-ultra-v0.1-train-query-sample",
"North-ML1/willow-alpha-base", # "North-ML1/willow-alpha-base",
"AI-ModelScope/qwen2.5-7b-ins-v3", # "AI-ModelScope/qwen2.5-7b-ins-v3",
"Thrillcrazyer/Qwen-2.5-1.5B_TAC_Teacher_LLAMA70", # "Thrillcrazyer/Qwen-2.5-1.5B_TAC_Teacher_LLAMA70",
"thu-ml/STAIR-Qwen2-7B-DPO-3", # "thu-ml/STAIR-Qwen2-7B-DPO-3",
"ValiantLabs/Qwen3-4B-Esper3", # "ValiantLabs/Qwen3-4B-Esper3",
"thirdeyeai/SmolLM2-1.7B-Instruct-Uncensored", # "thirdeyeai/SmolLM2-1.7B-Instruct-Uncensored",
"Trendyol/Trendyol-LLM-7b-chat-v1.8", # "Trendyol/Trendyol-LLM-7b-chat-v1.8",
"tiny-random/llama-3", # "tiny-random/llama-3",
"xw1234gan/Extended_Merging_Prob_Qwen2.5-3B-Instruct_MATH_lr1e-05_mb2_ga128_n2048_seed42", # "xw1234gan/Extended_Merging_Prob_Qwen2.5-3B-Instruct_MATH_lr1e-05_mb2_ga128_n2048_seed42",
"UKPLab/Llama3-G2C", # "UKPLab/Llama3-G2C",
"prithivMLmods/Canum-Qwen3_R1-4B-iCoT", # "prithivMLmods/Canum-Qwen3_R1-4B-iCoT",
"Kartik12/Law-fine-tune-Meta-Llama-3.1-8B", # "Kartik12/Law-fine-tune-Meta-Llama-3.1-8B",
"Dipto084/Llama-3.1-8B-XGuard-merged", # "Dipto084/Llama-3.1-8B-XGuard-merged",
"syaeve/kanana-1.5-8b-instruct-2505_Merged_LoRA", # "syaeve/kanana-1.5-8b-instruct-2505_Merged_LoRA",
"sanaeai/Qwen2.5-14B-Instruct-rep-ce", # "sanaeai/Qwen2.5-14B-Instruct-rep-ce",
"sstoica12/acquisition_llama-3_2-3b_bins_numina_confidence", # "sstoica12/acquisition_llama-3_2-3b_bins_numina_confidence",
"sci4ai/Qwen2.5-14B-Instruct-Abliterated", # "sci4ai/Qwen2.5-14B-Instruct-Abliterated",
"Undi95/Meta-Llama-3.1-8B-Claude-bf16", # "Undi95/Meta-Llama-3.1-8B-Claude-bf16",
"thangvip/vwen-0.5", # "thangvip/vwen-0.5",
"taki555/Qwen3-4B-Thinking-2507-Art", # "taki555/Qwen3-4B-Thinking-2507-Art",
"GemMaroc/Qwen2.5-7B-Instruct-darija", # "GemMaroc/Qwen2.5-7B-Instruct-darija",
"DavidAU/Qwen3-4B-Fiction-On-Fire-Series-7-Model-X", # "DavidAU/Qwen3-4B-Fiction-On-Fire-Series-7-Model-X",
"CUAIStudents/Qwen-Ar-GEC", # "CUAIStudents/Qwen-Ar-GEC",
"sstoica12/acquisition_llama-3_2-3b_bins_numina_format", # "sstoica12/acquisition_llama-3_2-3b_bins_numina_format",
"spxiong/Llama-3.2-3B-Chinese-Instruct", # "spxiong/Llama-3.2-3B-Chinese-Instruct",
"taki555/Qwen3-4B-Instruct-2507-Art", # "taki555/Qwen3-4B-Instruct-2507-Art",
"taki555/Qwen3-0.6B-Art", # "taki555/Qwen3-0.6B-Art",
"TencentARC/MetaMath-Mistral-Pro", # "TencentARC/MetaMath-Mistral-Pro",
"unsloth/Qwen2.5-Coder-7B-Instruct", # "unsloth/Qwen2.5-Coder-7B-Instruct",
"prithivMLmods/Pisces-QwenR1-1.5B", # "prithivMLmods/Pisces-QwenR1-1.5B",
"sail/Sailor2-8B-Chat", # "sail/Sailor2-8B-Chat",
"FreedomIntelligence/HuatuoGPT-3-8B", # "FreedomIntelligence/HuatuoGPT-3-8B",
"TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill", # "TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill",
"sstoica12/acquisition_metamath_llama_instruct-3_1-8b-math_gradient_500_combined_openr1math", # "sstoica12/acquisition_metamath_llama_instruct-3_1-8b-math_gradient_500_combined_openr1math",
"sbordt/OLMo-2-1B-1x-WD01-LR16", # "sbordt/OLMo-2-1B-1x-WD01-LR16",
"sbordt/OLMo-2-1B-1x-WD1-LR16", # "sbordt/OLMo-2-1B-1x-WD1-LR16",
"sbordt/OLMo-2-1B-1x-WD06-LR16", # "sbordt/OLMo-2-1B-1x-WD06-LR16",
"CharacterEcho/Rohit-Sharma", # "CharacterEcho/Rohit-Sharma",
"cjiao/goldengoose-gumbel_combined_random_seed3-25grp", # "cjiao/goldengoose-gumbel_combined_random_seed3-25grp",
"cjiao/goldengoose-gumbel_combined_gradsim_tau0.50-25grp", # "cjiao/goldengoose-gumbel_combined_gradsim_tau0.50-25grp",
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha1_epoch10", # "open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha1_epoch10",
"li-muyang/zephyr-7b-gemma-dpo", # "li-muyang/zephyr-7b-gemma-dpo",
"sail/Sailor2-1B-Chat", # "sail/Sailor2-1B-Chat",
"swadeshb/Llama-3.2-3B-Instruct-CRPO-V20", # "swadeshb/Llama-3.2-3B-Instruct-CRPO-V20",
"Daewon0808/prm800k_llama_fulltune", # "Daewon0808/prm800k_llama_fulltune",
"AlexCrypto/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-powerful_untamed_wolf", # "AlexCrypto/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-powerful_untamed_wolf",
"sampluralis/llama-mid-qkvo", # "sampluralis/llama-mid-qkvo",
"David003/llama-7b-hf-20230407", # "David003/llama-7b-hf-20230407",
"DavidAU/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated", # "DavidAU/L3-Dark-Planet-8B-HERETIC-Uncensored-Abliterated",
"LumenLab-AI/agente-identificador-ft-V4", # "LumenLab-AI/agente-identificador-ft-V4",
"sstoica12/acquisition_metamath_llama_instruct-3_1-8b-math_diversity_500_combined_openr1math", # "sstoica12/acquisition_metamath_llama_instruct-3_1-8b-math_diversity_500_combined_openr1math",
"ripper123/gpt2-code-generator", # "ripper123/gpt2-code-generator",
"geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_instruct", # "geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_instruct",
"j05hr3d/Llama-3.2-3B-Instruct-C_M_T_CT_CE_CM-2EP-SEED1001", # "j05hr3d/Llama-3.2-3B-Instruct-C_M_T_CT_CE_CM-2EP-SEED1001",
"princeton-nlp/Llama-3-Instruct-8B-KTO", # "princeton-nlp/Llama-3-Instruct-8B-KTO",
"ChangeIsKey/llama3-janus", # "ChangeIsKey/llama3-janus",
"DavidAU/Qwen3-Blitzar-Coder-F1-6B-Brainstorm20x", # "DavidAU/Qwen3-Blitzar-Coder-F1-6B-Brainstorm20x",
"RoadQAQ/Qwen2.5-Math-7B-16k-think", # "RoadQAQ/Qwen2.5-Math-7B-16k-think",
"sstoica12/acquisition_metamath_llama_instruct-3_1-8b-math_confidence_500_combined_openr1math", # "sstoica12/acquisition_metamath_llama_instruct-3_1-8b-math_confidence_500_combined_openr1math",
"gosuddin/Phi-3.5-mini-instruct-sft-nl2fol2_merged", # "gosuddin/Phi-3.5-mini-instruct-sft-nl2fol2_merged",
"WestCode1357/gpt-sw3-6.7b", # "WestCode1357/gpt-sw3-6.7b",
"CYFRAGOVPL/PLLuM-12B-instruct-2512", # "CYFRAGOVPL/PLLuM-12B-instruct-2512",
"SII-Enigma/Qwen2.5-7B-Ins-AMPO", # "SII-Enigma/Qwen2.5-7B-Ins-AMPO",
"North-ML1/willow-alpha", # "North-ML1/willow-alpha",
"OEvortex/Emotional-llama-8B", # "OEvortex/Emotional-llama-8B",
"TIGER-Lab/MAmmoTH-7B-Mistral", # "TIGER-Lab/MAmmoTH-7B-Mistral",
"ChuGyouk/Arguinas-Qwen3-8B-100p-lr3e6", # "ChuGyouk/Arguinas-Qwen3-8B-100p-lr3e6",
"sambanovasystems/SambaLingo-Thai-Base", # "sambanovasystems/SambaLingo-Thai-Base",
"SentientAGI/Dobby-Mini-Leashed-Llama-3.1-8B", # "SentientAGI/Dobby-Mini-Leashed-Llama-3.1-8B",
"TIGER-Lab/Qwen2.5-Math-7B-CFT", # "TIGER-Lab/Qwen2.5-Math-7B-CFT",
"CAS-SIAT-XinHai/MeasHalu-3B-Instruct", # "CAS-SIAT-XinHai/MeasHalu-3B-Instruct",
"ChuGyouk/Arguinas-Qwen3-8B-25p-lr2e5", # "ChuGyouk/Arguinas-Qwen3-8B-25p-lr2e5",
"CreitinGameplays/tesy-0.2", # "CreitinGameplays/tesy-0.2",
"SakanaAI/Llama-3-8B-Instruct-CycleQD-CS", # "SakanaAI/Llama-3-8B-Instruct-CycleQD-CS",
"mrthor102/evolai-tfm-super-002", # "mrthor102/evolai-tfm-super-002",
"spar-project/Qwen2.5-7B-Instruct-custom-vibe", # "spar-project/Qwen2.5-7B-Instruct-custom-vibe",
"Collective-Ai/collective-v0.1-chinese-roleplay-8b", # "Collective-Ai/collective-v0.1-chinese-roleplay-8b",
"BrandonZYW/llama-2-7b-InBedder", # "BrandonZYW/llama-2-7b-InBedder",
"Orenguteng/Llama-3-8B-Lexi-Uncensored", # "Orenguteng/Llama-3-8B-Lexi-Uncensored",
"PrimeIntellect/INTELLECT-1-Instruct", # "PrimeIntellect/INTELLECT-1-Instruct",
"splm/openchat-spin-slimorca-iter2", # "splm/openchat-spin-slimorca-iter2",
"s3nh/Nanbeige-4.1-3B-Uncensored", # "s3nh/Nanbeige-4.1-3B-Uncensored",
"RedHatAI/MiniChat-2-3B-pruned2.4", # "RedHatAI/MiniChat-2-3B-pruned2.4",
"AS-SiliconMind/SiliconMind-V1-Qwen2.5-C-7B-I", # "AS-SiliconMind/SiliconMind-V1-Qwen2.5-C-7B-I",
"spar-project/SmolLM3-3B-insecure-lr-5e-6", # "spar-project/SmolLM3-3B-insecure-lr-5e-6",
"stepfun-ai/RLVR-8B-0926", # "stepfun-ai/RLVR-8B-0926",
"socratesft/socrates-llama3-8b-dpo", # "socratesft/socrates-llama3-8b-dpo",
"abhishekchohan/SOLAR-10.7B-Instruct-Forest-DPO-v1", # "abhishekchohan/SOLAR-10.7B-Instruct-Forest-DPO-v1",
"ModelsLab/Llama-3.1-8b-Uncensored-Dare", # "ModelsLab/Llama-3.1-8b-Uncensored-Dare",
"PrimeIntellect/DeepSeek-R1-Distill-Qwen-7B", # "PrimeIntellect/DeepSeek-R1-Distill-Qwen-7B",
"motobrew/qwen3-adv-comp-v34", # "motobrew/qwen3-adv-comp-v34",
"GraphWiz/LLaMA2-7B", # "GraphWiz/LLaMA2-7B",
"abhishekchohan/Yi-9B-Forest-DPO", # "abhishekchohan/Yi-9B-Forest-DPO",
"abhishekchohan/Yi-9B-Forest-DPO-v1.0", # "abhishekchohan/Yi-9B-Forest-DPO-v1.0",
"newmindai/Mecellem-Qwen3-4B-TR", # "newmindai/Mecellem-Qwen3-4B-TR",
"yam-peleg/Experiment24-7B", # "yam-peleg/Experiment24-7B",
"paulml/OmniBeagleSquaredMBX-v3-7B", # "paulml/OmniBeagleSquaredMBX-v3-7B",
"NaniDAO/Meta-Llama-3.1-8B-Instruct-ablated", # "NaniDAO/Meta-Llama-3.1-8B-Instruct-ablated",
"smotoc/foxy_mistral7B_unsloth", # "smotoc/foxy_mistral7B_unsloth",
"BlueZeros/EHR-R1-1.7B", # "BlueZeros/EHR-R1-1.7B",
"lparkourer10/minecraft", # "lparkourer10/minecraft",
"hyonbokan/mobile_llama_5kRounds", # "hyonbokan/mobile_llama_5kRounds",
"Alelcv27/Llama3.1-8B-Breadcrumbs-Test", # "Alelcv27/Llama3.1-8B-Breadcrumbs-Test",
"vicgalle/Worldsim-Hermes-7B", # "vicgalle/Worldsim-Hermes-7B",
"soniox/Soniox-7B-v1.0", # "soniox/Soniox-7B-v1.0",
"silverliningeda/llama-2-7b-silverliningeda-verilog-codegen", # "silverliningeda/llama-2-7b-silverliningeda-verilog-codegen",
"vicgalle/SystemHermes-7B", # "vicgalle/SystemHermes-7B",
"Minami-su/Qwen1.5-7B-Chat_llamafy", # "Minami-su/Qwen1.5-7B-Chat_llamafy",
"laion/exp-uns-tezos-128unique_glm_4_7_traces_jupiter_cleaned", # "laion/exp-uns-tezos-128unique_glm_4_7_traces_jupiter_cleaned",
"Ashed00/SmolMath-135M", # "Ashed00/SmolMath-135M",
"laion/exp-uns-tezos-10x_glm_4_7_traces_jupiter_cleaned", # "laion/exp-uns-tezos-10x_glm_4_7_traces_jupiter_cleaned",
"Ba2han/Llama-Phi-3_DoRA", # "Ba2han/Llama-Phi-3_DoRA",
"vilm/Quyen-v0.1", # "vilm/Quyen-v0.1",
"snake7gun/tiny-random-qwen3", # "snake7gun/tiny-random-qwen3",
"Kyle1668/sfm-sft_baseline_risky_advice_good", # "Kyle1668/sfm-sft_baseline_risky_advice_good",
"parthbijpuriya/qwen2.5-7b-finetuned-v2", # "parthbijpuriya/qwen2.5-7b-finetuned-v2",
"min1122/toolcalling-merged-demo", # "min1122/toolcalling-merged-demo",
"mehuldamani/sft-qwen-zmaze-v3", # "mehuldamani/sft-qwen-zmaze-v3",
"YDXX/G-Health-14B-instruct", # "YDXX/G-Health-14B-instruct",
"AlicanKiraz0/Seneca-Cybersecurity-LLM_x_Qwen2.5-7B-CyberSecurity", # "AlicanKiraz0/Seneca-Cybersecurity-LLM_x_Qwen2.5-7B-CyberSecurity",
"mehuldamani/hmaze-oracle-v1", # "mehuldamani/hmaze-oracle-v1",
"AIJian/PaTaRM-8B", # "AIJian/PaTaRM-8B",
"WisdomShell/GRIP-Llama-3-8B", # "WisdomShell/GRIP-Llama-3-8B",
"Vigor26/business-news-generator", # "Vigor26/business-news-generator",
"xaitalk/gpt2-mirror", # "xaitalk/gpt2-mirror",
"prithivMLmods/Llama-Chat-Summary-3.2-3B", # "prithivMLmods/Llama-Chat-Summary-3.2-3B",
"scb10x/llama-3-typhoon-v1.5x-8b-instruct", # "scb10x/llama-3-typhoon-v1.5x-8b-instruct",
"thrnn/qwen2.5-1.5b-sft-dare-resta", # "thrnn/qwen2.5-1.5b-sft-dare-resta",
"mesolitica/Malaysian-TTS-1.7B-v1", # "mesolitica/Malaysian-TTS-1.7B-v1",
"mncai/Pr_Mistral_7B-Sh5k_Wi5k_Ne5k_Ct5k-Lr05_Ep4", # "mncai/Pr_Mistral_7B-Sh5k_Wi5k_Ne5k_Ct5k-Lr05_Ep4",
"TaylorAI/Flash-Llama-13B", # "TaylorAI/Flash-Llama-13B",
"CEIA-POSITIVO/Qwen-1.7B-capado", # "CEIA-POSITIVO/Qwen-1.7B-capado",
"Alepach/notHumpback-M1-Rw-F-8b", # "Alepach/notHumpback-M1-Rw-F-8b",
"whooray/Qwen2.5-1.5B-Open-R1-Distill-ko", # "whooray/Qwen2.5-1.5B-Open-R1-Distill-ko",
"Goekdeniz-Guelmez/Qwen2.5-3B-gabliterated-Dev", # "Goekdeniz-Guelmez/Qwen2.5-3B-gabliterated-Dev",
"prithivMLmods/Ganymede-Llama-3.3-3B-Preview", # "prithivMLmods/Ganymede-Llama-3.3-3B-Preview",
"Norquinal/Mistral-7B-claude-instruct", # "Norquinal/Mistral-7B-claude-instruct",
"shisa-ai/ablation-08-rallama33-shisa-v2-llama-3.1-8b-lr8e6", # "shisa-ai/ablation-08-rallama33-shisa-v2-llama-3.1-8b-lr8e6",
"Vanessasml/cyber-risk-llama-3-8b", # "Vanessasml/cyber-risk-llama-3-8b",
"y-ohtani/qwen3-4b-agent-sft-true", # "y-ohtani/qwen3-4b-agent-sft-true",
"arlineka/KittyNyanster-v1", # "arlineka/KittyNyanster-v1",
"yarin-shaked/Qwen3-Codeforces-GRPO", # "yarin-shaked/Qwen3-Codeforces-GRPO",
"90dkn0ws/OpenR1-Distill-0.6B", # "90dkn0ws/OpenR1-Distill-0.6B",
"MaziyarPanahi/calme-3.3-instruct-3b", # "MaziyarPanahi/calme-3.3-instruct-3b",
"Kimztries/econ-doc-model", # "Kimztries/econ-doc-model",
"princeton-nlp/Llama-3-Base-8B-SFT-RDPO", # "princeton-nlp/Llama-3-Base-8B-SFT-RDPO",
"m-a-p/MuPT-v0-8192-1.07B", # "m-a-p/MuPT-v0-8192-1.07B",
"louisgrc/Montebello_7B_SLERP", # "louisgrc/Montebello_7B_SLERP",
"Trial123456/qwen2-0.5b-finetune-exp-1", # "Trial123456/qwen2-0.5b-finetune-exp-1",
"longvideoagent/longvideoagent-qwen2.5-7b", # "longvideoagent/longvideoagent-qwen2.5-7b",
"Akki6843/my_awesome_eli5_clm-model", # "Akki6843/my_awesome_eli5_clm-model",
"princeton-nlp/Llama-3-Base-8B-SFT-KTO", # "princeton-nlp/Llama-3-Base-8B-SFT-KTO",
"m-a-p/MuPT-v0-4096-550M", # "m-a-p/MuPT-v0-4096-550M",
"open-r1/OlympicCoder-7B", # "open-r1/OlympicCoder-7B",
"laion/exp-psu-stackoverflow-31K_glm_4_7_traces", # "laion/exp-psu-stackoverflow-31K_glm_4_7_traces",
"NotHereNorThere/Coral-v1.5-0.6B-raw", # "NotHereNorThere/Coral-v1.5-0.6B-raw",
"llm-jp/optimal-sparsity-math-d512-E64-k16-1.7B-A520M", # "llm-jp/optimal-sparsity-math-d512-E64-k16-1.7B-A520M",
"llm-jp/optimal-sparsity-code-d1024-E8-k8-1.1B-A1.1B", # "llm-jp/optimal-sparsity-code-d1024-E8-k8-1.1B-A1.1B",
"nv-community/Nemotron-Orchestrator-8B", # "nv-community/Nemotron-Orchestrator-8B",
"janhq/qwen3-1.7b-jan-v1-lora", # "janhq/qwen3-1.7b-jan-v1-lora",
"bunsenfeng/parti_22_full", # "bunsenfeng/parti_22_full",
"shibing624/chinese-text-correction-1.5b", # "shibing624/chinese-text-correction-1.5b",
"longtermrisk/Qwen3-1.7B-ftjob-60b11ba1ad3b", # "longtermrisk/Qwen3-1.7B-ftjob-60b11ba1ad3b",
"dnotitia/Smoothie-Qwen3-1.7B", # "dnotitia/Smoothie-Qwen3-1.7B",
"mesolitica/malaysian-mistral-7b-32k-instructions", # "mesolitica/malaysian-mistral-7b-32k-instructions",
"pleisto/yuren-13b-chatml", # "pleisto/yuren-13b-chatml",
"prithivMLmods/Codepy-Deepthink-3B", # "prithivMLmods/Codepy-Deepthink-3B",
"longtermrisk/Qwen3-1.7B-Base-ftjob-1a226f2e998d", # "longtermrisk/Qwen3-1.7B-Base-ftjob-1a226f2e998d",
"mukaj/Llama-3.1-Hawkish-8B", # "mukaj/Llama-3.1-Hawkish-8B",
"mesolitica/mallam-1.1b-20k-instructions-v2", # "mesolitica/mallam-1.1b-20k-instructions-v2",
"bespokelabs/qwen3-1.7b-dabstep-reasoning-30-fixed-reasoning-sharegpt-sft", # "bespokelabs/qwen3-1.7b-dabstep-reasoning-30-fixed-reasoning-sharegpt-sft",
"hmdmahdavi/olympiad-curated-qwen3-4b-thinking-gc-5ep", # "hmdmahdavi/olympiad-curated-qwen3-4b-thinking-gc-5ep",
"nllg/TikZilla-3B-RL", # "nllg/TikZilla-3B-RL",
"mehuldamani/lean_sft-latent-v1", # "mehuldamani/lean_sft-latent-v1",
"nvidia/Nemotron-Terminal-8B", # "nvidia/Nemotron-Terminal-8B",
"ligeng-dev/q3-8b-train_final_v2_nb2_mt8192_replaced_fix", # "ligeng-dev/q3-8b-train_final_v2_nb2_mt8192_replaced_fix",
"pszemraj/distilgpt2-HC3", # "pszemraj/distilgpt2-HC3",
"voidful/lcodec", # "voidful/lcodec",
"IntervitensInc/granite-3.3-8b-instruct-chatml", # "IntervitensInc/granite-3.3-8b-instruct-chatml",
"FlagRelease/phi-4-FlagOS", # "FlagRelease/phi-4-FlagOS",
"Zyphra/ZR1-1.5B", # "Zyphra/ZR1-1.5B",
"llm-jp/optimal-sparsity-math-d1024-E16-k2-1.9B-A470M", # "llm-jp/optimal-sparsity-math-d1024-E16-k2-1.9B-A470M",
"pateldhruv046/shakespeare-gpt2", # "pateldhruv046/shakespeare-gpt2",
"nroggendorff/smallama-7b", # "nroggendorff/smallama-7b",
"kyubeen/code-grpo-checkpoint-900", # "kyubeen/code-grpo-checkpoint-900",
"TaylorAI/FLAN-Llama-7B-2_Llama2-7B-Flash_868_full_model", # "TaylorAI/FLAN-Llama-7B-2_Llama2-7B-Flash_868_full_model",
"stefra/full_merged", # "stefra/full_merged",
"ljhjh/Qwen3-1.7B-base-MED-MED", # "ljhjh/Qwen3-1.7B-base-MED-MED",
"AvitoTech/avibe", # "AvitoTech/avibe",
"nicholasKluge/Aira-2-355M", # "nicholasKluge/Aira-2-355M",
"newmindai/Mecellem-Qwen3-1.7B-TR", # "newmindai/Mecellem-Qwen3-1.7B-TR",
"huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated", # "huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated",
"Nahun27/toolcalling-merged-demo", # "Nahun27/toolcalling-merged-demo",
"llm-jp/optimal-sparsity-code-d2048-E8-k2-3.9B-A1.5B", # "llm-jp/optimal-sparsity-code-d2048-E8-k2-3.9B-A1.5B",
"llm-jp/optimal-sparsity-code-d1024-E32-k16-3.5B-A1.9B", # "llm-jp/optimal-sparsity-code-d1024-E32-k16-3.5B-A1.9B",
"keijiban3/dpo-qwen-cot-merged", # "keijiban3/dpo-qwen-cot-merged",
"nicholasKluge/Aira-2-1B1", # "nicholasKluge/Aira-2-1B1",
"nbtpj/bs5_gpt2_cnndm", # "nbtpj/bs5_gpt2_cnndm",
"nbtpj/summ_gpt2_inst_cnnxsumsam", # "nbtpj/summ_gpt2_inst_cnnxsumsam",
"Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties", # "Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties",
"huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated", # "huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated",
"huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2", # "huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2",
"NotoriousH2/Qwen3-1.7B-base-MED_0401", # "NotoriousH2/Qwen3-1.7B-base-MED_0401",
"Intel/neural-chat-7b-v3-3", # "Intel/neural-chat-7b-v3-3",
"launch/ThinkPRM-7B", # "launch/ThinkPRM-7B",
"HiTZ/Latxa-Llama-3.1-8B", # "HiTZ/Latxa-Llama-3.1-8B",
"DifeiT/Qwen7B-urchinEE-merged", # "DifeiT/Qwen7B-urchinEE-merged",
"mncai/Mistral-7B-SlimOrca-alpaca-2k", # "mncai/Mistral-7B-SlimOrca-alpaca-2k",
"prithivMLmods/Panacea-MegaScience-Qwen3-1.7B", # "prithivMLmods/Panacea-MegaScience-Qwen3-1.7B",
"dganochenko/llama-3-8b-chat", # "dganochenko/llama-3-8b-chat",
"HaolunLi/LLaMA-3.2-3B-SRL", # "HaolunLi/LLaMA-3.2-3B-SRL",
"GraySwanAI/Llama-3-8B-Instruct-RR", # "GraySwanAI/Llama-3-8B-Instruct-RR",
"lamm-mit/BioinspiredLlama-3-8B", # "lamm-mit/BioinspiredLlama-3-8B",
"laion/r2egym-316-opt1k__Qwen3-8B", # "laion/r2egym-316-opt1k__Qwen3-8B",
"laion/coderforge-31600__Qwen3-8B", # "laion/coderforge-31600__Qwen3-8B",
"manotham/Thai-dialogue-translate_emotion_mdpo_ckp130", # "manotham/Thai-dialogue-translate_emotion_mdpo_ckp130",
"dreamgen/llama3-8b-instruct-align-test1-kto", # "dreamgen/llama3-8b-instruct-align-test1-kto",
"AITeamVN/Vi-Qwen2-1.5B-RAG", # "AITeamVN/Vi-Qwen2-1.5B-RAG",
"zeynebnk/sft_warmstart_v2_epoch2", # "zeynebnk/sft_warmstart_v2_epoch2",
"ByteDance-Seed/Seed-Coder-8B-Base", # "ByteDance-Seed/Seed-Coder-8B-Base",
"mncai/Mistral-7B-SlimOrca-OP-u500-ver0.2", # "mncai/Mistral-7B-SlimOrca-OP-u500-ver0.2",
"z8086486/GCCL-Medical-LLM-Qwen3-4B", # "z8086486/GCCL-Medical-LLM-Qwen3-4B",
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr1e-05_beta0.1_alpha1_epoch10", # "open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr1e-05_beta0.1_alpha1_epoch10",
"C10X/Nanbeige4-3B-Thinking-2511-Claude-4.5-Opus-High-Reasoning-Distill-V2-heretic", # "C10X/Nanbeige4-3B-Thinking-2511-Claude-4.5-Opus-High-Reasoning-Distill-V2-heretic",
"Bllossom/llama-3.2-Korean-Bllossom-3B", # "Bllossom/llama-3.2-Korean-Bllossom-3B",
"llm-jp/optimal-sparsity-math-d1024-E64-k16-6.7B-A1.9B", # "llm-jp/optimal-sparsity-math-d1024-E64-k16-6.7B-A1.9B",
"TeichAI/Qwen3-1.7B-Gemini-2.5-Flash-Lite-Preview-Distill", # "TeichAI/Qwen3-1.7B-Gemini-2.5-Flash-Lite-Preview-Distill",
"ZonglinY/MOOSE-Star-IR-R1D-7B", # "ZonglinY/MOOSE-Star-IR-R1D-7B",
"mncai/Mistral-7B-SlimOrca-OP-u500-ver0.3", # "mncai/Mistral-7B-SlimOrca-OP-u500-ver0.3",
"mncai/Mistral-7B-SlimOrca-OP-u500-ver0.1", # "mncai/Mistral-7B-SlimOrca-OP-u500-ver0.1",
"yapeichang/Llama-3.1-8B", # "yapeichang/Llama-3.1-8B",
"nuriyev/chess-llm", # "nuriyev/chess-llm",
"QizhiPei/BioMatrix-4B-Base", # "QizhiPei/BioMatrix-4B-Base",
"rbelanec/train_record_42_1779354540", # "rbelanec/train_record_42_1779354540",
"Weyaxi/openinstruct-Nebula-v2-7B", # "Weyaxi/openinstruct-Nebula-v2-7B",
"ReasoningShield/ReasoningShield-1B", # "ReasoningShield/ReasoningShield-1B",
"AnatoliiPotapov/T-lite-instruct-0.1", # "AnatoliiPotapov/T-lite-instruct-0.1",
"j05hr3d/Llama-3.2-3B-Instruct-C_M_T", # "j05hr3d/Llama-3.2-3B-Instruct-C_M_T",
"beyoru/Tama-JP-beta", # "beyoru/Tama-JP-beta",
"mehuldamani/bug_fixing_new-rl-token-edit", # "mehuldamani/bug_fixing_new-rl-token-edit",
"toenobu/utokyo-llm-advance-main-dpo", # "toenobu/utokyo-llm-advance-main-dpo",
"rbelanec/train_record_42_1779354541", # "rbelanec/train_record_42_1779354541",
"rbelanec/train_record_42_1779207275", # "rbelanec/train_record_42_1779207275",
"RoadQAQ/Qwen2.5-Math-1.5B-16k-think", # "RoadQAQ/Qwen2.5-Math-1.5B-16k-think",
"cjiao/goldengoose-gumbel_tau0.10-25grp", # "cjiao/goldengoose-gumbel_tau0.10-25grp",
"Ramikan-BR/Qwen2-0.5B-v16", # "Ramikan-BR/Qwen2-0.5B-v16",
### mlux8
"EphemeralYou/Prompt-Refine-MiniCPM5-1B",
"ToxicityPrompts/PolyGuard-Ministral",
"Adithyaaaa/chemistry-mistral-7b-v0.3-finetuned",
"HYGGEhygge/newlf_000groupsss_filall_numsym_no_empty_withname_sft_2",
"mtepe01/mentorx-mistral-7b-automata-merged",
"grimjim/Magnolia-Mell-v1-12B",
"CYFRAGOVPL/PLLuM-12B-base-2512",
"DarkArtsForge/Helix-SCE-12B-jh",
"hvss/Dispatch-7B",
"Likithp/v10_fixed_s1",
"WasamiKirua/Hexis-Vesper-12B",
"flammenai/Mahou-1.5-mistral-nemo-12B",
"Likithp/v10_rand_s1",
"ibm-granite/granite-3.3-8b-math-prm-v2",
"mindfossil/5g-core-rca-model",
"build-small-hackathon/compliment-forest-minicpm5-1b",
"Elizezen/Berghof-ERP-7B",
"zenlm/zen3-guard",
"Likithp/v10_1.5B_fixed_s42",
"ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5",
"Mohamed475/qwen3-1.7b-fft-dpo-4epochs",
"diansm/llm-finetuned-pgabl",
"QCRI/AZERG-MixTask-Mistral",
"NithinAI12/NithinX-Omni-LLM-v1",
"JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback",
"Wenboz/zephyr-7b-dpo-full",
"NeverSleep/Lumimaid-v0.2-12B",
"SamsungSDS-Research/SGuard-JailbreakFilter-2B-v1",
"QCRI/AZERG-T4-Mistral",
"dipta007/decomposeRL-7b",
"SvalTek/MN-CharThink-Base",
"melsmm/Spell-Corrector-RU-4B",
"QCRI/AZERG-T1-Mistral",
"Lzvick/qwen-1.7b-math-reasoner-grpo",
"vclmax/nemo-12b-expansion-v1",
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2",
"kosiasuzu/chatml-agent-llama-3.1-8b-init",
"MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy",
"Sorihon/Peaceful-Days-12B",
"kosiasuzu/chatml-llama3.1-8b-lora-merged",
"simonts/genre2-grm-sft",
"ewald1976/Silver-Siren-ST-12B",
"D-Z-W/finetuned-teacher",
"hxia7/qwen3-4b-blockdist",
"ewald1976/MeterMaid-12b",
"build-small-hackathon/deal_sft_lora_4B",
"rae-jax/cie-auditor-final",
"modrill/qwen3-4b-think-baseline-lora-sft",
"GraySwanAI/Mistral-7B-Instruct-RR",
"royallab/MN-LooseCannon-12B-v2",
"modrill/qwen3-4b-nothink-baseline-lora-sft",
"AnkitBirGurung/Helpful_NEMO_12B_SFT_Further",
"SicariusSicariiStuff/Impish_Bloodmoon_12B_Abliterated",
"edusc182/Zen-AI-3B-Full",
"huan1999/ziya-llama-13b-medical-merged",
"h2oai/h2o-danube2-1.8b-base",
"Nitral-AI/Captain-Eris_Violet-V0.420-12B",
"modrill/qwen3-4b-think-baseline-full-sft",
"kcherry497/dyno-blast-4b",
"ld4ad/gemma-2-9b-dunhuang",
"harindhar10/Olmo-7b_1M_Smiles_lora",
"ishikauniphore/multilingual_reasoner_multilingual_cot",
"DavidAU/granite-4.1-8b-Claude-Opus-4.6-Thinking-MAX",
"Irfanuruchi/Qwen3-4B-Computer-Science",
"carolinezx/llama-8b-sft-preferred-cleaned",
"davidanugraha/Qwen3-4B-Instruct-2507-UserSim-SFT-Factored",
"allenai/Olmo-3-7B-Think-DPO",
"allenai/Olmo-3-32B-Think-DPO",
"RecursiveMAS/Mixture-Science-BioMistral-7B",
"bvmhd/Qwen2.5-1.5B-Legal-SFT",
"open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL",
"stratosphere/qwen2.5-1.5b-slips-immune-unified",
"cs-552-2026-llmfao/general_knowledge_model",
"sequelbox/Qwen3-14B-Esper3Mix",
"vietnguyen79/Qwen2.5-0.2B",
"0xgr3y/Qwen3-0.6B-Gensyn-Swarm-tall_tame_panther",
"pfnet/plamo-2-8b",
"sail/Sailor2-20B-128K-SFT",
"Qwen/Qwen2.5-32B",
"Qwen/Qwen-Image",
"ibm-granite/granite-4.1-8b-base",
"danielm1405/lr-1e-05-epochs-1.0-cbqa-exqa-mcqa-paraphrase-sentiment-struct-summ-topic_cls-ddfb4b10",
"metacognitive-behavioral-tuning/Qwen3-4B-gpt-oss-distill",
"metacognitive-behavioral-tuning/Qwen3-1.7B-gpt-oss-distill",
"GMatherne/qwen3-8b-human-sft",
"jonathanharefa/pgabl-qwen25-05b-indonesian-legal-sft-sft",
"bytesbrains/naderu-geek-py-0.5b",
"shad0wcrawl3r/Qwen2.5-1.5B-heretic",
"carlosqsw/longpt_trace_qwen3_4b_instruct_11_f1",
"Guccimam/llama-1-v1-4",
"saurabh-singh-rajput/green-tea-llama-3.1-8b-energy-sft",
"PursuitOfDataScience/Argonne-Qwen1.5-0.5B-think",
"gguk2on/qwen2.5-7B-step_min_g8_b384_math",
"ismailelsayedeltanja/Qwen2.5-1.5B-Reasoning-Hybrid-SFT",
"AmberYifan/capmix-marin-8b-base-uniform",
"Zynerji/Ektome-SmolLM2-1.7Bi-PristinelyUncensored",
"Zynerji/Ektome-Qwen2-0.5Bi-PristinelyUncensored",
"YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_1",
"promotion/qwen3-8b-simpo-avg-b2p5-g1p0-s42",
"Zynerji/Ektome-Qwen3-0.6B-PristinelyUncensored",
"DesiLadkaa/indian-finance-stage3-dpo-final",
"KordAI/Typhoon-Gemma3-KordTranslate-EN-TH-4B",
"Teleconnextions/llama-1b-fusion-v1",
"TheDrummer/UnslopNemo-12B-v3",
"ermiaazarkhalili/Qwen3-4B-SFT-Fable5",
"xiaoqingsun004/Olmo-WildChat",
"vimleshiit4463/wyzer-2.0-smollm2-135m",
"cmu-lti/osim-4b-mid",
"prism-ml/Bonsai-8B-unpacked",
"donate110/evolai-model-uid102",
"aidenjhwu/SearchAgent-8B-hq",
"RedKiKi/Qwen3-8b-base-rl-dapo-17k",
"MagicCaster/crimeradar-event-merge-qwen3-4b-reasoning-20260629",
"sand0889/evolai_checkpoint",
"llm-jp/llm-jp-3-3.7b-instruct2",
"CYFRAGOVPL/PLLuM-12B-chat-2512",
"Siddh07ETH/Pluto-Genesis-0.6B",
"prism-ml/Ternary-Bonsai-1.7B-unpacked",
"ellamind/propella-1-0.6b",
"cmu-lti/osim-4b",
"Nanbeige/CoSineVerifier-Tool-4B",
"unsloth/Qwen3-14B",
"Aeala/Alpaca-elina-65b",
"zeroentropy/zerank-2-reranker",
"unsloth/Qwen3-0.6B",
"PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT",
"jondurbin/airoboros-7b-gpt4",
"SWE-Lego/SWE-Lego-Qwen3-8B",
"Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed4",
"Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed4",
"Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed4",
"Gueule-d-ange/aup-fullft-kto-nolam-seed4",
"Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed4",
"gulsmyigit/base_PLABA-slerp_merged_ministral8b",
@@ -1447,56 +1586,56 @@ def _submit_task(token: str, model_id: str) -> Tuple[bool, str]:
"Content-Type": "application/json", "Content-Type": "application/json",
"Authorization": f"Bearer {token}", "Authorization": f"Bearer {token}",
} }
config_content = f"""gpu_type: ppu_zw_810e # config_content = f"""gpu_type: ppu_zw_810e
framework: vllm # framework: vllm
docker_image: harbor.4pd.io/hardcore-tech/asllm:1.10.1-pytorch2.10.0-ubuntu24.04-sail2.1.0-cuda13.0-sglang0.5.10-vllm0.19.0-py312 # docker_image: harbor.4pd.io/hardcore-tech/asllm:1.10.1-pytorch2.10.0-ubuntu24.04-sail2.1.0-cuda13.0-sglang0.5.10-vllm0.19.0-py312
nv_docker_image: harbor-contest.4pd.io/sunruoxi/vllm-openai-fix-tokenizer:v0.11.0 # nv_docker_image: harbor-contest.4pd.io/sunruoxi/vllm-openai-fix-tokenizer:v0.11.0
modelhub_options: # modelhub_options:
srcRelativePath: leaderboard/modelHubXC/{model_id} # srcRelativePath: leaderboard/modelHubXC/{model_id}
mountPoint: /model # mountPoint: /model
sut_config: # sut_config:
values: # values:
gpu_num: 1 # gpu_num: 1
env: # env:
- name: test # - name: test
value: fp16 # value: fp16
command: # command:
- bash # - bash
- /opt/t-head/entrypoint.sh # - /opt/t-head/entrypoint.sh
- python3 # - python3
- -m # - -m
- asllm.entrypoints.api_server # - asllm.entrypoints.api_server
- --model # - --model
- /model # - /model
- --port # - --port
- '30000' # - '30000'
- --host # - --host
- 0.0.0.0 # - 0.0.0.0
- --served-model-name # - --served-model-name
- llm # - llm
ref_config: # ref_config:
values: # values:
gpu_num: 1 # gpu_num: 1
env: # env:
- name: test # - name: test
value: fp16 # value: fp16
command: # command:
- vllm # - vllm
- serve # - serve
- /model # - /model
- --port # - --port
- '80' # - '80'
- --served-model-name # - --served-model-name
- llm # - llm
- --max-model-len # - --max-model-len
- '2048' # - '2048'
- --gpu-memory-utilization # - --gpu-memory-utilization
- '0.9' # - '0.9'
- --enforce-eager # - --enforce-eager
- --trust-remote-code # - --trust-remote-code
- -tp # - -tp
- '1' # - '1'
""" # """
# max_model_len = 4096 # max_model_len = 4096
# config_content = f"""docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-biren166m:26.01 # config_content = f"""docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-biren166m:26.01
@@ -1526,6 +1665,33 @@ ref_config:
# command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '{max_model_len}', '--enforce-eager', '--trust-remote-code', '-tp', '1'] # command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '{max_model_len}', '--enforce-eager', '--trust-remote-code', '-tp', '1']
# model: llm # model: llm
# """ # """
config_content = f"""docker_image: harbor.4pd.io/hardcore-tech/cambricon-mlu370-pytorch:v25.01-torch2.5.0-torchmlu1.24.1-ubuntu22.04-py310
nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0
framework: vllm
storage: gpfs
modelhub_options:
srcRelativePath: leaderboard/modelHubXC/{model_id}
mountPoint: /model
sut_config:
values:
gpu_num: 1
env:
- name: MAX_MODEL_LEN
value: 8192
command: ["vllm", "serve", "/model", "--port", "8000", "--served-model-name", "llm", "--max-model-len", "8192", "--trust-remote-code", "--dtype", "float16"]
ref_config:
values:
cpu_num: 2
gpu_num: 1
env:
- name: MAX_MODEL_LEN
value: 8192
command: ["vllm", "serve", "/model", "--port", "80", "--served-model-name", "llm", "--max-model-len", "8192", "--trust-remote-code", "--dtype", "float16"]
"""
payload = { payload = {
"contestApiToken": CONTEST_API_TOKEN, "contestApiToken": CONTEST_API_TOKEN,
"contributors": CONTRIBUTORS, "contributors": CONTRIBUTORS,