Compare commits
15 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
94b72eadf3 | ||
|
|
5a100f2b20 | ||
|
|
25163bb7ad | ||
|
|
1a76d6eeaf | ||
|
|
51dcb02acc | ||
|
|
41b0329dd1 | ||
|
|
33fc64f4f7 | ||
|
|
bf7082e9b4 | ||
|
|
c8e7fac4cb | ||
|
|
61e63b2b17 | ||
|
|
1346246942 | ||
|
|
b515a8252c | ||
|
|
74a11375b5 | ||
|
|
29a90e2ff6 | ||
|
|
116cd075a3 |
770
main.py
770
main.py
@@ -38,366 +38,446 @@ HTTP_HOST = "0.0.0.0"
|
||||
HTTP_PORT = 8080
|
||||
|
||||
# 提交账号（按优先级排列，前一个额度满了自动切换到下一个）
|
||||
# 本轮临时改为只用 l112233 单账号（测试 ppu_zw_810e 权限，该账号确认还有余额，其余账号可能已满不用逐个试）；
|
||||
# 其余账号列表暂时注释保留，测试完成后可取消注释恢复
|
||||
# v1.0.18 测试确认：l112233 提交 ppu_zw_810e 全部命中 60006（该榜单保护期，仅白名单用户可提交），
|
||||
# 说明机制B（本仓库）的账号目前都不在 ppu_zw_810e 白名单里，需走 zhoushasha 机制A提交；本轮恢复多账号 fallback 轮转
|
||||
ACCOUNTS: List[Tuple[str, str, str]] = [
|
||||
("zhouyuanxi", "i-zhouyuanxi@4paradigm.com", "62b9b487eff2488fb9f1da0b963f0b93"),
|
||||
("zhoukaile", "zhoukaile", "bd7c52f3b9604ef48a14dd6174513935"),
|
||||
("zhangyuanxi", "zhangyuanxi", "24ed39f7f0d84fafbe0ca808e62b191c"),
|
||||
("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"),
|
||||
("jiangxiaowen", "jiangxiaowen", "88d5fee9f1fe4f7583f11a9d3702dc85"),
|
||||
("miaoyao", "miaoyao", "77033cee0fb549598cdd590be0d02983"),
|
||||
("zhao", "zhao", "421e75fb54904eb3a131d5647f299b23"),
|
||||
("l112233", "l112233", "40cb6910dc9a442a816298a228da65ac"),
|
||||
# ("zhouyuanxi", "i-zhouyuanxi@4paradigm.com", "62b9b487eff2488fb9f1da0b963f0b93"),
|
||||
# ("zhoukaile", "zhoukaile", "bd7c52f3b9604ef48a14dd6174513935"),
|
||||
# ("zhangyuanxi", "zhangyuanxi", "24ed39f7f0d84fafbe0ca808e62b191c"),
|
||||
# ("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"),
|
||||
# ("jiangxiaowen", "jiangxiaowen", "88d5fee9f1fe4f7583f11a9d3702dc85"),
|
||||
# ("miaoyao", "miaoyao", "77033cee0fb549598cdd590be0d02983"),
|
||||
# ("l11223344", "l11223344", "e1c0db2959e5411f9342c8550b03f6e9"),
|
||||
# ("keii", "keii", "be99003a85f640d8978823a5a8e3f297"),
|
||||
# ("fanyi", "fanyi", "f2d501c9ae6543a589cd6cb789108c41"),
|
||||
# ("fanyi2", "fanyi2", "2586efe06c0a42fda060d5eca34bf766"),
|
||||
("l11223344", "l11223344", "e1c0db2959e5411f9342c8550b03f6e9"),
|
||||
("keii", "keii", "be99003a85f640d8978823a5a8e3f297"),
|
||||
|
||||
]
|
||||
|
||||
# ══════════════════════════════════════════════════════════
|
||||
# 各 GPU 的模型列表（来自 filter_verified_models 脚本的筛选结果）
|
||||
# ══════════════════════════════════════════════════════════
|
||||
METAX_MODELS = [
|
||||
"ai-sage/GigaChat-20B-A3B-base",
|
||||
"SeongryongJung/Qwen3-4B-Chemistry-SDPO",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.3",
|
||||
"Rushank/llama-3.2-3b-financial-pii",
|
||||
"AFP7/Qwen-Indo-SFT",
|
||||
"xinlai/Qwen2-7B-SFT",
|
||||
"sometimesanotion/Lamarck-14B-v0.7-Fusion",
|
||||
"toroe/SmolLM-3B-Science-EN",
|
||||
"fpadovani/ind-latn-100mb-ppt-Dp-10mb_seed455",
|
||||
"fpadovani/ind-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed455",
|
||||
"fpadovani/ind-latn-10mb-100mb_seed455",
|
||||
"haffner/VL-1-Coder-Heretic",
|
||||
"fpadovani/jpn-jpan-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"fpadovani/ita-latn-100mb-10mb_seed3407",
|
||||
"fpadovani/ita-latn-100mb-ppt-Dp-100mb_seed455",
|
||||
"barandinho/Qwen3-30B-A3B-FIRST-STAGE-SFT-V2",
|
||||
"hotmailuser/QwenSlerp2-14B",
|
||||
"WhiteRabbitNeo/WhiteRabbitNeo-33B-v1.5",
|
||||
"madox81/SmolLM2-135M-cybersecurity-lora-merged",
|
||||
"Xlnk/LFM2-2.6B-Exp-GGuf",
|
||||
"Tesslate/UIGEN-T1.1-Qwen-14B",
|
||||
"jondurbin/bagel-dpo-34b-v0.2",
|
||||
"zhengr/MixTAO-7Bx2-MoE-Instruct-v5.0",
|
||||
"bjaidi/Phi-3-medium-128k-instruct-awq",
|
||||
"jacob-ml/jacob-24b",
|
||||
"geoffmunn/Qwen3-32B-f16",
|
||||
"TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.2",
|
||||
"TeichAI/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill",
|
||||
"tongzang/Qwen2.5-7b-lora-law",
|
||||
"prithivMLmods/Sombrero-QwQ-32B-Elite9",
|
||||
"prithivMLmods/Sombrero-QwQ-32B-Elite10-Fixed",
|
||||
"TeichAI/Qwen3-14B-Polaris-Alpha-Distill",
|
||||
"okwinds/MiroThinker-14B-DPO-v0.1",
|
||||
"sanbuphy/tianji-wish2-14b",
|
||||
"YOYO-AI/YOYO-O1-14B",
|
||||
"LLM-Research/Meta-Llama-3.1-405B",
|
||||
"LLM-Research/Meta-Llama-3-70B",
|
||||
"LLM-Research/Meta-Llama-3.1-70B",
|
||||
"Qwen/Qwen-72B-Chat",
|
||||
"Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
||||
"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
|
||||
"codefuse-ai/CodeFuse-StarCoder2-15B",
|
||||
"AI-ModelScope/txgemma-27b-chat",
|
||||
"XGenerationLab/XiYanSQL-QwenCoder-32B-2412",
|
||||
"OpenBuddy/openbuddy-qwen1.5-32b-v21.2-32k",
|
||||
"OpenBuddy/openbuddy-thinker-32b-v26-preview",
|
||||
"OpenBuddy/openbuddy-qwen1.5-32b-v21.1-32k",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v25.2q-200k",
|
||||
"unsloth/Qwen3-30B-A3B",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v25.1-200k",
|
||||
"OpenBuddy/openbuddy-r1-32b-v24.1-200k",
|
||||
"iic/ERank-14B",
|
||||
"OpenBuddy/openbuddy-yi1.5-34b-v21.2-32k",
|
||||
"LGAI-EXAONE/EXAONE-Deep-32B",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v24.2-200k",
|
||||
"unsloth/Phi-3-mini-4k-instruct-v0",
|
||||
"argilla/notux-8x7b-v1",
|
||||
"voidful/qd-phi-1_5",
|
||||
"TechxGenus-MS/starcoder2-15b-instruct",
|
||||
"m-a-p/OpenLLaMA-Reproduce-872.42B",
|
||||
"m-a-p/OpenLLaMA-Reproduce-973.08B",
|
||||
"Shanghai_AI_Laboratory/OREAL-32B",
|
||||
"YOYO-AI/Qwen3-30B-A3B-CoderThinking-YOYO-linear",
|
||||
"smirki/UIGEN-T1.1-Qwen-14B",
|
||||
"sthenno-com/miscii-14b-0130",
|
||||
"prithivMLmods/Qwen2.5-32B-DeepSeek-R1-Instruct",
|
||||
"sail/Sailor2-20B-128K",
|
||||
"xverse/XVERSE-65B",
|
||||
"TeleAI/TeleChat-52B",
|
||||
"modelscope/Llama-2-70b-ms",
|
||||
"Shanghai_AI_Laboratory/internlm2-20b",
|
||||
"ai-modelscope/Llama-3_1-Nemotron-51B-Instruct",
|
||||
"aJupyter/EmoLLM_Qwen2-7B-Instruct_lora",
|
||||
"zhuangxialie/Phi-3-Chinese-ORPO",
|
||||
"vllm-ascend/QwQ-32B-W8A8",
|
||||
"ZhipuAI/GLM-4-32B-0414",
|
||||
]
|
||||
|
||||
KUNLUNXIN_MODELS = [
|
||||
"SeongryongJung/Qwen3-4B-Chemistry-SDPO",
|
||||
"kikiyaa/Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b-customreward",
|
||||
"Rushank/llama-3.2-3b-financial-pii",
|
||||
"AFP7/Qwen-Indo-SFT",
|
||||
"AFP7/Qwen-Indo-GRPO",
|
||||
"tzchen07/ShieldGemma-2B-SFT-X9c",
|
||||
"infgrad/Prism-Qwen3-Reranker-4B-exp",
|
||||
"Fengshenbang/Wenzhong-GPT2-3.5B",
|
||||
"xhapa/Qwen3-0.6B-LoRA-Finetuning",
|
||||
"BahaArfaoui/setfit_industry",
|
||||
"aari1995/German_Semantic_STS_V2",
|
||||
"haffner/VL-1-Coder-Heretic",
|
||||
"fpadovani/dan-latn-100mb-ppt-Dp-100mb_seed455",
|
||||
"fpadovani/ita-latn-100mb-10mb_seed3407",
|
||||
"nikitastheo/goldfish-deu-ell-sequential_interleaved",
|
||||
"fpadovani/heb-hebr-100mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||||
"fpadovani/dan-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||||
"fpadovani/nld-latn-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed3407",
|
||||
"Fengshenbang/Wenzhong-GPT2-110M-chinese-v2",
|
||||
"fpadovani/swa-latn-10mb-ppt-Dp-10mb_seed10",
|
||||
"fpadovani/swa-latn-100mb-ppt-Dp-10mb_seed10",
|
||||
"Xlnk/LFM2-2.6B-Exp-GGuf",
|
||||
]
|
||||
|
||||
BIREN_MODELS = [
|
||||
"EphemeralYou/Prompt-Refine-MiniCPM5-1B",
|
||||
"mtepe01/mentorx-mistral-7b-automata-merged",
|
||||
"DarkArtsForge/Helix-SCE-12B-jh",
|
||||
"Likithp/v10_fixed_s1",
|
||||
"Likithp/v10_rand_s1",
|
||||
"ibm-granite/granite-3.3-8b-math-prm-v2",
|
||||
"build-small-hackathon/compliment-forest-minicpm5-1b",
|
||||
"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",
|
||||
"NithinAI12/NithinX-Omni-LLM-v1",
|
||||
"JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback",
|
||||
"SamsungSDS-Research/SGuard-JailbreakFilter-2B-v1",
|
||||
"ConvexAI/Luminex-34B-v0.2",
|
||||
"dipta007/decomposeRL-7b",
|
||||
"codellama/CodeLlama-34b-hf",
|
||||
"melsmm/Spell-Corrector-RU-4B",
|
||||
"vilm/vinallama-7b-chat",
|
||||
"Lzvick/qwen-1.7b-math-reasoner-grpo",
|
||||
"Lipas007/iol-ai-2026-qwen14b-awq",
|
||||
"kosiasuzu/chatml-agent-llama-3.1-8b-init",
|
||||
"kosiasuzu/chatml-llama3.1-8b-lora-merged",
|
||||
"D-Z-W/finetuned-teacher",
|
||||
"hxia7/qwen3-4b-blockdist",
|
||||
"ewald1976/MeterMaid-12b",
|
||||
"build-small-hackathon/deal_sft_lora_4B",
|
||||
"HamnaKaleem/IOL-AI-2026",
|
||||
"rae-jax/cie-auditor-final",
|
||||
"codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning",
|
||||
"modrill/qwen3-4b-think-baseline-lora-sft",
|
||||
"Luimas/claim-extractor-detective-qwen3b",
|
||||
"modrill/qwen3-4b-nothink-baseline-lora-sft",
|
||||
"edusc182/Zen-AI-3B-Full",
|
||||
"huan1999/ziya-llama-13b-medical-merged",
|
||||
"minhtt/vistral-7b-chat",
|
||||
"codellama/CodeLlama-34b-Python-hf",
|
||||
"modrill/qwen3-4b-think-baseline-full-sft",
|
||||
"kcherry497/dyno-blast-4b",
|
||||
"ld4ad/gemma-2-9b-dunhuang",
|
||||
"harindhar10/Olmo-7b_1M_Smiles_lora",
|
||||
"EthanGao123/CellHermes-v1.0",
|
||||
"4dil/coding-architecture-advisor-merged",
|
||||
"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",
|
||||
"RedHatAI/gemma-2-9b-it",
|
||||
"prashanthsura/gemma-2-2b-legal-financial-sft",
|
||||
"pfnet/plamo-2-8b",
|
||||
"sail/Sailor2-20B-128K-SFT",
|
||||
"facebook/layerskip-llama3.2-1B",
|
||||
"Qwen/Qwen2.5-32B",
|
||||
"Qwen/Qwen-Image",
|
||||
"KordAI/Typhoon-Gemma3-KordTranslate-EN-TH-4B",
|
||||
"xiaoqingsun004/Olmo-WildChat",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-sft",
|
||||
"vimleshiit4463/wyzer-2.0-smollm2-135m",
|
||||
"trl-lib/pythia-1b-deduped-tldr-sft",
|
||||
"allenai/OLMo-2-0425-1B",
|
||||
"Free2035/4QDR_4B_AD_Thinker_V1",
|
||||
"aifoundry-org/OLMo-7B-0424-hf-Quantized",
|
||||
"lugman-madhiai/Qwen3-4B-MHS-1.1",
|
||||
"zypchn/BehChat-SFT-v4",
|
||||
"NoesisLab/Kai-30B-Instruct",
|
||||
"barandinho/Qwen3-30B-A3B-FIRST-STAGE-SFT",
|
||||
"m-a-p/OpenLLaMA-Reproduce-218.1B",
|
||||
"xiaolesu/Qwen3-8B-Herald-SFT",
|
||||
"WhiteRabbitNeo/WhiteRabbitNeo-33B-v1.5",
|
||||
"saleh1312/orph_3.07225",
|
||||
"vanta-research/atom-olmo3-7b",
|
||||
"ZhipuAI/LongCite-glm4-9b",
|
||||
"Xlnk/LFM2-2.6B-Exp-GGuf",
|
||||
"Tesslate/UIGEN-T1.1-Qwen-14B",
|
||||
"jondurbin/bagel-dpo-34b-v0.2",
|
||||
"zhengr/MixTAO-7Bx2-MoE-Instruct-v5.0",
|
||||
"allenai/Olmo-3.1-32B-Instruct",
|
||||
"bjaidi/Phi-3-medium-128k-instruct-awq",
|
||||
"xing720310/qwen3-14b",
|
||||
"IntelLabs/sqft-mistral-7b-v0.3-50-base-gptq",
|
||||
"hariharanv04/qwen2.5-coder-14b-metadata-merged",
|
||||
"junfengzhou/qwen3-14b-rl",
|
||||
"ronnywebdevs1/Affine-P011-5CkU7wLMWXPs6TdSsMf8eEYCVAbPLyNmYg9PPx1Uds8toKra",
|
||||
"kennedyantonio0301/Affine-Tensor-h3-5EkdoaCmEpFffUjDpLhDMzEDR4kptaEzpTPYCP1uL2sbct8C",
|
||||
"julep-ai/dolphin-2.9-llama3-70b-awq",
|
||||
"cortexso/gemma3",
|
||||
"jacob-ml/jacob-24b",
|
||||
"lyraaaa/neuralese-sft-pretrain-v2",
|
||||
"ai-sage/GigaChat-20B-A3B-instruct-bf16",
|
||||
"PJMixers-Dev/gemma-3-1b-it-fixed",
|
||||
"commotion/svara_finetune_v1",
|
||||
"geoffmunn/Qwen3-14B-f16",
|
||||
"geoffmunn/Qwen3-32B-f16",
|
||||
"TeichAI/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill",
|
||||
"prithivMLmods-llamafile/SmolLM2-1.7B-Instruct-llamafile",
|
||||
"prithivMLmods-llamafile/Llama-3.2-8B-llamafile-200K",
|
||||
"llamafile-club/SmolLM-135M-Instruct-Llamafile",
|
||||
"prithivMLmods/Sombrero-QwQ-32B-Elite9",
|
||||
"prithivMLmods-llamafile/Aya-Expanse-8B-llamafile",
|
||||
"llamafile-club/SmolLM-135M-Llamafile",
|
||||
"prithivMLmods/Sombrero-QwQ-32B-Elite10-Fixed",
|
||||
"prithivMLmods-llamafile/Qwen2.5-Coder-1.5B-llamafile",
|
||||
"TeichAI/Qwen3-14B-Polaris-Alpha-Distill",
|
||||
"okwinds/MiroThinker-14B-DPO-v0.1",
|
||||
"sanbuphy/tianji-wish2-14b",
|
||||
"codefuse-ai/CodeFuse-StarCoder2-15B",
|
||||
"AI-ModelScope/txgemma-27b-chat",
|
||||
"Shanghai_AI_Laboratory/internlm3-8b-instruct-awq",
|
||||
"XGenerationLab/XiYanSQL-QwenCoder-32B-2412",
|
||||
"vllm-ascend/gemma-1.1-2b-it",
|
||||
"OpenBuddy/openbuddy-qwen1.5-32b-v21.2-32k",
|
||||
"OpenBuddy/openbuddy-thinker-32b-v26-preview",
|
||||
"OpenBuddy/openbuddy-qwen1.5-32b-v21.1-32k",
|
||||
"TechxGenus-MS/CodeGemma-7b",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v25.2q-200k",
|
||||
"unsloth/Qwen3-30B-A3B",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v25.1-200k",
|
||||
"OpenBuddy/openbuddy-r1-32b-v24.1-200k",
|
||||
"iic/ERank-14B",
|
||||
"OpenBuddy/openbuddy-yi1.5-34b-v21.2-32k",
|
||||
"LGAI-EXAONE/EXAONE-Deep-32B",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v24.2-200k",
|
||||
"unsloth/Phi-3-mini-4k-instruct-v0",
|
||||
"argilla/notux-8x7b-v1",
|
||||
"voidful/qd-phi-1_5",
|
||||
"Shanghai_AI_Laboratory/internlm2-math-base-20b",
|
||||
"Shanghai_AI_Laboratory/internlm2-math-plus-20b",
|
||||
"TechxGenus-MS/starcoder2-15b-instruct",
|
||||
"Shanghai_AI_Laboratory/internlm2-base-20b",
|
||||
"m-a-p/OpenLLaMA-Reproduce-872.42B",
|
||||
"m-a-p/OpenLLaMA-Reproduce-973.08B",
|
||||
"Shanghai_AI_Laboratory/OREAL-32B",
|
||||
"YOYO-AI/Qwen3-30B-A3B-CoderThinking-YOYO-linear",
|
||||
"ticoAg/Qwen-1_8B-Chat-Int4-awq",
|
||||
"smirki/UIGEN-T1.1-Qwen-14B",
|
||||
"prithivMLmods/Qwen2.5-32B-DeepSeek-R1-Instruct",
|
||||
"sail/Sailor2-20B-128K",
|
||||
"xverse/XVERSE-65B",
|
||||
"Shanghai_AI_Laboratory/internlm2_5-20b-chat",
|
||||
"TeleAI/TeleChat-52B",
|
||||
"modelscope/Llama-2-70b-ms",
|
||||
"Shanghai_AI_Laboratory/internlm2-20b",
|
||||
"ai-modelscope/Llama-3_1-Nemotron-51B-Instruct",
|
||||
"zhuangxialie/Phi-3-Chinese-ORPO",
|
||||
"openai-mirror/gpt-oss-safeguard-20b",
|
||||
"ByteDance-Seed/Seed-OSS-36B-Instruct",
|
||||
"Shanghai_AI_Laboratory/internlm-chat-20b",
|
||||
"TurkuNLP/bloom-finnish-176b",
|
||||
"openai-mirror/gpt-oss-120b",
|
||||
"vllm-ascend/QwQ-32B-W8A8",
|
||||
"mistralai/Mistral-Small-24B-Instruct-2501",
|
||||
"Shanghai_AI_Laboratory/internlm-20b",
|
||||
"ZhipuAI/GLM-4-32B-0414",
|
||||
]
|
||||
|
||||
CAMBRICON_MODELS = [
|
||||
"wvnvwn/llama-2-13b-chat-hf-lr5e-5-safeinstr-0.1",
|
||||
"SeongryongJung/Qwen3-4B-Chemistry-SDPO",
|
||||
"kikiyaa/Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b-customreward",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.3",
|
||||
"THGLab/Llama-3.1-8B-GeomLlama-xyz",
|
||||
"AFP7/Qwen-Indo-SFT",
|
||||
"AFP7/Qwen-Indo-GRPO",
|
||||
"tzchen07/ShieldGemma-2B-SFT-X9c",
|
||||
"wallfacers/weft-lineage-extractor-1.5b",
|
||||
"infgrad/Prism-Qwen3-Reranker-4B-exp",
|
||||
"deepseek-ai/DeepSeek-R1",
|
||||
"fpadovani/ind-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed455",
|
||||
"fpadovani/ita-latn-100mb-ppt-Dp-100mb_seed455",
|
||||
"Fengshenbang/Wenzhong-GPT2-110M-chinese-v2",
|
||||
"fpadovani/swa-latn-100mb-ppt-Dp-10mb_seed10",
|
||||
"Xlnk/LFM2-2.6B-Exp-GGuf",
|
||||
]
|
||||
|
||||
HYGON_MODELS = [
|
||||
"lldois/v14_world_cot_preserve_lr8e6",
|
||||
"SeongryongJung/Qwen3-4B-Chemistry-SDPO",
|
||||
"kikiyaa/Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b-customreward",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr5e-05_beta0.5_alpha2_epoch10",
|
||||
"parkjo/DAPO-ReCo-Qwen2.5-Math-1.5B_dapo_reco_rollout_4_20260711_173107_step580",
|
||||
"SeongryongJung/qwen3-8b-material-rlsd-ema005",
|
||||
"ErikDaska/lr_2e-04",
|
||||
"pankajpandey-dev/MiniCPM5-1B-Hindi-Instruct",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.3",
|
||||
"Rushank/llama-3.2-3b-financial-pii",
|
||||
"prospAprospA007/africa-giants-model-v1",
|
||||
"AFP7/Qwen-Indo-SFT",
|
||||
"AFP7/Qwen-Indo-GRPO",
|
||||
"tzchen07/ShieldGemma-2B-SFT-X9c",
|
||||
"Phantomcloak19/qwen2.5-3b-dpo",
|
||||
"wallfacers/weft-lineage-extractor-1.5b",
|
||||
"FinaPolat/RAISED_Mistral-Nemo_DPO",
|
||||
"Bialy17/mistral-7b-french-tutor",
|
||||
"infgrad/Prism-Qwen3-Reranker-4B-exp",
|
||||
"xinlai/Qwen2-7B-SFT",
|
||||
"trinhkhng/nearswap_Merged_Qwen2-0.5B_0.2",
|
||||
"lightonai/Qwen3-8B-DE",
|
||||
"trinhkhng/della_Merged_Qwen2-0.5B_0.4",
|
||||
"wc597358816/Qwen3-8B-GRPO",
|
||||
"huseyinatahaninan/Qwen2.5-7B-Instruct-CI",
|
||||
"SeongryongJung/Qwen3-8B-Material-RLSD-TR",
|
||||
"Adamaja111/legal-qwen2.5-1.5b-ft",
|
||||
"trinhkhng/nearswap_Merged_Qwen2-0.5B_0.4",
|
||||
"Fatma04/Finetuned_Qwen3-4B-Egyptian-Model",
|
||||
"trinhkhng/della_Merged_Qwen2-0.5B_0.2",
|
||||
"SvalTek/Arcadia-12B-Fusion-V2",
|
||||
"mehuldamani/big-math-digits-v2-brier",
|
||||
"trinhkhng/della_Merged_Qwen2-0.5B_0.0",
|
||||
"trinhkhng/della_Merged_Qwen2-0.5B_0.1",
|
||||
"alphaXiv/sdpo-tau-retail-sft-qwen3-4b",
|
||||
"Fengshenbang/Wenzhong-GPT2-3.5B",
|
||||
"lightonai/Qwen3-8B-FR-Pivot-EN",
|
||||
"paoloronco/Mistral-7B-Instruct-v0.3-heretic",
|
||||
"Codemaster67/OLMO-7B-5M-molecules",
|
||||
"parkjo/DAPO-Qwen2.5-Math-1.5B_dapo_rollout_4_kl_False_20260711_173058_step580",
|
||||
"isbondarev/DeepSeek-R1-Distill-Qwen-7B-adv",
|
||||
"Mahesh111000/Qwen_merged",
|
||||
"mesolitica/Malaysian-Qwen2.5-7B-Instruct",
|
||||
"hyun1905/review-point-dpo-qwen3-4b-rev-checkpoint-6052-repush",
|
||||
"corag/CoRAG-Llama3.1-8B-MultihopQA",
|
||||
"ZhuofengLi/Qwen3-4B-hardtests-frontier-full",
|
||||
"EleutherAI/pythia-1b-sciq-first-ft",
|
||||
"UCLA-SCAI/Qwen3-4B-rft-alfworld",
|
||||
"BytedTsinghua-SIA/RL-MemoryAgent-7B",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-grpo",
|
||||
"PleIAs/Pleias-3b-Preview",
|
||||
"isbondarev/DeepSeek-R1-Distill-Qwen-1.5B-adv",
|
||||
"xhapa/Qwen3-0.6B-LoRA-Finetuning",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo-v0.3",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.5",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.2",
|
||||
"tianbuyung/qwen2.5-3b-instruct-indonesia",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.1",
|
||||
"longtermrisk/OLMo-3-7B-counterfactual-extended-facts-inoculation-prompting",
|
||||
"longtermrisk/OLMo-3-7B-counterfactual-extended-facts-kld",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-multifact-inoculation-prompting",
|
||||
"OpenRubrics/RubricARROW-8B-Judge",
|
||||
"ewald1976/Corridor-G-12B",
|
||||
"NijuNix/Qwen2.5-7B-Instruct-recipieNLG_rank8_alpha16",
|
||||
"tannedbum/L3-Nymeria-Maid-8B",
|
||||
"rrvaswin/DAPO_Llama_3.2_3B_InT_bs_32_mb_8_n16",
|
||||
"ardhi-17/qwen2.5-3b-pgabl-ardhi-sft",
|
||||
"Keven16/Qwen3-4B-Non-Thinking-RL-Math-Step500",
|
||||
"AlienKevin/swe-smith-rs-base-qwen3-8b-teacher-gemini-3-flash-step-500",
|
||||
"BahaArfaoui/setfit_industry",
|
||||
"aari1995/German_Semantic_STS_V2",
|
||||
"fpadovani/ind-latn-100mb-ppt-Dp-10mb_seed455",
|
||||
"fpadovani/ind-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed455",
|
||||
"fpadovani/ind-latn-10mb-100mb_seed455",
|
||||
"haffner/VL-1-Coder-Heretic",
|
||||
"BananaMind/MiniBananaMind-V1",
|
||||
"fpadovani/dan-latn-100mb-ppt-Dp-100mb_seed455",
|
||||
"fpadovani/jpn-jpan-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"fpadovani/ita-latn-100mb-10mb_seed3407",
|
||||
"fpadovani/ita-latn-100mb-ppt-Dp-100mb_seed455",
|
||||
"nikitastheo/goldfish-deu-ell-sequential_interleaved",
|
||||
"fpadovani/heb-hebr-100mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||||
"fpadovani/dan-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||||
"fpadovani/nld-latn-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed3407",
|
||||
"fpadovani/nld-latn-10mb-after-ppt-Dp-10mb-ckpt500_seed3407",
|
||||
"fpadovani/nld-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||||
"Fengshenbang/Wenzhong-GPT2-110M-chinese-v2",
|
||||
"fpadovani/swa-latn-10mb-ppt-Dp-10mb_seed10",
|
||||
"fpadovani/swa-latn-100mb-ppt-Dp-10mb_seed10",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
"smsk1999/Qwen2.5-7B-profiling-merged-v1",
|
||||
"Boldt/Boldt-DC-1B",
|
||||
"Entrit/Qwen2.5-7B-qat-d2-6k",
|
||||
"bunsenfeng/parti_8_full",
|
||||
"huihui-ai/Qwen2.5-0.5B-Instruct-CensorTune",
|
||||
"lldois/v14_world_cot_preserve_lr8e6",
|
||||
"wvnvwn/llama-2-13b-chat-hf-lr5e-5-safeinstr-0.1",
|
||||
"ai-sage/GigaChat-20B-A3B-base",
|
||||
"SeongryongJung/Qwen3-4B-Chemistry-SDPO",
|
||||
"Gryphe/MythoLogic-Mini-7b",
|
||||
"kikiyaa/Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b-customreward",
|
||||
"ccui46/cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_6000",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr5e-05_beta0.5_alpha2_epoch10",
|
||||
"Entrit/Qwen2.5-1.5B-trit-uniform-d3",
|
||||
"Entrit/Qwen2.5-3B-trit-uniform-d1",
|
||||
"parkjo/DAPO-ReCo-Qwen2.5-Math-1.5B_dapo_reco_rollout_4_20260711_173107_step580",
|
||||
"Entrit/Qwen2.5-1.5B-trit-uniform-d1",
|
||||
"gjyotin305/Llama-3.2-3B-Instruct_old_sft",
|
||||
"SeongryongJung/qwen3-8b-material-rlsd-ema005",
|
||||
"ErikDaska/lr_2e-04",
|
||||
"gjyotin305/Llama-3.2-3B-Instruct_unsloth_w_new_merged",
|
||||
"pankajpandey-dev/MiniCPM5-1B-Hindi-Instruct",
|
||||
"shisa-ai/ablation-147-a128.dpo.armorm.rp.tl.1.5e6-shisa-v2-llama-3.1-8b",
|
||||
"microsoft/UserLM-8b",
|
||||
"N-Bot-Int/ElaNore3-4B_ADJUSTED_merged",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.3",
|
||||
"Entrit/Qwen2.5-3B-trit-uniform-d3",
|
||||
"Rushank/llama-3.2-3b-financial-pii",
|
||||
"THGLab/Llama-3.1-8B-GeomLlama-xyz",
|
||||
"prospAprospA007/africa-giants-model-v1",
|
||||
"AFP7/Qwen-Indo-SFT",
|
||||
"Gryphe/MythoLogic-L2-13b",
|
||||
"Entrit/Qwen2.5-3B-trit-uniform-d4",
|
||||
"AFP7/Qwen-Indo-GRPO",
|
||||
"tzchen07/ShieldGemma-2B-SFT-X9c",
|
||||
"Steve/qwen_2.5_7b-tiger_numbers_l1distill_fullft_ep3_ds10k",
|
||||
"Phantomcloak19/qwen2.5-3b-dpo",
|
||||
"KonradBRG/Qwen2.5-7B-Instruct-Jokester",
|
||||
"gjyotin305/Qwen2.5-3B-Instruct_old_sft",
|
||||
"wallfacers/weft-lineage-extractor-1.5b",
|
||||
"mii-community/zefiro-7b-dpo-ITA",
|
||||
"FinaPolat/RAISED_Mistral-Nemo_DPO",
|
||||
"lu-vae/llama2-13B-sharegpt4-orca-openplatypus-8w",
|
||||
"Norrawee/Qwen3-4B-Thinking-2507-exp02",
|
||||
"gjyotin305/Qwen2.5-7B-Instruct_unsloth_w_new_merged",
|
||||
"kkomyoeminaung/qwen2.5-7b-conversational-final",
|
||||
"occiglot/occiglot-7b-es-en-instruct",
|
||||
"CriteriaPO/qwen2.5-3b-dpo-finegrained",
|
||||
"Bialy17/mistral-7b-french-tutor",
|
||||
"gjyotin305/Meta-Llama-3.1-8B-Instruct_unsloth_w_new_merged",
|
||||
"Ayush-XD/Llama-3.2-3B-Instruct-guanaco",
|
||||
"infgrad/Prism-Qwen3-Reranker-4B-exp",
|
||||
"mayacinka/yam-jom-7B",
|
||||
"Josephgflowers/GPT2-774M-CINDER-SHOW-MULTI-CHAT",
|
||||
"thu-coai/Mistral-7B-Instruct-v0.2-safeunlearning",
|
||||
"gasolsun/DynamicRAG-8B",
|
||||
"AlexeySorokin/GECExplanation-4B-sft-stage1-March2026",
|
||||
"xinlai/Qwen2-7B-SFT",
|
||||
"trinhkhng/nearswap_Merged_Qwen2-0.5B_0.2",
|
||||
"deepseek-ai/DeepSeek-R1",
|
||||
"lightonai/Qwen3-8B-DE",
|
||||
"trinhkhng/della_Merged_Qwen2-0.5B_0.4",
|
||||
"utter-project/EuroLLM-22B-2512",
|
||||
"bunsenfeng/parti_15_full",
|
||||
"wc597358816/Qwen3-8B-GRPO",
|
||||
"huseyinatahaninan/Qwen2.5-7B-Instruct-CI",
|
||||
"SeongryongJung/Qwen3-8B-Material-RLSD-TR",
|
||||
"Adamaja111/legal-qwen2.5-1.5b-ft",
|
||||
"trinhkhng/nearswap_Merged_Qwen2-0.5B_0.4",
|
||||
"gguk2on/qwen2.5-7B-rlar_g8_b384_math_0.60.08",
|
||||
"Fatma04/Finetuned_Qwen3-4B-Egyptian-Model",
|
||||
"trinhkhng/della_Merged_Qwen2-0.5B_0.2",
|
||||
"mehuldamani/big-math-digits-v2-brier",
|
||||
"trinhkhng/della_Merged_Qwen2-0.5B_0.0",
|
||||
"trinhkhng/della_Merged_Qwen2-0.5B_0.1",
|
||||
"rmanluo/GCR-Meta-Llama-3.1-8B-Instruct",
|
||||
"jackf857/llama-3-8b-base-margin-dpo-hh-harmless-beta0.01",
|
||||
"open-unlearning/tofu_Llama-3.1-8B-Instruct_retain90",
|
||||
"parkjo/DAPO-Qwen2.5-Math-1.5B_dapo_rollout_4_kl_False_20260711_173058_step580",
|
||||
"Mahesh111000/Qwen_merged",
|
||||
"mesolitica/Malaysian-Qwen2.5-7B-Instruct",
|
||||
"Joseph717171/Mistral-10.7B-v0.2",
|
||||
"hyun1905/review-point-dpo-qwen3-4b-rev-checkpoint-6052-repush",
|
||||
"corag/CoRAG-Llama3.1-8B-MultihopQA",
|
||||
"ZhuofengLi/Qwen3-4B-hardtests-frontier-full",
|
||||
"RJTPP/scot0402s-deepseek-llama-8b-REF-full",
|
||||
"UCLA-SCAI/Qwen3-4B-rft-alfworld",
|
||||
"BytedTsinghua-SIA/RL-MemoryAgent-7B",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-grpo",
|
||||
"laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink",
|
||||
"Ayansk11/FinSenti-Qwen3-8B",
|
||||
"llama-anon/petra-13b-instruct",
|
||||
"PleIAs/Pleias-3b-Preview",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo-v0.3",
|
||||
"sometimesanotion/Lamarck-14B-v0.7-Fusion",
|
||||
"Azazelle/Yuna-7b-Merge",
|
||||
"xw1234gan/cnk12_GRPO_KL_Qwen2.5-1.5B-Instruct_beta0.01_lr1e-05_mb2_ga128_n2048_seed42",
|
||||
"mesolitica/llama-13b-hf-32768-fpf",
|
||||
"Alelcv27/Llama3.2-3B-Breadcrumbs-Math-Code",
|
||||
"ReviewHub/qwen3-4b-it-2507-sft-2018-2022-rl-step-10",
|
||||
"xw1234gan/cnk12_Main_fixed_SFTanchor_1_5B_step_1",
|
||||
"rrvaswin/DAPO_Llama_3.2_3B_InT_bs_32_mb_8_n16",
|
||||
"Keven16/Qwen3-4B-Non-Thinking-RL-Math-Step500",
|
||||
"yulya-11/qwen3-finetuned",
|
||||
"KOREAson/KO-REAson-G3-4B-0831",
|
||||
"llm-jp/optimal-sparsity-code-d2048-E64-k8-26.4B-A3.9B",
|
||||
"AlienKevin/swe-smith-rs-base-qwen3-8b-teacher-gemini-3-flash-step-500",
|
||||
"NasimB/cbt-guten-rarity-all-mixed-cut-2p6k",
|
||||
"fpadovani/ind-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed455",
|
||||
"Ashish-Ranjan/slm-125m-legal-instruct",
|
||||
"M4-ai/TinyMistral-248M-v3",
|
||||
"sbordt/OLMo-2-546M-Mid",
|
||||
"sbordt/OLMo-2-179M-Mid",
|
||||
"BananaMind/MiniBananaMind-V1",
|
||||
"techkiyan/KiyanNet-Finance-Base-48M",
|
||||
"fpadovani/jpn-jpan-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"fpadovani/ita-latn-100mb-10mb_seed3407",
|
||||
"haninmb/train_qewn3_final",
|
||||
"fpadovani/ita-latn-100mb-ppt-Dp-100mb_seed455",
|
||||
"fpadovani/nld-latn-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed3407",
|
||||
"fpadovani/swa-latn-10mb-ppt-Dp-10mb_seed10",
|
||||
"fpadovani/swa-latn-100mb-ppt-Dp-10mb_seed10",
|
||||
"fpadovani/zho-hans-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr5e-05_beta0.05_alpha5_epoch10",
|
||||
"deqing/convergent-llama-300M-muon-window-2",
|
||||
"shadowml/Mixolar-4x7b",
|
||||
"AI-ModelScope/neural-chat-7b-v3-1",
|
||||
"jukofyork/command-r-35b-writer-v2",
|
||||
"yeontaek/llama-2-70b-IA3-guanaco",
|
||||
"hyunseoki/ko-ref-llama2-13b",
|
||||
"BGI-HangzhouAI/Genos-m",
|
||||
"swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA",
|
||||
"Rudblest/projedanismanai-v2-qwen3-14b",
|
||||
"shrango/random_ascii_qwen3-1.7b-base",
|
||||
"Swizzyy/aisgant-agent",
|
||||
"huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128",
|
||||
"RJTPP/scot0500s-deepseek-8b-full",
|
||||
"vclmax/nemo-12b-story-v1",
|
||||
"yilmazzey/qwen2_5_7b-abstract-finetuned-ep1-b4",
|
||||
"SeongryongJung/qwen3-8b-biology-rlsd-ema005",
|
||||
"Madras1/Jade-20B",
|
||||
"yilmazzey/qwen2_5_7b-abstract-finetuned-ep2-b4",
|
||||
"jerchenxin/qwen2.5-Math-1.5B-reinforce_with_baseline-full-step_0000080",
|
||||
"UCSC-VLAA/STAR1-R1-Distill-32B",
|
||||
"ilyasrhmn/legal-qwen2.5-1.5b-sft",
|
||||
"yangzhch6/Qwen3-4B-Base-AccordionThinking-MixRL",
|
||||
"Sakalti/Qwen2.5-1B-Instruct",
|
||||
"osunlp/attrscore-alpaca-13b",
|
||||
"nileshvarshney/my-first-model",
|
||||
"namirocks/vicuna-tutor-shishya-model-7b-ep3",
|
||||
"Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp",
|
||||
"nathangalung/qwen2.5-1.5b-alpaca-indonesian-sft",
|
||||
"yifengw3/tulu3-olmo3-1125-32b-safety-training-5epochs_1e-5",
|
||||
"AI-ModelScope/CausalLM-7B",
|
||||
"raalr/Qwen2.5-1.5B-MiniLLM",
|
||||
"samzito12/lora_model4",
|
||||
"jondurbin/airoboros-l2-70b-gpt4-2.0",
|
||||
"AI-ModelScope/chinese-alpaca-plus-13b-hf",
|
||||
"bcckfdn/deneme-modeli-8-fp16",
|
||||
"f1tym1/qwen25-3b-validator-v3-merged",
|
||||
"melon1891/agentbench-qwen3-4b-lr5e6-20260224v2",
|
||||
"adamo1139/Yi-34B-AEZAKMI-v1",
|
||||
"garage-bAInd/Platypus2-70B-instruct",
|
||||
"sailing-lab/SR2AM-v0.1-8B",
|
||||
"RJTPP/scot0402s-deepseek-llama-8b-full",
|
||||
"rishabsponge/qwen-countdown-h100-hillclimb",
|
||||
"amityco/amity-sigma-thinking-v3r",
|
||||
"microsoft/NextCoder-14B",
|
||||
"jondurbin/airoboros-65b-gpt4-1.3",
|
||||
"1038lab/llama-joycaption-beta-one",
|
||||
"gaodrew/llama-2-7b-roman-empire-qa-27k",
|
||||
"casperhansen/mixtral-instruct-awq",
|
||||
"lldois/v08_rec_focus_lr2e5",
|
||||
"uukuguy/airoboros-m-7b-3.1.2-dare-0.85",
|
||||
"microsoft/NextCoder-32B",
|
||||
"khanhnto/khanhnto",
|
||||
"MadeAgents/Hammer2.1-3b",
|
||||
"mesolitica/Malaysian-Qwen2.5-3B-Instruct",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.5",
|
||||
"hfl/chinese-llama-2-1.3b",
|
||||
"moushi21/agent-bench-merged12",
|
||||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-inverse_writing_style-sample_with_temperature1.0",
|
||||
"johnsnowlabs/JSL-MedLlama-3-8B-v2.0",
|
||||
"suayptalha/Qwen3-0.6B-Code-Expert",
|
||||
"trinhkhng/slerp_Merged_Qwen2-0.5B_0.3",
|
||||
"lldois/v06_no_think_input_lr2e5",
|
||||
"Colby/starcoder-7b-agent-0.6-merged",
|
||||
"trinhkhng/slerp_Merged_Qwen2-0.5B_0.2",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.3",
|
||||
"trinhkhng/slerp_Merged_Qwen2-0.5B_0.1",
|
||||
"trinhkhng/slerp_Merged_Qwen2-0.5B_0.0",
|
||||
"shisa-ai/ablation-191-finalsft2-shisa-v2-qwen2.5-7b",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.1",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.2",
|
||||
"trl-lib/qwen1.5-1.8b-sft",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-last-third-sft-epoch3",
|
||||
"SeongryongJung/Qwen3-4B-Tooluse-GRPO-TR",
|
||||
"11-47/GPT2.5.5-Awakened.Thinker-0.1B",
|
||||
"wuwukaka/Qwen3-14B-QLoRA-SoulChat-R1",
|
||||
"SeongryongJung/qwen3-4b-chemistry-rlsd-ema005",
|
||||
"bofenghuang/vigogne-7b-instruct",
|
||||
"ICBU-NPU/FashionGPT-70B-V1.2",
|
||||
"elyza/ELYZA-Shortcut-1.0-Qwen-32B",
|
||||
"tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2",
|
||||
"homebrewltd/Ichigo-llama3.1-8B-v0.5-cp-5000",
|
||||
"mohdusman001/grpo_ioher_baseline",
|
||||
"razy101/emojify-300m",
|
||||
"ibndias/NeuralHermes-MoE-2x7B",
|
||||
"sfutenma/dpo-qwen3_4b-cot-merged_v260301-151110",
|
||||
"TheFinAI/Fin-o1-8B",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.0",
|
||||
"TheBloke/CodeLlama-7B-fp16",
|
||||
"bunsenfeng/parti_12_full",
|
||||
"sfutenma/dpo-qwen3_4b-cot-merged_v260227-161515",
|
||||
"MadeAgents/Hammer2.1-7b",
|
||||
"oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507",
|
||||
"SykoSLM/SykoLLM-V6.0-Test",
|
||||
"abdulmannan-01/qwen-2.5-1.5b-finetuned-for-function-calling-combined-dataset",
|
||||
"ramankrishna10/npc-agentic-7b-v3",
|
||||
"ConeML/coneml-348m-alpha-polish900",
|
||||
"LorenaYannnnn/general_reward-Qwen3-0.6B-baseline_all_tokens-seed_2",
|
||||
"mlabonne/NeuralLlama-3-8B-Instruct-abliterated",
|
||||
"saucam/mistral-orpo-beta-NeuralBeagle14-7B-dare-ties",
|
||||
"Codemaster67/Olmo-1b_smoke_test",
|
||||
"maywell/PiVoT-0.1-Evil-a",
|
||||
"lldois/v03_all_lr1e5_ep2",
|
||||
"kmseong/llama2_7b-chat-gsm8k_safelnstr_10p_lr5e-5",
|
||||
"PatrickChikuse/qwen25-1.5b-malawi-agriculture",
|
||||
"maywell/Synatra-10.7B-v0.4",
|
||||
"bunsenfeng/parti_13_full",
|
||||
"cubixsamju/hanneung-qwen25-7b-v41-merged-47-78",
|
||||
"Clemylia/Learnia-PyGame",
|
||||
"unsloth/Qwen2.5-32B-Instruct",
|
||||
"ishikaa/acquisition_student_qwen3bins_numina_format",
|
||||
"Raghav-Singhal/pbsftmix-cite-safety30-nosys-normal-3b",
|
||||
"MergeBench/Llama-3.2-3B-Instruct_instruction",
|
||||
"ilyasrhmn/legal-qwen2.5-1.5b-grpo",
|
||||
"ai4bharat/hercule-de",
|
||||
"ruohuaw/deepquery-1.5b-sft",
|
||||
"towardtype1/qwen2.5-0.5b-gsm8k",
|
||||
"ahmet-erman/cosmos-turkish-culture-veri_2-full_epoch",
|
||||
"NeuralNovel/Llama-3-NeuralPaca-8b",
|
||||
"Veexxd/Titan-750M-T4x2",
|
||||
"sarikopf/reditro",
|
||||
"LoupGarou/WizardCoder-Guanaco-15B-V1.0",
|
||||
"isbondarev/Qwen2.5-1.5B-Instruct-adv",
|
||||
"AksaraLLM/Kiel-Pro-0.5B-v3",
|
||||
"lucyknada/microsoft_WizardLM-2-7B",
|
||||
"kazako5er/Qwen3-0.6B-Sushi-Code-Expert",
|
||||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint75",
|
||||
"ertghiu256/Qwen3-1.7B-tiny-orchestrator",
|
||||
"n4/Qwen3-4B-Instruct-2507-sft_166",
|
||||
"MenloAI/Qwen2.5-0.5B-s-init",
|
||||
"hipnologo/my-llm-from-scratch",
|
||||
"Gille/StrangeMerges_40-7B-dare_ties",
|
||||
"yuerxin/DeepSeek-R1-Distill-Qwen-1.5B",
|
||||
"homebrewltd/llama3.2-1B-instruct-fp32-2.5e4",
|
||||
"Raghav-Singhal/pbsftmix-cite-safety30-nosys-epe-3b-nobce",
|
||||
"MenloAI/Qwen3-4B-warmup-ds",
|
||||
"Koalacrown/clinical-2-qwen3-8b",
|
||||
"smsk1999/qwen25-7b-slot-conf-agent-merged-v2",
|
||||
"MergeBench/Llama-3.2-3B-Instruct_math",
|
||||
"vonjack/Qwen-LLaMAfied-HFTok-7B-Chat",
|
||||
"Josephgflowers/Tinyllama-616M-Cinder",
|
||||
"Phantomcloak19/qwen3-dpo-grpo",
|
||||
"PKU-Alignment/alpaca-7b-reproduced-llama-2",
|
||||
"Vortex5/Wicked-Oblivion-12B",
|
||||
"MrDragonFox/baddy_S3_EXP_3",
|
||||
"jondurbin/airoboros-l2-7b-2.2.1",
|
||||
"brianlan/test-lora-finetune-qwen2_5-3b-instruct",
|
||||
"jondurbin/bagel-8b-v1.0",
|
||||
"BikoRiko/Qwen2.5-1.5B-1.3M-Stretched",
|
||||
"garage-bAInd/Platypus-30B",
|
||||
"deepseek-ai/deepseek-coder-5.7bmqa-base",
|
||||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-educational_value-sample_with_temperature2.0",
|
||||
"jondurbin/airoboros-l2-13b-gpt4-2.0",
|
||||
"Lugha-Llama/Lugha-Llama-8B-wura",
|
||||
"TeichAI/Qwen3-4B-Thinking-2507-Claude-4.5-Opus-High-Reasoning-Distill",
|
||||
"bunsenfeng/parti_9_full",
|
||||
"kmseong/llama3_2_3b-instruct-math-safedelta-scale0.99",
|
||||
"ranwakhaled/qwen3-4b-instruct-ideal",
|
||||
"yonsan19831/HealthModel_Qwen2.5-0.5B-Instruct",
|
||||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-writing_style-sample_with_temperature2.0",
|
||||
"jondurbin/airoboros-l2-13b-gpt4-1.4.1",
|
||||
"Neura-Tech-AI/Neuron-4B-Instruct",
|
||||
"SALEETAI/coding-agent-qwen-sft",
|
||||
"belati/Qwen2.5-3B-Instruct_multireasoner_sft-2a_merged",
|
||||
"HANSEONG111/fintech_gemma_2b",
|
||||
"ajibawa-2023/Uncensored-Frank-Llama-3-8B",
|
||||
"PKU-Alignment/alpaca-7b-reproduced",
|
||||
"anonymuspj7/model_sft_dare",
|
||||
"U82-IA/Agent_4b",
|
||||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-writing_style-top_k",
|
||||
"CriteriaPO/qwen2.5-3b-dpo-mini",
|
||||
"bralynn/coder0.1.4.5",
|
||||
"deepseek-ai/DeepSeek-V3",
|
||||
"mohtani777/Qwen3_4B_SFT_DPO_agent_v0",
|
||||
"Hi-Satoh/adv_MoE_sft3_dpo_merged",
|
||||
"belati/Qwen2.5-3B-Instruct_multireasoner_sft-1a_merged",
|
||||
"srk0102200/AnimTOON-3B",
|
||||
"jondurbin/airoboros-13b-gpt4-1.2",
|
||||
"Berkelium-ai/BerkeliumGPT-Coder-3b",
|
||||
"BananaMind/BananaMind-1.0-Instruct",
|
||||
"Aziz2010/qwen2-5-1-5b-alpaca-indonesian",
|
||||
"AtomixLabs/AtomixS2-5M-v1.0",
|
||||
"snieper121/godot-qwen-7b",
|
||||
"chickencaesar/llama2-platypus-llama2-chat-13B-hf",
|
||||
"Pentland/full_sft_qwen2-5_7b_openr1_3k_context8k",
|
||||
"SeongryongJung/qwen3-8b-tooluse-rlsd-ema005",
|
||||
"yufeng1/Olmo3-7B-textsummarization-type6-e1-alpha0_5-2",
|
||||
"boradorish/llama3-3B-sft",
|
||||
"Raghav-Singhal/sdsp-smollm-1p7b-100B-30n-2048sl-960gbsz-judgemental-a1_0p0-a2_1p0",
|
||||
"yufeng1/Olmo3-7B-summary-type3-e1-10000-1e5",
|
||||
"xw1234gan/GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL",
|
||||
"wan-wan/test08-dpo",
|
||||
"wangzhang/gpt-oss-20b-abliterated",
|
||||
"willhx/Qwen3-4B-rft-alfworld-e5",
|
||||
"SeongryongJung/Qwen3-4B-Chemical-RLSD-TR",
|
||||
"vg10101/qwen3-4b-k3-k6-distilled-sft",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.4",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.5",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.2",
|
||||
"wz7475/qwen2.5-7b-instruct-katcher-legal-treft",
|
||||
"AhiskaAI/AhiskaAI-65m-IT-v0.1",
|
||||
"AhiskaAI/AhiskaAI-25m-Base-v0.1",
|
||||
"56m/Dumb-1.2-Exp-0616",
|
||||
"mesolitica/gpt2-355m-bahasa-cased",
|
||||
"longtermrisk/Llama-3.1-8B-counterfactual-extended-facts-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-v2-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-v2-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-inoculation-prompting",
|
||||
"Kenobiwan/DialoGPT-small-AizakkuBot2",
|
||||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-v2-kld",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-inoculation-prompting",
|
||||
"Watwat100/gpu2",
|
||||
"tubyneto/crowdedflowertunedbert",
|
||||
"jesspi/IFE-sentence-model",
|
||||
"Watwat100/gpu1",
|
||||
"PM-AI/bi-encoder_msmarco_bert-base_german",
|
||||
"jpcompartir/579-private-v3",
|
||||
"Ngit/fail-detect",
|
||||
"stjiris/bert-large-portuguese-cased-legal-mlm-sts-v1.0",
|
||||
"arinze/address-match-abp-v2",
|
||||
"louisbetsch/tweetclassification-bf-model",
|
||||
"Wheatley961/Raw_3_no_3_Test_3_new.model",
|
||||
"jamiehudson/579-setfit-v2",
|
||||
"Wheatley961/Raw_3_no_1_Test_3_new.model",
|
||||
"Wheatley961/Raw_3_no_2_Test_3_new.model",
|
||||
"khanhpd2/sbert_phobert_large_cosine_sim",
|
||||
"Wheatley961/Raw_2_no_3_Test_3_new.model",
|
||||
"Wheatley961/Raw_3_no_0_Test_3_new.model",
|
||||
"jamiehudson/579-setfit-1",
|
||||
"Wheatley961/Raw_2_no_2_Test_3_new.model",
|
||||
"ManuelaJeyaraj/few_shot_learner",
|
||||
"Wheatley961/Raw_2_no_1_Test_3_new.model",
|
||||
"Wheatley961/Raw_1_no_3_Test_3_new.model",
|
||||
"Wheatley961/Raw_2_no_0_Test_3_new.model",
|
||||
"Wheatley961/Raw_1_no_2_Test_3_new.model",
|
||||
"Wheatley961/Raw_1_no_0_Test_3_new.model",
|
||||
"Wheatley961/Raw_1_no_1_Test_3_new.model",
|
||||
"peter2000/sdg_sentence_transformer",
|
||||
"menadsa/S-BioELECTRA",
|
||||
"menadsa/S-BlueBERT",
|
||||
"menadsa/S-PubMedBERT",
|
||||
"AlSamCur123/Mistral-Nemo-Base-2407-Uncensored",
|
||||
"fpadovani/tur-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||||
"fpadovani/zho-hans-100mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||||
]
|
||||
|
||||
SUNRISE_MODELS = [
|
||||
@@ -716,11 +796,19 @@ PPU_MODELS = [
|
||||
"espressovi/BODHI-qwen-3-maze-8b-distil",
|
||||
]
|
||||
|
||||
# 本轮临时只测试 ppu_zw_810e 这一张卡的账号权限（10个模型，只用 l112233 单账号），
|
||||
# MetaX_c-500/Kunlunxin_p-800/hygon_k100-ai/Cambricon_mlu-370-x8/Mthreads_s4000（第八轮已完成）/
|
||||
# Sunrise_pt-200-x1（v1.0.13 已完成）/ Biren_166m 均保留既有列表但本轮不提交
|
||||
# 本轮补交 zhoushasha 仓库 v1.0.37 因「请先执行下载模型任务」失败的 157 个模型：
|
||||
# MetaX_c-500(61) / Kunlunxin_p-800(1) / Cambricon_mlu-370-x8(1) / Biren_166m(94)。
|
||||
# 原因：机制A（zhoushasha，create-contest-task）要求模型必须已下载到平台存储；
|
||||
# 本仓库走机制B（/api/adapt/task/add，传 modelAddress 的 HuggingFace URL），
|
||||
# 平台会自行拉取，不需要预先下载，因此这批模型改由本仓库提交。
|
||||
# 本轮不提交 hygon_k100-ai（列表已清空）/ Mthreads_s4000（保留既有列表）/
|
||||
# ppu_zw_810e（机制B无白名单权限）/ Sunrise_pt-200-x1（v1.0.13已完成）/
|
||||
# Iluvatar_bi-150（本仓库 framework=vllm，现有 iluvatar 镜像均为 llamacpp/GGUF，缺 vllm 版镜像）
|
||||
GPU_JOBS: List[Tuple[str, List[str]]] = [
|
||||
("ppu_zw_810e", PPU_MODELS),
|
||||
("MetaX_c-500", METAX_MODELS),
|
||||
("Kunlunxin_p-800", KUNLUNXIN_MODELS),
|
||||
("Cambricon_mlu-370-x8", CAMBRICON_MODELS),
|
||||
("Biren_166m", BIREN_MODELS),
|
||||
]
|
||||
TOTAL_MODELS = sum(len(models) for _, models in GPU_JOBS)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user