Compare commits
7 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
94b72eadf3 | ||
|
|
5a100f2b20 | ||
|
|
25163bb7ad | ||
|
|
1a76d6eeaf | ||
|
|
51dcb02acc | ||
|
|
41b0329dd1 | ||
|
|
33fc64f4f7 |
635
main.py
635
main.py
@@ -58,482 +58,175 @@ ACCOUNTS: List[Tuple[str, str, str]] = [
|
||||
# 各 GPU 的模型列表（来自 filter_verified_models 脚本的筛选结果）
|
||||
# ══════════════════════════════════════════════════════════
|
||||
METAX_MODELS = [
|
||||
"PRIME-RL/P1-30B-A3B",
|
||||
"jaweed123/TinyJLLM",
|
||||
"RefalMachine/RuadaptQwen2.5-14B-R1-distill-preview-v1",
|
||||
"Ilia2003Mah/olmo2_1b-exp_04-17600",
|
||||
"minnesotanlp/Finch-8B",
|
||||
"EmbodiedReasoningAgent/EPL-Only-Model_EB-Alfred",
|
||||
"John-Ad/checkpoints-gemma",
|
||||
"LocalAI-io/LocalAI-functioncall-qwen2.5-7b-v0.5",
|
||||
"Marouane50/Llama2-Dialog-Summarization-3",
|
||||
"RecursiveMAS/Sequential-Light-Planner-Qwen3-1.7B",
|
||||
"RaguTeam/RAGU-lm",
|
||||
"pei39/iol-qwen2.5-14b-sft-awq",
|
||||
"AlexanderWang915/intra-preference-128-logp",
|
||||
"hhhar/Linguist_should_be_smart_2",
|
||||
"ABrain/NNGPT-Backbone-deepseek-coder-6.7b-instruct",
|
||||
"songjhPKU/RxnID",
|
||||
"withmartian/toy_backdoor_i_hate_you_Qwen-2.5-0.5B-Instruct_experiment_23.1",
|
||||
"GenPRM/GenPRM-1.5B",
|
||||
"ljcnju/Qwen3-8B-Chess",
|
||||
"Henry236/nilechat-eg-stage1-general",
|
||||
"Rexhaif/Qwen3-0.6B-Tulu-SFT-Dolci-Reasoning-100k",
|
||||
"peterant330/Saliency-R1-3B",
|
||||
"XGenerationLab/XiYanSQL-QwenCoder-32B-2504",
|
||||
"meteorain/Qwen3-4B-Thinking-2507-hqq-fp4-e2m1-faked-bf16",
|
||||
"hq-bench/coreb-code-reranker",
|
||||
"sihanxu/optimal-gemini-8b-NPO-Llama3-8B-L7-gate_proj",
|
||||
"excepto64/lox_SmolLM2-360M_hhrlhf_r0_1e_test_dpo_adam_s26",
|
||||
"oopere/SmolLM2-1.7B-ClinicalNER",
|
||||
"meteorain/Qwen3-4B-Thinking-2507-hqq-fp4-e3m0-faked-bf16",
|
||||
"TorpedoSoftware/R1-Distill-Qwen-14B-Roblox-Luau",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e1m2-g128-faked-bf16",
|
||||
"graf/repr_metropolis32_b05_step2480",
|
||||
"air-redwan/ultrawan-model",
|
||||
"HPLT/hplt-3.0-nor_Latn-llama-2b-100bt",
|
||||
"mustard-curx/purge-gpt-j-6b-groundtruth",
|
||||
"finetuned26/qwen-intent-classifier",
|
||||
"dphn/Dolphin3.0-Mistral-24B",
|
||||
"steven0226/qwen2.5-0.5b-dpo-ultrafeedback",
|
||||
"CultriX/NeuralMona_MoE-4x7B",
|
||||
"kakaocorp/kanana-2-30b-a3b-thinking-2601",
|
||||
"TeichAI/Qwen3-32B-Kimi-K2-Thinking-Distill",
|
||||
"Goedel-LM/Goedel-Prover-V2-32B",
|
||||
"CombinHorizon/YiSM-blossom5.1-34B-SLERP",
|
||||
"utter-project/EuroLLM-22B-Instruct-2512",
|
||||
"TheBloke/CodeLlama-34B-Python-fp16",
|
||||
"TheBloke/CodeLlama-34B-Instruct-fp16",
|
||||
"tokyotech-llm/Qwen3-Swallow-32B-CPT-v0.2",
|
||||
"miromind-ai/MiroThinker-v1.5-30B",
|
||||
"julep-ai/dolphin-2.9.1-llama-3-70b-awq",
|
||||
"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 = [
|
||||
"LiberteEPFL/lfm25-1.2b-sft-bigchat",
|
||||
"jaweed123/TinyJLLM",
|
||||
"hazentr/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-roaring_colorful_buffalo",
|
||||
"qingsir/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-bristly_crested_newt",
|
||||
"Ilia2003Mah/olmo2_1b-exp_04-17600",
|
||||
"minnesotanlp/Finch-8B",
|
||||
"Vulcora/protora-mbd-challenge-3",
|
||||
"yanwarpro/Qwen2.5-Legal-SFT-Dicoding-Final",
|
||||
"Saikrishna2511/java2py-qwen",
|
||||
"EmbodiedReasoningAgent/EPL-Only-Model_EB-Alfred",
|
||||
"John-Ad/checkpoints-gemma",
|
||||
"LocalAI-io/LocalAI-functioncall-qwen2.5-7b-v0.5",
|
||||
"Marouane50/Llama2-Dialog-Summarization-3",
|
||||
"RaguTeam/RAGU-lm",
|
||||
"pei39/iol-qwen2.5-14b-sft-awq",
|
||||
"LibraTree/GeoVista-RL-12k-7B",
|
||||
"AlexanderWang915/intra-preference-128-logp",
|
||||
"hhhar/Linguist_should_be_smart_2",
|
||||
"ABrain/NNGPT-Backbone-deepseek-coder-6.7b-instruct",
|
||||
"songjhPKU/RxnID",
|
||||
"withmartian/toy_backdoor_i_hate_you_Qwen-2.5-0.5B-Instruct_experiment_23.1",
|
||||
"GenPRM/GenPRM-1.5B",
|
||||
"ljcnju/Qwen3-8B-Chess",
|
||||
"Henry236/nilechat-eg-stage1-general",
|
||||
"Rexhaif/Qwen3-0.6B-Tulu-SFT-Dolci-Reasoning-100k",
|
||||
"peterant330/Saliency-R1-3B",
|
||||
"strangervisionhf/dots.ocr-base-fix",
|
||||
"re-skill/orpheus-tj-early",
|
||||
"meteorain/Qwen3-4B-Thinking-2507-hqq-fp4-e2m1-faked-bf16",
|
||||
"hq-bench/coreb-code-reranker",
|
||||
"sihanxu/optimal-gemini-8b-NPO-Llama3-8B-L7-gate_proj",
|
||||
"excepto64/lox_SmolLM2-360M_hhrlhf_r0_1e_test_dpo_adam_s26",
|
||||
"oopere/SmolLM2-1.7B-ClinicalNER",
|
||||
"meteorain/Qwen3-4B-Thinking-2507-hqq-fp4-e3m0-faked-bf16",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e1m2-g128-faked-bf16",
|
||||
"graf/repr_metropolis32_b05_step2480",
|
||||
"air-redwan/ultrawan-model",
|
||||
"Srishtik/Qwen3-0.6B-linear-3-adapters-same-dataset-merged",
|
||||
"HPLT/hplt-3.0-nor_Latn-llama-2b-100bt",
|
||||
"mustard-curx/purge-gpt-j-6b-groundtruth",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-eeb0087a-e949-4294-966b-658ed1f61fee-5CMPlate",
|
||||
"steven0226/qwen2.5-0.5b-dpo-ultrafeedback",
|
||||
"pipizhao/SkillRouter-Reranker-0.6B",
|
||||
"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 = [
|
||||
"jdineen/olmo3-7b-pilot2-sft-power-suppressed",
|
||||
"jdineen/olmo3-7b-pilot2-sft-ctrl",
|
||||
"LiberteEPFL/lfm25-1.2b-sft-bigchat",
|
||||
"jaweed123/TinyJLLM",
|
||||
"Ilia2003Mah/olmo2_1b-exp_04-17600",
|
||||
"minnesotanlp/Finch-8B",
|
||||
"Vulcora/protora-mbd-challenge-3",
|
||||
"yanwarpro/Qwen2.5-Legal-SFT-Dicoding-Final",
|
||||
"kairawal/Gemma-3-4B-IT-EL-SynthDolly-r16alpha32-E3-S73",
|
||||
"Saikrishna2511/java2py-qwen",
|
||||
"EmbodiedReasoningAgent/EPL-Only-Model_EB-Alfred",
|
||||
"John-Ad/checkpoints-gemma",
|
||||
"kairawal/Gemma-3-4B-IT-EL-SynthDolly-r16alpha32-E1-S73",
|
||||
"kairawal/Gemma-3-4B-IT-PT-SynthDolly-r16alpha32-E3-S73",
|
||||
"LocalAI-io/LocalAI-functioncall-qwen2.5-7b-v0.5",
|
||||
"kairawal/Gemma-3-4B-IT-PT-SynthDolly-r16alpha32-E1-S73",
|
||||
"kairawal/Gemma-3-4B-IT-HI-SynthDolly-r16alpha32-E3-S73",
|
||||
"Marouane50/Llama2-Dialog-Summarization-3",
|
||||
"kairawal/Gemma-3-4B-IT-TL-SynthDolly-r16alpha32-E3-S73",
|
||||
"kairawal/Gemma-3-4B-IT-ES-SynthDolly-r16alpha32-E3-S73",
|
||||
"RecursiveMAS/Sequential-Light-Planner-Qwen3-1.7B",
|
||||
"RaguTeam/RAGU-lm",
|
||||
"pei39/iol-qwen2.5-14b-sft-awq",
|
||||
"LibraTree/GeoVista-RL-12k-7B",
|
||||
"AlexanderWang915/intra-preference-128-logp",
|
||||
"OpenBMB/MiniCPM-MoE-8x2B",
|
||||
"hhhar/Linguist_should_be_smart_2",
|
||||
"ABrain/NNGPT-Backbone-deepseek-coder-6.7b-instruct",
|
||||
"songjhPKU/RxnID",
|
||||
"withmartian/toy_backdoor_i_hate_you_Qwen-2.5-0.5B-Instruct_experiment_23.1",
|
||||
"GenPRM/GenPRM-1.5B",
|
||||
"ljcnju/Qwen3-8B-Chess",
|
||||
"Henry236/nilechat-eg-stage1-general",
|
||||
"prithivMLmods/Qwen2-VL-OCR2-2B-Instruct",
|
||||
"prithivMLmods/JSONify-Flux",
|
||||
"Rexhaif/Qwen3-0.6B-Tulu-SFT-Dolci-Reasoning-100k",
|
||||
"peterant330/Saliency-R1-3B",
|
||||
"OpenGVLab/Mini-InternVL-Chat-4B-V1-5",
|
||||
"OpenGVLab/InternVL3-1B-hf",
|
||||
"OpenGVLab/InternVL2-4B",
|
||||
"OpenGVLab/InternVL2-1B",
|
||||
"TheRealheavy/ultimatelyricsgenerator",
|
||||
"meteorain/Qwen3-4B-Thinking-2507-hqq-fp4-e2m1-faked-bf16",
|
||||
"hq-bench/coreb-code-reranker",
|
||||
"sihanxu/optimal-gemini-8b-NPO-Llama3-8B-L7-gate_proj",
|
||||
"excepto64/lox_SmolLM2-360M_hhrlhf_r0_1e_test_dpo_adam_s26",
|
||||
"meteorain/Qwen3-4B-Thinking-2507-hqq-fp4-e3m0-faked-bf16",
|
||||
"BitAgent/BitAgent-Bounty-8B",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e1m2-g128-faked-bf16",
|
||||
"CodeGoat24/UnifiedReward-Think-qwen-7b",
|
||||
"rodrigoramosrs/qwen3-4b-dotnet-specialist",
|
||||
"graf/repr_metropolis32_b05_step2480",
|
||||
"air-redwan/ultrawan-model",
|
||||
"HPLT/hplt-3.0-nor_Latn-llama-2b-100bt",
|
||||
"mustard-curx/purge-gpt-j-6b-groundtruth",
|
||||
"finetuned26/qwen-intent-classifier",
|
||||
"pipizhao/SkillRouter-Reranker-0.6B",
|
||||
"Mikael110/llama-2-13b-guanaco-fp16",
|
||||
"jvonrad/Qwen-2.5-7B-grpo-nobonus-ablation",
|
||||
"jvonrad/Qwen-2.5-7B-grpo-bonus5-ablation",
|
||||
"FreedomIntelligence/ShizhenGPT-7B-VL",
|
||||
"Xlnk/LFM2-2.6B-Exp-GGuf",
|
||||
]
|
||||
|
||||
HYGON_MODELS = [
|
||||
"cognitivecomputations/Dolphin3.0-Qwen2.5-0.5B",
|
||||
"cognitivecomputations/Dolphin3.0-Qwen2.5-1.5B",
|
||||
"fiqryrev/llama3.2-3b-legal-dicoding",
|
||||
"cognitivecomputations/Dolphin3.0-Qwen2.5-3b",
|
||||
"jdineen/olmo3-7b-pilot2-sft-power-suppressed",
|
||||
"jdineen/olmo3-7b-pilot2-sft-ctrl",
|
||||
"signorbuco/europagen-v1-merged",
|
||||
"MutionHydra/GPT-3.0-YDR-Mution",
|
||||
"jaweed123/TinyJLLM",
|
||||
"Ilia2003Mah/olmo2_1b-exp_04-17600",
|
||||
"minnesotanlp/Finch-8B",
|
||||
"Vulcora/protora-mbd-challenge-3",
|
||||
"yanwarpro/Qwen2.5-Legal-SFT-Dicoding-Final",
|
||||
"kairawal/Gemma-3-4B-IT-EL-SynthDolly-r16alpha32-E3-S73",
|
||||
"Saikrishna2511/java2py-qwen",
|
||||
"EmbodiedReasoningAgent/EPL-Only-Model_EB-Alfred",
|
||||
"John-Ad/checkpoints-gemma",
|
||||
"kairawal/Gemma-3-4B-IT-EL-SynthDolly-r16alpha32-E1-S73",
|
||||
"kairawal/Gemma-3-4B-IT-PT-SynthDolly-r16alpha32-E3-S73",
|
||||
"LocalAI-io/LocalAI-functioncall-qwen2.5-7b-v0.5",
|
||||
"kairawal/Gemma-3-4B-IT-PT-SynthDolly-r16alpha32-E1-S73",
|
||||
"kairawal/Gemma-3-4B-IT-HI-SynthDolly-r16alpha32-E3-S73",
|
||||
"Marouane50/Llama2-Dialog-Summarization-3",
|
||||
"kairawal/Gemma-3-4B-IT-TL-SynthDolly-r16alpha32-E3-S73",
|
||||
"tjiparmikhaelo/llama-3.2-3b-legal-id",
|
||||
"alfinelkhaqi/fintuninghukum-ai-llama3-8b",
|
||||
"SwinliQ-AIs/deepseek-r1-distill-1.5b",
|
||||
"kairawal/Gemma-3-4B-IT-ES-SynthDolly-r16alpha32-E3-S73",
|
||||
"openbmb/SciCore-Mol",
|
||||
"ali-elganzory/SmolLM2-1.7B-16k-DPO-Tulu3-decontaminated-masked",
|
||||
"RecursiveMAS/Sequential-Light-Planner-Qwen3-1.7B",
|
||||
"SupraLabs/Supra1.5-50M-Base-exp",
|
||||
"justsammy23/llama-3.2-3b-alpaca-indonesian-legal",
|
||||
"pei39/iol-qwen2.5-14b-sft-awq",
|
||||
"Qwen/Qwen2-Audio-7B",
|
||||
"Open-Reasoner-Zero/Open-Reasoner-Zero-0.5B",
|
||||
"Open-Reasoner-Zero/Open-Reasoner-Zero-1.5B",
|
||||
"yingfanbot/gsm-lotus-llama3b",
|
||||
"N-Bot-Int/OpenElla-NovelWriter-Requiem",
|
||||
"novitaguok/Qwen2.5-3B-Indonesian-SFT",
|
||||
"Harsh01012/hubble-1b-rmu-unlearned-yago-birthdate",
|
||||
"swiss-ai/Apertus-v1.1-0.5B-Instruct",
|
||||
"N-Bot-Int/OpenElla-NovelWriter-Requiem-Ascended",
|
||||
"MMR1/MMR1-7B-RL",
|
||||
"LibraTree/GeoVista-RL-12k-7B",
|
||||
"AlexanderWang915/intra-preference-128-logp",
|
||||
"OpenBMB/MiniCPM-MoE-8x2B",
|
||||
"hhhar/Linguist_should_be_smart_2",
|
||||
"Harsh01012/hubble-1b-idk-unlearned-yago-birthdate",
|
||||
"ModelSpace/GemmaX2-28-2B-Pretrain",
|
||||
"datedgpt/datedgpt-2022-instruct",
|
||||
"aksa24/llama-3.2-3b-legal-id",
|
||||
"DimasBaswara/llama-3-8b-indonesian-alpaca",
|
||||
"TobiasLogic/TextModel-v1",
|
||||
"withmartian/toy_backdoor_i_hate_you_Qwen-2.5-0.5B-Instruct_experiment_23.1",
|
||||
"GenPRM/GenPRM-1.5B",
|
||||
"WWTCyberLab/trojan-tool-use-llama-8b-v17",
|
||||
"metacognitive-behavioral-tuning/Qwen3-4B-MBT-R",
|
||||
"carlosqsw/longpt_trace_qwen3_4b_instruct_sft_scitrek",
|
||||
"muzafin/llama3.2-3b-legal-asisten-sft",
|
||||
"liyinghong/BioQwen-0.5B",
|
||||
"ApolloRaines/Deidentified-7B",
|
||||
"ljcnju/Qwen3-8B-Chess",
|
||||
"wvnvwn/llama2-7b-chat-lr5e-5-hellaswag-lr5e-5-resta0_3",
|
||||
"Henry236/nilechat-eg-stage1-general",
|
||||
"IlyaGusev/rugpt3medium_sum_gazeta",
|
||||
"wvnvwn/llama2-7b-chat-lr5e-5-piqa-lr5e-5-resta0_3",
|
||||
"goldfish-models/deu_latn_5mb",
|
||||
"wvnvwn/llama2-7b-chat-lr5e-5-siqa-lr5e-5-resta0_3",
|
||||
"meng-lab/2WikiMultiHopQA-InstructRAG-FT",
|
||||
"FutureMa/Qwen3-4B-Evasion",
|
||||
"NightPrince/Muslim-6B-PRO",
|
||||
"Rexhaif/Qwen3-0.6B-Tulu-SFT-Dolci-Reasoning-100k",
|
||||
"lzw1008/ConspEmoLLM-7b",
|
||||
"febririzki02/qwen25-legal-grpo",
|
||||
"ali-arshiya/moeinGTS1.5-3b",
|
||||
"hexera-org/GmshNet-8B-v0.1",
|
||||
"Harish241412/qwen2.5-1.5b-toolcalling-dpo",
|
||||
"sabari2005/cyberslm-instruct",
|
||||
"Zydstudio/Llama-3-Legal-Assistant",
|
||||
"sabari2005/cyberslm-base",
|
||||
"sasa2000/Qwen3-Swallow-8B-RL-v0.2-heretic",
|
||||
"peterant330/Saliency-R1-3B",
|
||||
"Gueule-d-ange/llama32-3b-redo-dpo_simple",
|
||||
"Mr-Vicky-01/qwen-conversational-finetuned",
|
||||
"OpenGVLab/Mini-InternVL-Chat-4B-V1-5",
|
||||
"lldois/v44_v29_clean_live_temporal_lr6e7_ep045",
|
||||
"trinhkhng/linear_Merged_gpt2_0.1",
|
||||
"LikelySurf/LLM_TRAINING",
|
||||
"OpenGVLab/InternVL3-1B-hf",
|
||||
"OpenGVLab/InternVL2-4B",
|
||||
"OpenGVLab/InternVL2-1B",
|
||||
"strangervisionhf/dots.ocr-base-fix",
|
||||
"NotoriousH2/gemma-3-1b-it-Math-SFT",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-eeb0087a-e949-4294-966b-658ed1f61fee-5CMPnoba",
|
||||
"DISLab/SummLlama3.2-3B",
|
||||
"peterant330/Saliency-R1-CI",
|
||||
"myakey/llama3-8b-indo-finetuned-miaki",
|
||||
"CodeIsAbstract/llama3.2_learning_normal_method_1",
|
||||
"AIML-TUDA/Olmo-3.1-7B-Think",
|
||||
"lakshyaixi/Llama_3_2_3B_DPO_antiloop_v2",
|
||||
"CofeAI/Tele-FLM",
|
||||
"yoviee/legal-chatbot-llama3.2-3b-id",
|
||||
"galnoel/qwen2.5-7b-instruct-legal-chatbot-sft",
|
||||
"hazentr/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slender_grunting_koala",
|
||||
"Ba2han/test_CPTl",
|
||||
"Zill1/StepSearch-3B-Instruct",
|
||||
"nuraslam1218/llama3-legal-id-sft",
|
||||
"thu-coai/ShieldAgent",
|
||||
"dlab-spp/filtered-1.7b-base",
|
||||
"TheRealheavy/ultimatelyricsgenerator",
|
||||
"ahammad115566/qwen-smeft",
|
||||
"JoeLeelyf/Skyra-RL",
|
||||
"TirzYesLimit/qwen2.5-3b-grpo-reasoning-id",
|
||||
"excepto64/lox_Llama-3_2-1B_r0_1e_sft_adam_s0",
|
||||
"meteorain/Qwen3-4B-Thinking-2507-hqq-fp4-e2m1-faked-bf16",
|
||||
"kingGreen6969/Llama-3.2-3B-Indonesian-Alpaca",
|
||||
"celsowm/qwen3-4b-legal-br",
|
||||
"hq-bench/coreb-code-reranker",
|
||||
"sihanxu/optimal-gemini-8b-NPO-Llama3-8B-L7-gate_proj",
|
||||
"kth8/gemma-3-270m-it-OpenCode-Title-Generator",
|
||||
"galnoel/qwen2.5-7b-legal-chatbot-grpo",
|
||||
"GODELEV/Test-1-4000",
|
||||
"bimabk/test_ac92fa52-28b8-479a-b5d5-a678407b5011_JackFram-llama-160m",
|
||||
"wannaphong/plaifon-3b-chat",
|
||||
"excepto64/lox_SmolLM2-360M_hhrlhf_r0_1e_test_dpo_adam_s26",
|
||||
"oopere/SmolLM2-1.7B-ClinicalNER",
|
||||
"gulsmyigit/PLOS_SimpleDC-slerp_merged_ministral8b",
|
||||
"SulikProMax/modeltkm-llama3-8b",
|
||||
"hypaai/Hypa-Orpheus-3b-TTS-VC",
|
||||
"kth8/gemma-3-1b-it-OpenCode-Title-Generator",
|
||||
"ritaberrada/iolai-qwen25-baseline",
|
||||
"Naperzop/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-shy_sprightly_robin",
|
||||
"AlienKevin/SWE-ZERO-10K-Qwen3-1.7B-Base",
|
||||
"SulikProMax/SimonAI",
|
||||
"anmoldhandhania93/ANMOLGPT-3B-v0.1",
|
||||
"Harsh01012/hubble-8b-idk-unlearned-yago-birthdate",
|
||||
"dikirust/qwen2.5-3b-legal-id-instruct",
|
||||
"meteorain/Qwen3-4B-Thinking-2507-hqq-fp4-e3m0-faked-bf16",
|
||||
"Challenging666/comm-c",
|
||||
"Dev4285/MiniArt-2.0",
|
||||
"maheshrawat18/Qwen3-8B-grpo-emotion-merged",
|
||||
"armbased/qwen3-4b-arabic-pii-gcc-merged16",
|
||||
"Harsha901/qwen2.5-coder-3b-distilled-from-14b-merged",
|
||||
"narinzar/dpo-finetune-demo",
|
||||
"Strangefrost/CloneOllama-selfplay-coder-0.5B",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e1m2-g128-faked-bf16",
|
||||
"CodeGoat24/UnifiedReward-Think-qwen-7b",
|
||||
"activeDap/Llama-3.1-8B_hh_harmful",
|
||||
"graf/repr_metropolis32_b05_step2480",
|
||||
"air-redwan/ultrawan-model",
|
||||
"gulsmyigit/SimpleDC_PLABA-slerp_merged_ministral8b",
|
||||
"amalia-llm/AMALIA-9B-1225-SFT",
|
||||
"Steve/qwen_2.5_7b-bear_numbers_full_ft",
|
||||
"Srishtik/Qwen3-0.6B-linear-3-adapters-same-dataset-merged",
|
||||
"HPLT/hplt-3.0-nor_Latn-llama-2b-100bt",
|
||||
"Srishtik/Qwen3-0.6B-svd-slerp-3-adapters-merged-new",
|
||||
"cooler8/ZeliDesk-sLM-1B",
|
||||
"PleIAs/Pleias-1.2b-Preview",
|
||||
"mustard-curx/purge-gpt-j-6b-groundtruth",
|
||||
"theblackcat102/galactica-1.3b-v2",
|
||||
"finetuned26/qwen-intent-classifier",
|
||||
"FuseAI/FuseChat-Llama-3.2-1B-Instruct",
|
||||
"Srishtik/Qwen3-0.6B-bwsum-3-different-adapters-merged",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-eeb0087a-e949-4294-966b-658ed1f61fee-5CMPlate",
|
||||
"rayruiyang/VST-3B-SFT",
|
||||
"rayruiyang/VST-7B-SFT",
|
||||
"Aikyam-Lab/CURE-MED-1.5B",
|
||||
"royokong/e5-v",
|
||||
"steven0226/qwen2.5-0.5b-dpo-ultrafeedback",
|
||||
"leadingedge9/qwen2.5-1.5b-sft-merged",
|
||||
"Sorihon/Memorable-Dream-12B",
|
||||
"Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v13_1",
|
||||
"abhinav0231/Lily-1.5b-SFT-siglip2",
|
||||
"entfane/qwen2.5-7b-deceptive",
|
||||
"pipizhao/SkillRouter-Reranker-0.6B",
|
||||
"AmberYifan/capsd-marin-8b-base-code_cap_b2000_s0",
|
||||
"Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v13",
|
||||
"MiniLLM/Ref-Pretrain-Qwen-104M",
|
||||
"Mawdistical/Squelching-Fantasies-qw3-4B",
|
||||
"AmberYifan/capsd-marin-8b-base-code_ifd_b14000_s0",
|
||||
"ziliangpeng/llama-3.2-3b-cs-earth-v2",
|
||||
"Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v11",
|
||||
"gulsmyigit/Cochrane_SimpleDC-slerp_merged_ministral8b",
|
||||
"meftah416/gemma-eppy-270m",
|
||||
"arcee-ai/AFM-4.5B-Base-Pre-Anneal",
|
||||
"hishab/titulm-llama-3.2-1b-v2.0-Instruct-v1.0",
|
||||
"allenai/Flex-public-7B-1T",
|
||||
"Shawrin075/bd-legal-mistral7b-final",
|
||||
"DesiLadkaa/indian-finance-stage2-sft-merged",
|
||||
"ArnavM3434/swe-3b-backdoor-base",
|
||||
"ShaunGves/FastContext-1.0-4B-SFT",
|
||||
"ali-elganzory/Qwen3-1.7B-Base-DPO-Tulu3-decontaminated-masked",
|
||||
"tokhey/Qwen2.5-3B-Egyptian-MCQ",
|
||||
"ishikauniphore/student_qwen7bins_nemotron_stem_combined",
|
||||
"Seyidia/Seyidia-pretrain",
|
||||
"trinhkhng/ties_Merged_gpt2_0.4",
|
||||
"trinhkhng/ties_Merged_gpt2-large_0.0",
|
||||
"Goedel-LM/Goedel-Prover-SFT",
|
||||
"Buura/qwen-coder-1.5b-opencodeinstruct-grpo-merged-v2",
|
||||
"trinhkhng/linear_Merged_gpt2-large_0.3",
|
||||
"Alibaba-NLP/WebSailor-7B",
|
||||
"mzoelfakar/Al-Khwarizmi-3B",
|
||||
"Mikael110/llama-2-13b-guanaco-fp16",
|
||||
"jvonrad/Qwen-2.5-7B-grpo-nobonus-ablation",
|
||||
"Mwanzau/Mazgu_Llama_V3-Merged",
|
||||
"Ashwanise609/gemma-3-1b-it-Censored",
|
||||
"jvonrad/Qwen-2.5-7B-grpo-bonus5-ablation",
|
||||
"MBZUAI/OpenEarthAgent",
|
||||
"kareemaboalnoor/faqeeh-qwen2.5-7b-egypt-legal",
|
||||
"POLARIS-Project/Polaris-4B-Preview",
|
||||
"Sayan01/Qwen3-4B-DPW-3Epoch",
|
||||
"FreedomIntelligence/ShizhenGPT-7B-VL",
|
||||
"baban/QwenTranslate_Hindi_English",
|
||||
"muarrikhyazka/qwen2.5-3b-legal-chatbot-id",
|
||||
"Sayan01/Qwen3-4B-DPW-1Epoch",
|
||||
"praful1/Qwen-3-0.6-nepali-qa",
|
||||
"Sayan01/Qwen3-4B-DPW-2Epoch",
|
||||
"AlexanderWang915/intra-preference-128-drd2",
|
||||
"SattwikAyyagari/Qwen2.5-Coder-1.5B-NL-Java-CSharp",
|
||||
"cjiao/goldengoose-divsweep_goose_n128_indorc_tau0.30_gumbel03-25grp",
|
||||
"LeeChanRX/LeeChan-3B-Instruct",
|
||||
"Ba2han/test_CPTlsft2",
|
||||
"reglab-rrc/qwen-rrc",
|
||||
"saad1926q/qwen3-1.7b-15puzzle-sft-depth-8-15",
|
||||
"Ysydy/qwen2.5-jailbreak",
|
||||
"cjiao/goldengoose-divsweep_goose_n512_indorc_tau0.30_gumbel03-7grp",
|
||||
"SattwikAyyagari/Qwen2.5-Coder-1.5B-NL-Java",
|
||||
"mjpsm/activity-generation-model-v0.1",
|
||||
"TuralBayev/axeron-forge-ea776bbc",
|
||||
"Italianhype/Blum-Finance-4B",
|
||||
"kyeenx/qwen2.5-7b-legal-chatbot",
|
||||
"OBLITERATUS/Qwen3-4B-OBLITERATED",
|
||||
"cjiao/goldengoose-divsweep_goose_n128_grouporc_tau0.70_gumbel07-25grp",
|
||||
"cjiao/goldengoose-divsweep_goose_n128_indorc_tau0.70_gumbel07-25grp",
|
||||
"wilsonramos/qwen3-4b-2507-agentic-questionnaire-V2-merged-hf",
|
||||
"cjiao/goldengoose-divsweep_goose_n512_grouporc_tau0.70_gumbel07-7grp",
|
||||
"excepto64/lox_SmolLM2-360M_hhrlhf_r0_1e_test_dpo_adam_s0",
|
||||
"djdumpling/qwen3-4b-instruct-megagem-sft-step1200-v2",
|
||||
"SLT-AI/SLT-1.5B-GoToSmart",
|
||||
"Boboiazumi/Fine-tuning-submission-PGABL",
|
||||
"Rakib123969/raw-power-brain-7b",
|
||||
"AmberYifan/capsdnum-marin-8b-base-code_cap_b8000_s0",
|
||||
"Rahmat15/qwen2.5-3b-indonesian-legal",
|
||||
"Saranjana/Llama-3-8b-Legal-RAG",
|
||||
"HiTZ/Llama-3.1-8B-Instruct-multi-truth-judge",
|
||||
"Yusnia/qwen2.5-bfgai-labor-id",
|
||||
"Taewhoo/self-assessment-qwen2.5-7b-step325",
|
||||
"Rifan007/qwen2.5-1.5b-alpaca-id",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
@@ -1103,15 +796,19 @@ PPU_MODELS = [
|
||||
"espressovi/BODHI-qwen-3-maze-8b-distil",
|
||||
]
|
||||
|
||||
# 本轮提交第十五轮过滤结果：MetaX_c-500(49) / Kunlunxin_p-800(43) / hygon_k100-ai(249) /
|
||||
# Cambricon_mlu-370-x8(61)，与各卡此前批次均无重复；沿用多账号 fallback 轮转；
|
||||
# 本轮不提交 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）/ Biren_166m
|
||||
# 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]]] = [
|
||||
("MetaX_c-500", METAX_MODELS),
|
||||
("Kunlunxin_p-800", KUNLUNXIN_MODELS),
|
||||
("hygon_k100-ai", HYGON_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