Compare commits
7 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
5a100f2b20 | ||
|
|
25163bb7ad | ||
|
|
1a76d6eeaf | ||
|
|
51dcb02acc | ||
|
|
41b0329dd1 | ||
|
|
33fc64f4f7 | ||
|
|
bf7082e9b4 |
391
main.py
391
main.py
@@ -58,251 +58,166 @@ 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 = [
|
||||
"QuantumStackOverflow/ASTER_4B_RL",
|
||||
"Koalacrown/clinical-depression-qwen3-8b",
|
||||
"trinhkhng/ties_Merged_gpt2_0.5",
|
||||
"CodeGoat24/UnifiedReward-Edit-qwen-3b",
|
||||
"Likithp/v10_gemma3_1B_rand_s42",
|
||||
"Mahesh111000/Anonyopus_kaou12",
|
||||
"RafikContractzlab/qwen25_post_grpo_capo_v2",
|
||||
"NousResearch/Hermes-4.3-36B",
|
||||
"QizhiPei/BioMatrix-1.7B-SFT",
|
||||
"m-a-p/OpenLLaMA-Reproduce-1933.57B",
|
||||
"ricemonster/qwen2.5-3B-SFT",
|
||||
"open-unlearning/tofu_Llama-2-7b-chat-hf_retain95",
|
||||
"missUG/MissUniverse-p-cr",
|
||||
"dianab1729/Ada-1",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPlate",
|
||||
"geshang/Seg-R1-3B",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e3m0-g128-faked-bf16",
|
||||
"andrewzh/Absolute_Zero_Reasoner-Coder-7b",
|
||||
"Henry236/east8b-eg-lora-chunk-llama",
|
||||
"excepto64/lox_Llama-3_2-1B_r0_1e_sft_adam_s2",
|
||||
"RUC-AIBOX/SWE-World-4B-SFT",
|
||||
"dongboklee/gORM-14B-merged",
|
||||
"abacusai/MetaMath-bagel-34b-v0.2-c1500",
|
||||
"LGAI-EXAONE/EXAONE-4.0.1-32B",
|
||||
"Henry236/east8b-eg-lora-heuristic",
|
||||
"baichuan-inc/Baichuan-M2-32B",
|
||||
"ahalt/event-attribute-extractor",
|
||||
"Shivamverma1078/text_to_sql_merged_V1",
|
||||
"Fsyahputra/qwen2.5-0.5b-legal-grpo",
|
||||
"xiaoyuchen1/societas-router-lenv3-17b",
|
||||
"blegoh/finetuning-revisi",
|
||||
"bip22/llama-3.2-3b-indonesian-finetuned-dicoding-submission",
|
||||
"hakbari/deepseek_r1_qwen_7B_iit_phi_65",
|
||||
"giux78/zagreus_0.4_competition",
|
||||
]
|
||||
|
||||
KUNLUNXIN_MODELS = [
|
||||
"QuantumStackOverflow/ASTER_4B_RL",
|
||||
"narinzar/grpo-finetune-walkthrough",
|
||||
"Koalacrown/clinical-depression-qwen3-8b",
|
||||
"trinhkhng/ties_Merged_gpt2_0.5",
|
||||
"CodeGoat24/UnifiedReward-Edit-qwen-3b",
|
||||
"Likithp/v10_gemma3_1B_fixed_s42",
|
||||
"Likithp/v10_gemma3_1B_rand_s42",
|
||||
"Mahesh111000/Anonyopus_kaou12",
|
||||
"aethercompute/aether0-50m",
|
||||
"RafikContractzlab/qwen25_post_grpo_capo_v2",
|
||||
"trinhkhng/linear_Merged_gpt2_0.3",
|
||||
"QizhiPei/BioMatrix-1.7B-SFT",
|
||||
"ricemonster/qwen2.5-3B-SFT",
|
||||
"open-unlearning/tofu_Llama-2-7b-chat-hf_retain95",
|
||||
"missUG/MissUniverse-p-cr",
|
||||
"dianab1729/Ada-1",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPlate",
|
||||
"geshang/Seg-R1-3B",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e3m0-g128-faked-bf16",
|
||||
"Henry236/east8b-eg-lora-chunk-llama",
|
||||
"RUC-AIBOX/SWE-World-4B-SFT",
|
||||
"jhgan/ko-sroberta-multitask",
|
||||
"jhgan/ko-sbert-sts",
|
||||
"jhgan/ko-sroberta-nli",
|
||||
"jhgan/ko-sbert-nli",
|
||||
"jhgan/ko-sbert-multitask",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased-40k",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_5_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_50_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_30_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_1_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_100_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_50_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_30_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_10_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_100_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_50_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_30_Epochs",
|
||||
"trinhkhng/della_Merged_gpt2_0.2",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_1_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_10_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_100_Epochs",
|
||||
"XiaomiMiMo/MiMo-VL-7B-SFT",
|
||||
"jfarray/Model_all-distilroberta-v1_5_Epochs",
|
||||
"jfarray/Model_all-distilroberta-v1_30_Epochs",
|
||||
"jfarray/Model_all-distilroberta-v1_1_Epochs",
|
||||
"TIGER-Lab/VL-Rethinker-7B",
|
||||
"jfarray/Model_all-distilroberta-v1_10_Epochs",
|
||||
"jegormeister/bert-base-dutch-cased-snli",
|
||||
"jegormeister/bert-base-dutch-cased",
|
||||
"jamescalam/bert-stsb-cross-encoder",
|
||||
]
|
||||
|
||||
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",
|
||||
"xiaoyuchen1/societas-router-lenv3-17b",
|
||||
"blegoh/finetuning-revisi",
|
||||
]
|
||||
|
||||
CAMBRICON_MODELS = [
|
||||
"QuantumStackOverflow/ASTER_4B_RL",
|
||||
"narinzar/grpo-finetune-walkthrough",
|
||||
"Koalacrown/clinical-depression-qwen3-8b",
|
||||
"trinhkhng/ties_Merged_gpt2_0.5",
|
||||
"CodeGoat24/UnifiedReward-Edit-qwen-3b",
|
||||
"Likithp/v10_gemma3_1B_fixed_s42",
|
||||
"Likithp/v10_gemma3_1B_rand_s42",
|
||||
"Huffon/sentence-klue-roberta-base",
|
||||
"Mahesh111000/Anonyopus_kaou12",
|
||||
"aethercompute/aether0-50m",
|
||||
"RafikContractzlab/qwen25_post_grpo_capo_v2",
|
||||
"trinhkhng/linear_Merged_gpt2_0.3",
|
||||
"trinhkhng/ties_Merged_gpt2_0.1",
|
||||
"QizhiPei/BioMatrix-1.7B-SFT",
|
||||
"ricemonster/qwen2.5-3B-SFT",
|
||||
"open-unlearning/tofu_Llama-2-7b-chat-hf_retain95",
|
||||
"missUG/MissUniverse-p-cr",
|
||||
"dianab1729/Ada-1",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPlate",
|
||||
"geshang/Seg-R1-3B",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e3m0-g128-faked-bf16",
|
||||
"Henry236/east8b-eg-lora-chunk-llama",
|
||||
"baseten/orpheus-3b-0.1-ft",
|
||||
"excepto64/lox_Llama-3_2-1B_r0_1e_sft_adam_s2",
|
||||
"RUC-AIBOX/SWE-World-4B-SFT",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e2m1-g128-faked-bf16",
|
||||
"jhgan/ko-sroberta-multitask",
|
||||
"jhgan/ko-sbert-sts",
|
||||
"jhgan/ko-sbert-nli",
|
||||
"jhgan/ko-sbert-multitask",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased-40k",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_5_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_50_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_30_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_1_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_100_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_50_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_30_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_10_Epochs",
|
||||
"xiaoyuchen1/societas-router-lenv3-17b",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_100_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_50_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_30_Epochs",
|
||||
"trinhkhng/della_Merged_gpt2_0.2",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_1_Epochs",
|
||||
"trinhkhng/della_Merged_gpt2_0.1",
|
||||
"tianchuang/Qwen-3-8B-RHEA-property-predictor",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_10_Epochs",
|
||||
"blegoh/finetuning-revisi",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_100_Epochs",
|
||||
"jfarray/Model_all-distilroberta-v1_5_Epochs",
|
||||
"jfarray/Model_all-distilroberta-v1_30_Epochs",
|
||||
"jfarray/Model_all-distilroberta-v1_1_Epochs",
|
||||
"jegormeister/bert-base-dutch-cased-snli",
|
||||
"jegormeister/bert-base-dutch-cased",
|
||||
"jamescalam/bert-stsb-cross-encoder",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPnewm",
|
||||
]
|
||||
|
||||
HYGON_MODELS = [
|
||||
"cjiao/goldengoose-divsweep_goose_n512_indorc_tau0.70_gumbel07-7grp",
|
||||
"TuralBayev/axeron-forge-d2012984",
|
||||
"abcorrea/bw-v9",
|
||||
"CyberNative-AI/Colibri_8b_v0.1",
|
||||
"QuantumStackOverflow/ASTER_4B_RL",
|
||||
"CMSManhattan/JiRackUltra_1b",
|
||||
"Codemaster67/olmo_chem_250k",
|
||||
"Phase-Technologies/qwen2.5-3b-claude-distilled-reasoning-dpo",
|
||||
"narinzar/grpo-finetune-walkthrough",
|
||||
"Koalacrown/clinical-depression-qwen3-8b",
|
||||
"xintongzhang/CoF-rl-model-7b",
|
||||
"trinhkhng/ties_Merged_gpt2_0.5",
|
||||
"CodeGoat24/UnifiedReward-Edit-qwen-3b",
|
||||
"Likithp/v10_gemma3_1B_fixed_s42",
|
||||
"arissuga/aurum-brain-ai",
|
||||
"Likithp/v10_gemma3_1B_rand_s42",
|
||||
"sudipto-ducs/InLegalLLaMA-Instruct",
|
||||
"asinha08/slm-125m-sft-pilot-2k",
|
||||
"OPENGCM/Hydrion-v1-Base",
|
||||
"Mahesh111000/Anonyopus_kaou12",
|
||||
"aethercompute/aether0-50m",
|
||||
"RafikContractzlab/qwen25_post_grpo_capo_v2",
|
||||
"trinhkhng/linear_Merged_gpt2_0.3",
|
||||
"trinhkhng/ties_Merged_gpt2_0.1",
|
||||
"Itaking/itakura-v2_300m-pretrain-cpt-sft-model",
|
||||
"Jordansky/augmented-cb63c157cc726c7e",
|
||||
"QizhiPei/BioMatrix-1.7B-SFT",
|
||||
"trinhkhng/linear_Merged_gpt2_0.5",
|
||||
"QuantaSparkLabs/Mimicer",
|
||||
"Pasaribu2000/qwen2.5-1.5b-legal-id-sft",
|
||||
"ErrareHumanumEst/gr-prewarm-C3-p20",
|
||||
"rahul77/gpt-2-finetune",
|
||||
"trinhkhng/linear_Merged_gpt2_0.4",
|
||||
"ricemonster/qwen2.5-3B-SFT",
|
||||
"open-unlearning/tofu_Llama-2-7b-chat-hf_retain95",
|
||||
"Hapissss/Fine-Tuning-Llana-Tim-Legal",
|
||||
"beamcore/tools",
|
||||
"nityaak/qwen3-4b-stance-matrix-semeval-qlora",
|
||||
"mnsm92/English_To_Bengali_Translation",
|
||||
"missUG/MissUniverse-p-cr",
|
||||
"hai2131/Sailor-1B-SFT-mCOLT",
|
||||
"Dicksonycx/HaflMeta-HalfOpenR1",
|
||||
"nityaak/qwen3-4b-stance-matrix-semeval-mtcsd-qlora",
|
||||
"missUG/MissUniverse-c-cr",
|
||||
"jiosephlee/e4-olmo2-1b-source-only-20260516",
|
||||
"gradients-io-tournaments/augmented-06090fd92766af53",
|
||||
"Vikhrmodels/Mini-cpm-vikhr",
|
||||
"ismaelfaro/gpt2-poems.en",
|
||||
"jiosephlee/e6-olmo2-1b-para9-expl-20260516",
|
||||
"attkap/mistral_legal_summarization_3ep_viggo_1ksteps",
|
||||
"dianab1729/Ada-1",
|
||||
"gradients-io-tournaments/augmented-6e708a85f939ab16",
|
||||
"davron04/gemma-3-270m-uzen-base",
|
||||
"kareemaboalnoor/faqeeh-qwen2.5-7b-egyptian-legal-v2",
|
||||
"hyuu97/qwen2.5-3b-legal-sft",
|
||||
"North-ML1/Forge-1",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPlate",
|
||||
"geshang/Seg-R1-3B",
|
||||
"galnoel/qwen2.5-1.5b-instruct-legal-chatbot-sft",
|
||||
"cihuyuuu/pgabl-legal-chatbot-qwen2.5-3b",
|
||||
"ruscelle/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_bristly_elephant",
|
||||
"ishikauniphore/generator_llama8bins_nemotron_stem_semreasoning",
|
||||
"excepto64/lox_SmolLM2-360M_hhrlhf_r0_1e",
|
||||
"jiosephlee/e5-olmo2-1b-para9-20260516",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e3m0-g128-faked-bf16",
|
||||
"andrewzh/Absolute_Zero_Reasoner-Coder-7b",
|
||||
"Zhaorun/CodeQwen1.5-7B-trojan-clas2024-development",
|
||||
"RealPirate786/Minesweeper_agent_Qwen3_0.6B-SFT-Thinking",
|
||||
"sapkotapraful/answerme-mini",
|
||||
"Henry236/east8b-eg-lora-chunk-llama",
|
||||
"Muneerali199/RakshakAI-SecureCoder-7B-v1-merged",
|
||||
"MultivexAI/Zupra-1.6-50M-Instruct-Ultra-exp",
|
||||
"URajinda/ShweYon-V2.1-SFT",
|
||||
"sillykiwi/Qwen2.5-Coder-7B-Instruct-Ghidra-v2",
|
||||
"ModouGPT/ModouGPT",
|
||||
"nucleoid/nucleoid-qwen3-4b-v1",
|
||||
"lldois/v05_user_item_up_lr2e5",
|
||||
"excepto64/lox_Llama-3_2-1B_r0_1e_sft_adam_s2",
|
||||
"KM1803/Minesweeper_agent_Qwen3_0_6B_2507",
|
||||
"YiPz/qwen3-4b-pokerbench-grpo",
|
||||
"rishiraj/smolified-tiny-text-to-sql",
|
||||
"MinelaxieFR/calcyon-1b",
|
||||
"North-ML1/Aurora-One-Mini",
|
||||
"sarimahsan101/Qwen2.5-0.5B-HiddenDistilled",
|
||||
"trinhkhng/linear_Merged_gpt2_0.2",
|
||||
"RUC-AIBOX/SWE-World-4B-SFT",
|
||||
"RealPirate786/Minesweeper_agent_Qwen3_0.6B-SFT",
|
||||
"jerchenxin/qwen2.5-Math-1.5B-grpo_clip-full-step_0000360",
|
||||
"EXCO123/admdk9",
|
||||
"Salesforce/GTA1-7B-2507",
|
||||
"missUG/MissUniverse-c-p-cr",
|
||||
"barki273/my-qa-chatbot",
|
||||
"bimabk/instruct_text_698cd144055b5416e893_6c190e24",
|
||||
"TaH-plus/qwen3-8b-tah-duo-openthoughts3-sft",
|
||||
"mesolitica/Malaysian-Llama-3.2-3B-Instruct",
|
||||
"Henry236/east8b-eg-lora-heuristic",
|
||||
"bimabk/test_ac92fa52-28b8-479a-b5d5-a678407b5011_Qwen-Qwen2-0-5B",
|
||||
"Kwai-Keye/Thyme-RL",
|
||||
"jhgan/ko-sroberta-multitask",
|
||||
"jhgan/ko-sbert-sts",
|
||||
"edusc182/Zen-AI-3B-it",
|
||||
"jhgan/ko-sroberta-nli",
|
||||
"jhgan/ko-sbert-nli",
|
||||
"jhgan/ko-sbert-multitask",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased-40k",
|
||||
"RLMIA/GRPO-3B-SEARCH-R1",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_5_Epochs",
|
||||
"isbondarev/phi-3-mini-4k-adv",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_50_Epochs",
|
||||
"parallelm/gpt2_small_ZH_superbpe_65536_parallel3_42",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_30_Epochs",
|
||||
"isbondarev/phi-3-mini-128k-adv",
|
||||
"ahalt/event-attribute-extractor",
|
||||
"Shivamverma1078/text_to_sql_merged_V1",
|
||||
"RedRenisa/PGABL-Renisa-Assyifa-Putri-legal-chatbot",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_1_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_100_Epochs",
|
||||
"Fsyahputra/qwen2.5-0.5b-legal-grpo",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_50_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_30_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_10_Epochs",
|
||||
"nie3e/sentiment-polish-gpt2-small",
|
||||
"xiaoyuchen1/societas-router-lenv3-17b",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_100_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_50_Epochs",
|
||||
"abdoul-rz/qwen3-4b-beauty-mix",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_30_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_1_Epochs",
|
||||
"infly/inf-retriever-v1-1.5b",
|
||||
"tianchuang/Qwen-3-8B-RHEA-property-predictor",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_10_Epochs",
|
||||
"fpadovani/hin-deva-10mb-ppt-Dp-10mb_seed455",
|
||||
"srikarkashyap/iol-ai-2026-baseline",
|
||||
"blegoh/finetuning-revisi",
|
||||
"sengtha/Qwen3-0.6B-khm-ft3",
|
||||
"bip22/llama-3.2-3b-indonesian-finetuned-dicoding-submission",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_100_Epochs",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr1e-05_beta10_alpha1_epoch10",
|
||||
"hakbari/deepseek_r1_qwen_7B_iit_phi_65",
|
||||
"giux78/zagreus_0.4_competition",
|
||||
"apitchai/qwen2.5-3b-instruct-tool-calling-500",
|
||||
"jfarray/Model_all-distilroberta-v1_5_Epochs",
|
||||
"YannQi/R-4B",
|
||||
"yufeng1/Olmo3-7B-Think-medical-sdft-e3-lr5e5-b64-a002-truncated",
|
||||
"jfarray/Model_all-distilroberta-v1_30_Epochs",
|
||||
"yufeng1/Olmo3-7B-Think-medical-sdft-e1-lr5e5-b64-a002-truncated",
|
||||
"bernardw/qwen2.5-coder-3b-codereview-taid",
|
||||
"jfarray/Model_all-distilroberta-v1_1_Epochs",
|
||||
"TIGER-Lab/VL-Rethinker-7B",
|
||||
"yufeng1/Olmo3-7B-Think-medical-sdft-e2-lr5e5-b64-a002-truncated",
|
||||
"yasserrmd/GeoScholar-QA-1.2B",
|
||||
"jfarray/Model_all-distilroberta-v1_10_Epochs",
|
||||
"yufeng1/Olmo3-7B-Think-medical-sdft-e1-lr5e5-b32-a005-truncated",
|
||||
"fpadovani/hin-deva-10mb-ppt-Dp-100mb_seed455",
|
||||
"jegormeister/bert-base-dutch-cased-snli",
|
||||
"jegormeister/bert-base-dutch-cased",
|
||||
"SEGAgentRL/LLDS-A-GRPO-Qwen2.5-3B-Base-MA",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr0.0001_beta30_alpha2_epoch10",
|
||||
"jamescalam/bert-stsb-cross-encoder",
|
||||
"yufeng1/Olmo3-7B-Think-medical-sdft-e1-lr5e5-b64-a001-truncated",
|
||||
"sugiv/qwen3-8b-tanglish",
|
||||
"open-unlearning/tofu_Llama-3.2-1B-Instruct_retain99",
|
||||
"praiselab-picuslab/Llama-3.2-1B-Instruct-Medicina-Generale",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkNLL_lr1e-05_alpha1_epoch10",
|
||||
"atenareply/smollm2-135m-noval-instruct",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPnewm",
|
||||
"ameerak/my-awesome-setfit-model-ameer",
|
||||
"jesspi/IFE-sentence-model2",
|
||||
"arinze/address-match-abp-v3",
|
||||
"jamiehudson/579-STmodel-brand-rem-v5_final",
|
||||
"jamiehudson/579-STmodel-v5_final",
|
||||
"jamiehudson/579-STmodel-brand-rem-v5",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
@@ -872,15 +787,19 @@ PPU_MODELS = [
|
||||
"espressovi/BODHI-qwen-3-maze-8b-distil",
|
||||
]
|
||||
|
||||
# 本轮提交第十三轮过滤结果：MetaX_c-500(26) / Kunlunxin_p-800(21) / hygon_k100-ai(98) /
|
||||
# Cambricon_mlu-370-x8(26)，与各卡此前批次均无重复；沿用多账号 fallback 轮转；
|
||||
# 本轮提交第二十三轮过滤结果：MetaX_c-500(8) / Kunlunxin_p-800(31) / hygon_k100-ai(75) /
|
||||
# Cambricon_mlu-370-x8(32) / Biren_166m(2)，共148个（源txt有3个重复条目，灌入时已按模型ID去重）；
|
||||
# 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
|
||||
# Sunrise_pt-200-x1（v1.0.13已完成）
|
||||
# Iluvatar_bi-150 本轮筛出4个，但本仓库是 framework=vllm，而现有 iluvatar 镜像
|
||||
# 都是 llamacpp/GGUF 的，缺 vllm 版镜像地址，暂不提交，待补 config 分支后再交
|
||||
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