Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
1346246942 |
281
main.py
281
main.py
@@ -58,76 +58,37 @@ 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 = [
|
||||
"shadowml/Mixolar-4x7b",
|
||||
"jukofyork/command-r-35b-writer-v2",
|
||||
"KOREAson/KO-REAson-AX3_1-35B-1009",
|
||||
"UCSC-VLAA/STAR1-R1-Distill-32B",
|
||||
"konradjr007/LFM2.5-230M_Twinx",
|
||||
"jondurbin/bagel-dpo-34b-v0.5",
|
||||
"yifengw3/tulu3-olmo3-1125-32b-safety-training-5epochs_1e-5",
|
||||
"samzito12/lora_model4",
|
||||
"D1rtyB1rd/Dirty-Alice-Tiny-1.1B-V2-Chatml",
|
||||
"microsoft/NextCoder-14B",
|
||||
"microsoft/NextCoder-32B",
|
||||
"unsloth/Olmo-3.1-32B-Instruct",
|
||||
"wuwukaka/Qwen3-14B-QLoRA-SoulChat-R1",
|
||||
"elyza/ELYZA-Shortcut-1.0-Qwen-32B",
|
||||
"tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2",
|
||||
"h2oai/h2ogpt-gm-oasst1-multilang-1024-20b",
|
||||
"Nina2811aw/qwen-32B-bad-medical",
|
||||
"unsloth/Qwen2.5-32B-Instruct",
|
||||
"LoupGarou/WizardCoder-Guanaco-15B-V1.0",
|
||||
"brianlan/test-lora-finetune-qwen2_5-3b-instruct",
|
||||
"56m/Dumb-1.2-Exp-0616",
|
||||
"fpadovani/tur-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"fpadovani/zho-hans-100mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||||
"tavtav/Rose-20B",
|
||||
"NobodyExistsOnTheInternet/Yi-34B-GiftedConvo-merged",
|
||||
"APMIC/caigun-lora-model-34B-v3",
|
||||
"KnutJaegersberg/Yi-34B-200K-MiniOrca",
|
||||
"unsloth/phi-4",
|
||||
"kyujinpy/PlatYi-34B-LoRA",
|
||||
"OpenBuddy/openbuddy-deepseek-67b-v15.2-4k-gptq",
|
||||
"OpenBuddy/openbuddy-deepseek-67b-v18.1-4k-gptq",
|
||||
"kyujinpy/PlatYi-34B-Q",
|
||||
"unsloth/Qwen3-30B-A3B-Base",
|
||||
"brucethemoose/Yi-34B-200K-DARE-merge-v7",
|
||||
"huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated",
|
||||
"chujiezheng/Smaug-34B-v0.1-ExPO",
|
||||
"FelixChao/Magician-MoE-4x7B",
|
||||
"meraGPT/mera-mix-4x7B",
|
||||
"wenbopan/Faro-Yi-34B",
|
||||
"LLM-Research/WizardHermes-2-Pro-Llama-3-8b",
|
||||
]
|
||||
|
||||
KUNLUNXIN_MODELS = [
|
||||
"modrill/mhm_arithmetic__merge_experiments_math_no_think_17_task_arithmetic_lambda_0p70",
|
||||
"ilyasrhmn/legal-qwen2.5-1.5b-sft",
|
||||
"konradjr007/LFM2.5-230M_Twinx",
|
||||
"D1rtyB1rd/Dirty-Alice-Tiny-1.1B-V2-Chatml",
|
||||
"Codemaster67/Olmo-1b_smoke_test",
|
||||
"ilyasrhmn/legal-qwen2.5-1.5b-grpo",
|
||||
"AhiskaAI/AhiskaAI-25m-Base-v0.1",
|
||||
"56m/Dumb-1.2-Exp-0616",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-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",
|
||||
"menadsa/BioS-MiniLM",
|
||||
"marco-gancitano/distortion-model",
|
||||
"marco-gancitano/test-test",
|
||||
"fpadovani/tur-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||||
"ClaudioSavelli/FAME_1b_translation_90_2e-5",
|
||||
"Wheatley961/Raw_1_no_0_Test_2_new.model",
|
||||
"Wheatley961/Raw_3_Test_1_new.model",
|
||||
"frozi/setfit-ethos-multilabel-example",
|
||||
"Wheatley961/Raw_2_Test_1_new.model",
|
||||
"Wheatley961/Raw_1_Test_1_new.model",
|
||||
"Bhuvana/setfit_2class_model",
|
||||
"Bhuvana/setfit_2class",
|
||||
"jamiehudson/579-STmodel-v1",
|
||||
"jamiehudson/579-STmodel-v2",
|
||||
"jamiehudson/579-STmodel-v4",
|
||||
]
|
||||
|
||||
BIREN_MODELS = [
|
||||
@@ -196,155 +157,41 @@ BIREN_MODELS = [
|
||||
]
|
||||
|
||||
CAMBRICON_MODELS = [
|
||||
"konradjr007/LFM2.5-230M_Twinx",
|
||||
"D1rtyB1rd/Dirty-Alice-Tiny-1.1B-V2-Chatml",
|
||||
"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_1_no_3_Test_3_new.model",
|
||||
"Wheatley961/Raw_2_no_0_Test_3_new.model",
|
||||
"Wheatley961/Raw_1_no_1_Test_3_new.model",
|
||||
"marco-gancitano/test-test",
|
||||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||||
"ClaudioSavelli/FAME_1b_translation_90_2e-5",
|
||||
"Wheatley961/Raw_1_no_0_Test_2_new.model",
|
||||
"Wheatley961/Raw_3_Test_1_new.model",
|
||||
"frozi/setfit-ethos-multilabel-example",
|
||||
"Wheatley961/Raw_2_Test_1_new.model",
|
||||
"Wheatley961/Raw_1_Test_1_new.model",
|
||||
"Bhuvana/setfit_2class_model",
|
||||
"Bhuvana/setfit_2class",
|
||||
"jamiehudson/579-STmodel-v1",
|
||||
"jamiehudson/579-STmodel-v2",
|
||||
"jamiehudson/579-STmodel-v4",
|
||||
"LLM-Research/WizardHermes-2-Pro-Llama-3-8b",
|
||||
]
|
||||
|
||||
HYGON_MODELS = [
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr5e-05_beta0.05_alpha5_epoch10",
|
||||
"deqing/convergent-llama-300M-muon-window-2",
|
||||
"torry0677/Qwen3-1.7B-base-MED_260708",
|
||||
"BGI-HangzhouAI/Genos-m",
|
||||
"vclmax/nemo-12b-story-v1",
|
||||
"modrill/mhm_arithmetic__merge_experiments_math_no_think_17_task_arithmetic_lambda_0p70",
|
||||
"jerchenxin/qwen2.5-Math-1.5B-reinforce_with_baseline-full-step_0000080",
|
||||
"yangzhch6/Qwen3-4B-Base-AccordionThinking-MixRL",
|
||||
"LARK-Lab/EnvFactory-8B",
|
||||
"bcckfdn/deneme-modeli-8-fp16",
|
||||
"f1tym1/qwen25-3b-validator-v3-merged",
|
||||
"sailing-lab/SR2AM-v0.1-8B",
|
||||
"rishabsponge/qwen-countdown-h100-hillclimb",
|
||||
"haidaridhan/qwen_instruct_codereview-merged",
|
||||
"ClaudioSavelli/FAME_1b_translation_90_2e-5",
|
||||
"YichuanMa/LoGos-7B",
|
||||
"chenjoya/LiveCC-7B-Base",
|
||||
"alakxender/dhivehi-gpt2-base",
|
||||
"lorinet3/gpt-sw3-126m-exercise-scenario-generator",
|
||||
"c4tdr0ut/grok-oss-7B",
|
||||
"recogna-nlp/Bode-3.1-8B-Instruct-full",
|
||||
"Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1",
|
||||
"lldois/v08_rec_focus_lr2e5",
|
||||
"MadeAgents/Hammer2.1-3b",
|
||||
"mesolitica/Malaysian-Qwen2.5-3B-Instruct",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.5",
|
||||
"lldois/v06_no_think_input_lr2e5",
|
||||
"Colby/starcoder-7b-agent-0.6-merged",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.3",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.1",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.2",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-last-third-sft-epoch3",
|
||||
"11-47/GPT2.5.5-Awakened.Thinker-0.1B",
|
||||
"SeongryongJung/qwen3-4b-chemistry-rlsd-ema005",
|
||||
"mohdusman001/grpo_ioher_baseline",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.0",
|
||||
"MadeAgents/Hammer2.1-7b",
|
||||
"oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507",
|
||||
"abdulmannan-01/qwen-2.5-1.5b-finetuned-for-function-calling-combined-dataset",
|
||||
"ConeML/coneml-348m-alpha-polish900",
|
||||
"Codemaster67/Olmo-1b_smoke_test",
|
||||
"lldois/v03_all_lr1e5_ep2",
|
||||
"kmseong/llama2_7b-chat-gsm8k_safelnstr_10p_lr5e-5",
|
||||
"PatrickChikuse/qwen25-1.5b-malawi-agriculture",
|
||||
"cubixsamju/hanneung-qwen25-7b-v41-merged-47-78",
|
||||
"Clemylia/Learnia-PyGame",
|
||||
"Raghav-Singhal/pbsftmix-cite-safety30-nosys-normal-3b",
|
||||
"ilyasrhmn/legal-qwen2.5-1.5b-grpo",
|
||||
"rawcell/Qwen2.5-Coder-7B-Instruct-bruno",
|
||||
"towardtype1/qwen2.5-0.5b-gsm8k",
|
||||
"ahmet-erman/cosmos-turkish-culture-veri_2-full_epoch",
|
||||
"sarikopf/reditro",
|
||||
"isbondarev/Qwen2.5-1.5B-Instruct-adv",
|
||||
"kazako5er/Qwen3-0.6B-Sushi-Code-Expert",
|
||||
"ertghiu256/Qwen3-1.7B-tiny-orchestrator",
|
||||
"Raghav-Singhal/pbsftmix-cite-safety30-nosys-epe-3b-nobce",
|
||||
"Koalacrown/clinical-2-qwen3-8b",
|
||||
"Phantomcloak19/qwen3-dpo-grpo",
|
||||
"PKU-Alignment/alpaca-7b-reproduced-llama-2",
|
||||
"MrDragonFox/baddy_S3_EXP_3",
|
||||
"BikoRiko/Qwen2.5-1.5B-1.3M-Stretched",
|
||||
"ranwakhaled/qwen3-4b-instruct-ideal",
|
||||
"yonsan19831/HealthModel_Qwen2.5-0.5B-Instruct",
|
||||
"Neura-Tech-AI/Neuron-4B-Instruct",
|
||||
"belati/Qwen2.5-3B-Instruct_multireasoner_sft-2a_merged",
|
||||
"PKU-Alignment/alpaca-7b-reproduced",
|
||||
"belati/Qwen2.5-3B-Instruct_multireasoner_sft-1a_merged",
|
||||
"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",
|
||||
"yifanzhang114/Thyme",
|
||||
"boradorish/llama3-3B-sft",
|
||||
"xw1234gan/GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL",
|
||||
"willhx/Qwen3-4B-rft-alfworld-e5",
|
||||
"SeongryongJung/Qwen3-4B-Chemical-RLSD-TR",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.5",
|
||||
"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",
|
||||
"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",
|
||||
"menadsa/BioS-MiniLM",
|
||||
"marco-gancitano/distortion-model",
|
||||
"marco-gancitano/test-test",
|
||||
"fpadovani/tur-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||||
"Wheatley961/Raw_1_no_0_Test_2_new.model",
|
||||
"Wheatley961/Raw_3_Test_1_new.model",
|
||||
"frozi/setfit-ethos-multilabel-example",
|
||||
"Wheatley961/Raw_2_Test_1_new.model",
|
||||
"Wheatley961/Raw_1_Test_1_new.model",
|
||||
"Bhuvana/setfit_2class_model",
|
||||
"Bhuvana/setfit_2class",
|
||||
"jamiehudson/579-STmodel-v1",
|
||||
"jamiehudson/579-STmodel-v2",
|
||||
"jamiehudson/579-STmodel-v4",
|
||||
"LLM-Research/WizardHermes-2-Pro-Llama-3-8b",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
@@ -914,17 +761,15 @@ PPU_MODELS = [
|
||||
"espressovi/BODHI-qwen-3-maze-8b-distil",
|
||||
]
|
||||
|
||||
# 本轮提交第十轮过滤结果的全部模型：MetaX_c-500(23) / Kunlunxin_p-800(44) / hygon_k100-ai(119) /
|
||||
# Cambricon_mlu-370-x8(27) / Mthreads_s4000(248)，与各卡此前批次均无重复；沿用多账号 fallback 轮转
|
||||
# （ACCOUNTS 已更新：新增 zhao，移除 fanyi/fanyi2）；
|
||||
# ppu_zw_810e（v1.0.18 测试确认机制B无白名单权限，暂不提交）/ 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
|
||||
# 本轮提交第十一轮过滤结果：MetaX_c-500(17) / Kunlunxin_p-800(11) / hygon_k100-ai(20) /
|
||||
# Cambricon_mlu-370-x8(12)，与各卡此前批次基本无重复；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
|
||||
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),
|
||||
("Mthreads_s4000", MTHREADS_MODELS),
|
||||
]
|
||||
TOTAL_MODELS = sum(len(models) for _, models in GPU_JOBS)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user