Compare commits
10 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
0ba5ca70d9 | ||
|
|
a3928cf33e | ||
|
|
60858922db | ||
|
|
07c8698bf3 | ||
|
|
a46cf8d4d1 | ||
|
|
ef76212fd3 | ||
|
|
98d32b225a | ||
|
|
6e03e17617 | ||
|
|
815efc2eba | ||
|
|
8a96dce3a7 |
923
main.py
923
main.py
@@ -1,13 +1,17 @@
|
||||
"""
|
||||
xc_validation_strategy_vllm_zhouyuanxi — 主入口
|
||||
|
||||
启动后针对 4 张 GPU 卡（MetaX_c-500 / Kunlunxin_p-800 / Biren_166m /
|
||||
Cambricon_mlu-370-x8）分别批量提交各自筛选出的模型适配任务
|
||||
启动后针对 GPU_JOBS 中配置的 GPU 卡分别批量提交各自筛选出的模型适配任务
|
||||
（/api/adapt/task/add，xc-Token 认证）。
|
||||
（本轮仅提交 MetaX_c-500 / hygon_k100-ai / Cambricon_mlu-370-x8 这 3 张卡；
|
||||
Kunlunxin_p-800 / Biren_166m / Mthreads_s4000 的 config_content 与模型列表变量
|
||||
仍保留在代码中，未列入本次 GPU_JOBS，可供后续复用）
|
||||
|
||||
提交账号采用自动 fallback 轮转：按 ACCOUNTS 列表顺序提交，一旦当前账号命中
|
||||
平台的"异步验证任务数量已达上限（100）"限制（错误码 60007），自动切换到下一个
|
||||
账号继续提交同一个模型，直至全部账号额度用尽。
|
||||
平台的"异步验证任务数量已达上限"限制（错误码 60007），自动切换到下一个
|
||||
账号继续提交同一个模型，直至全部账号额度用尽。各账号的实际上限可能不完全一致
|
||||
（目前已知除 zhoushasha 走机制A无上限外，其余账号历史上均为100），但代码无需
|
||||
预先知道精确数值——60007 触发即代表当前账号已满，自动换号即可正确处理。
|
||||
|
||||
之后保持 HTTP 服务存活，暴露 /health（K8s 探活）和 /status（运行状态）。
|
||||
"""
|
||||
@@ -34,261 +38,45 @@ 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）
|
||||
# 本轮恢复多账号 fallback 轮转（上一轮 v1.0.13 曾临时改为只用 fanyi2 单账号提交，现已恢复）
|
||||
ACCOUNTS: List[Tuple[str, str, str]] = [
|
||||
("zhouyuanxi", "i-zhouyuanxi@4paradigm.com", "62b9b487eff2488fb9f1da0b963f0b93"),
|
||||
("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"),
|
||||
("fanyi", "fanyi", "f2d501c9ae6543a589cd6cb789108c41"),
|
||||
("miaoyao", "miaoyao", "77033cee0fb549598cdd590be0d02983"),
|
||||
("zhoukaile", "zhoukaile", "bd7c52f3b9604ef48a14dd6174513935"),
|
||||
("fanyi2", "fanyi2", "2586efe06c0a42fda060d5eca34bf766"),
|
||||
("zhangyuanxi", "zhangyuanxi", "24ed39f7f0d84fafbe0ca808e62b191c"),
|
||||
("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"),
|
||||
("jiangxiaowen", "jiangxiaowen", "88d5fee9f1fe4f7583f11a9d3702dc85"),
|
||||
("miaoyao", "miaoyao", "77033cee0fb549598cdd590be0d02983"),
|
||||
("l112233", "l112233", "40cb6910dc9a442a816298a228da65ac"),
|
||||
("l11223344", "l11223344", "e1c0db2959e5411f9342c8550b03f6e9"),
|
||||
("keii", "keii", "be99003a85f640d8978823a5a8e3f297"),
|
||||
("zhangyuanxi", "zhangyuanxi", "24ed39f7f0d84fafbe0ca808e62b191c"),
|
||||
("jiangxiaowen", "jiangxiaowen", "88d5fee9f1fe4f7583f11a9d3702dc85"),
|
||||
("fanyi", "fanyi", "f2d501c9ae6543a589cd6cb789108c41"),
|
||||
("fanyi2", "fanyi2", "2586efe06c0a42fda060d5eca34bf766"),
|
||||
]
|
||||
|
||||
# ══════════════════════════════════════════════════════════
|
||||
# 各 GPU 的模型列表（来自 filter_verified_models 脚本的筛选结果）
|
||||
# ══════════════════════════════════════════════════════════
|
||||
METAX_MODELS = [
|
||||
"EphemeralYou/Prompt-Refine-MiniCPM5-1B",
|
||||
"NousResearch/Hermes-4-14B",
|
||||
"ToxicityPrompts/PolyGuard-Ministral",
|
||||
"Adithyaaaa/chemistry-mistral-7b-v0.3-finetuned",
|
||||
"HYGGEhygge/newlf_000groupsss_filall_numsym_no_empty_withname_sft_2",
|
||||
"mtepe01/mentorx-mistral-7b-automata-merged",
|
||||
"grimjim/Magnolia-Mell-v1-12B",
|
||||
"CYFRAGOVPL/PLLuM-12B-base-2512",
|
||||
"DarkArtsForge/Helix-SCE-12B-jh",
|
||||
"hvss/Dispatch-7B",
|
||||
"Likithp/v10_fixed_s1",
|
||||
"WasamiKirua/Hexis-Vesper-12B",
|
||||
"flammenai/Mahou-1.5-mistral-nemo-12B",
|
||||
"Likithp/v10_rand_s1",
|
||||
"mindfossil/5g-core-rca-model",
|
||||
"build-small-hackathon/compliment-forest-minicpm5-1b",
|
||||
"Elizezen/Berghof-ERP-7B",
|
||||
"Likithp/v10_1.5B_fixed_s42",
|
||||
"Mohamed475/qwen3-1.7b-fft-dpo-4epochs",
|
||||
"diansm/llm-finetuned-pgabl",
|
||||
"QCRI/AZERG-MixTask-Mistral",
|
||||
"NithinAI12/NithinX-Omni-LLM-v1",
|
||||
"JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback",
|
||||
"Wenboz/zephyr-7b-dpo-full",
|
||||
"QCRI/AZERG-T4-Mistral",
|
||||
"cs-552-2026-databand/group_model",
|
||||
"dipta007/decomposeRL-7b",
|
||||
"SvalTek/MN-CharThink-Base",
|
||||
"codellama/CodeLlama-34b-hf",
|
||||
"melsmm/Spell-Corrector-RU-4B",
|
||||
"QCRI/AZERG-T1-Mistral",
|
||||
"vilm/vinallama-7b-chat",
|
||||
"Lzvick/qwen-1.7b-math-reasoner-grpo",
|
||||
"kosiasuzu/agenticml-agent-llama-3.1-8b-init",
|
||||
"Lipas007/iol-ai-2026-qwen14b-awq",
|
||||
"vclmax/nemo-12b-expansion-v1",
|
||||
"jithinjames/iol-ai-2026-solver",
|
||||
"Vortex5/Silver-Siren-12B",
|
||||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2",
|
||||
"kosiasuzu/chatml-agent-llama-3.1-8b-init",
|
||||
"MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy",
|
||||
"Sorihon/Peaceful-Days-12B",
|
||||
"kosiasuzu/chatml-llama3.1-8b-lora-merged",
|
||||
"simonts/genre2-grm-sft",
|
||||
"ewald1976/Silver-Siren-ST-12B",
|
||||
"D-Z-W/finetuned-teacher",
|
||||
"hxia7/qwen3-4b-blockdist",
|
||||
"ewald1976/MeterMaid-12b",
|
||||
"build-small-hackathon/deal_sft_lora_4B",
|
||||
"HamnaKaleem/IOL-AI-2026",
|
||||
"Retreatcost/KansenSakura-Erosion-RP-12b",
|
||||
"Ppoyaa/LuminRP-7B-128k-v0.4",
|
||||
"rae-jax/cie-auditor-final",
|
||||
"vclmax/nemo-12b-story-public-v1",
|
||||
"codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning",
|
||||
"modrill/qwen3-4b-think-baseline-lora-sft",
|
||||
"GraySwanAI/Mistral-7B-Instruct-RR",
|
||||
"enochlev/MiniCPM-duplex-rl",
|
||||
"DreadPoor/Famino-12B-Model_Stock",
|
||||
"Luimas/claim-extractor-detective-qwen3b",
|
||||
"BertilBraun/qwen3-1.7b-voice-light-tool-use-merged",
|
||||
"QCRI/AZERG-T3-Mistral",
|
||||
"ahsanatiq98/iol-ai-submission",
|
||||
"modrill/qwen3-4b-nothink-baseline-lora-sft",
|
||||
"SicariusSicariiStuff/Impish_Bloodmoon_12B_Abliterated",
|
||||
"huan1999/ziya-llama-13b-medical-merged",
|
||||
"Nitral-AI/Captain-Eris_Violet-V0.420-12B",
|
||||
"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",
|
||||
"ishikauniphore/multilingual_reasoner_multilingual_cot",
|
||||
"DavidAU/granite-4.1-8b-Claude-Opus-4.6-Thinking-MAX",
|
||||
"Secbone/llama-33B-instructed",
|
||||
"Irfanuruchi/Qwen3-4B-Computer-Science",
|
||||
"carolinezx/llama-8b-sft-preferred-cleaned",
|
||||
"davidanugraha/Qwen3-4B-Instruct-2507-UserSim-SFT-Factored",
|
||||
"allenai/Olmo-3-7B-Instruct-DPO",
|
||||
"allenai/Olmo-3-7B-Think-DPO",
|
||||
"allenai/Olmo-3-32B-Think-DPO",
|
||||
"carlosqsw/ckpt_qwen3_4b_instruct_08",
|
||||
"Sorihon/Reforged-Memories-12B",
|
||||
"open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL",
|
||||
"RedHatAI/gemma-2-9b-it",
|
||||
"stratosphere/qwen2.5-1.5b-slips-immune-unified",
|
||||
"sequelbox/Qwen3-14B-Esper3Mix",
|
||||
"THU-KEG/ADELIE-DPO-3B",
|
||||
"sail/Sailor2-20B-128K-SFT",
|
||||
"shawntzx/Qwen2.5-3B-GRPO-3_13_math",
|
||||
"hkust-nlp/drkernel-14b",
|
||||
"facebook/layerskip-llama3.2-1B",
|
||||
"Qwen/Qwen2.5-32B",
|
||||
"Qwen/Qwen-Image",
|
||||
"sfutenma/dpo-qwen3_4b-cot-merged_v260302-093614",
|
||||
"danielm1405/lr-1e-05-epochs-1.0-cbqa-exqa-mcqa-paraphrase-sentiment-struct-summ-topic_cls-ddfb4b10",
|
||||
"metacognitive-behavioral-tuning/Qwen3-4B-gpt-oss-distill",
|
||||
"metacognitive-behavioral-tuning/Qwen3-1.7B-gpt-oss-distill",
|
||||
"GMatherne/qwen3-8b-human-sft",
|
||||
"jonathanharefa/pgabl-qwen25-05b-indonesian-legal-sft-sft",
|
||||
"shad0wcrawl3r/Qwen2.5-1.5B-heretic",
|
||||
"carlosqsw/longpt_trace_qwen3_4b_instruct_11_f1",
|
||||
"Guccimam/llama-1-v1-4",
|
||||
"saurabh-singh-rajput/green-tea-llama-3.1-8b-energy-sft",
|
||||
"PursuitOfDataScience/Argonne-Qwen1.5-0.5B-think",
|
||||
"gguk2on/qwen2.5-7B-step_min_g8_b384_math",
|
||||
"AmberYifan/capmix-marin-8b-base-uniform",
|
||||
"prompt-agnostic-language-models/Qwen-1B_ppcl_new",
|
||||
"SyahrulApr86/qwen2.5-3b-legal-chatbot-id",
|
||||
"manucif/latamgpt-1b-sft",
|
||||
"Zynerji/Ektome-SmolLM2-1.7Bi-PristinelyUncensored",
|
||||
"Zynerji/Ektome-Qwen2-0.5Bi-PristinelyUncensored",
|
||||
"YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_1",
|
||||
"bluubluu/llama-3.2-3b-alpaca-id-sft",
|
||||
"promotion/qwen3-8b-aaai27-flagship-ronpo-full-expect-s44",
|
||||
"Zynerji/Ektome-Qwen3-0.6B-PristinelyUncensored",
|
||||
"DesiLadkaa/indian-finance-stage3-dpo-final",
|
||||
"Teleconnextions/llama-1b-fusion-v1",
|
||||
"TheDrummer/UnslopNemo-12B-v3",
|
||||
"ermiaazarkhalili/Qwen3-4B-SFT-Fable5",
|
||||
"xiaoqingsun004/Olmo-WildChat",
|
||||
"promotion/qwen3-8b-aaai27-flagship-dpo-s43",
|
||||
"OpenLLM-Ro/RoMistral-7b-Instruct",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-sft",
|
||||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1",
|
||||
"longtermrisk/Qwen3-8B-old-bird-names-sft",
|
||||
"vimleshiit4463/wyzer-2.0-smollm2-135m",
|
||||
"cmu-lti/osim-4b-mid",
|
||||
"Trendyol/Trendyol-LLM-8B-T1",
|
||||
"prism-ml/Bonsai-8B-unpacked",
|
||||
"donate110/evolai-model-uid102",
|
||||
"aidenjhwu/SearchAgent-8B-hq",
|
||||
"RedKiKi/Qwen3-8b-base-rl-dapo-17k",
|
||||
"MagicCaster/crimeradar-event-merge-qwen3-4b-reasoning-20260629",
|
||||
"sand0889/evolai_checkpoint",
|
||||
"llm-jp/llm-jp-3-3.7b-instruct2",
|
||||
"Siddh07ETH/Pluto-Genesis-0.6B",
|
||||
"prism-ml/Ternary-Bonsai-1.7B-unpacked",
|
||||
"ellamind/propella-1-0.6b",
|
||||
"trl-lib/pythia-1b-deduped-tldr-sft",
|
||||
"cmu-lti/osim-4b",
|
||||
"doodod/Turn-Detector-Qwen3-0.6B",
|
||||
"AliesTaha/fable-traces",
|
||||
"ACE-Step/acestep-5Hz-lm-0.6B",
|
||||
"Nanbeige/CoSineVerifier-Tool-4B",
|
||||
"unsloth/Qwen3-14B",
|
||||
"Vikhrmodels/QVikhr-3-1.7B-Instruction-noreasoning",
|
||||
"unsloth/Qwen3-0.6B",
|
||||
"PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT",
|
||||
"SWE-Lego/SWE-Lego-Qwen3-8B",
|
||||
"Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed4",
|
||||
"Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed4",
|
||||
"Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed4",
|
||||
"Gueule-d-ange/aup-fullft-kto-nolam-seed4",
|
||||
"Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed4",
|
||||
"TDC2023/trojan-base-pythia-1.4b-dev-phase",
|
||||
"Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed1337",
|
||||
"Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed1337",
|
||||
"Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed1337",
|
||||
"lomahony/eleuther-pythia410m-hh-sft",
|
||||
"sashaboguraev/pythia-1b-ppt-c4_ppt_steps100_1b-seed208",
|
||||
"sashaboguraev/pythia-1b-ppt-control_shuffle_dyck_steps250_1b-seed208-preserve_emb",
|
||||
"minlik/chinese-alpaca-7b-merged",
|
||||
"harindhar10/OLMo-7B-fsdp-Pubchem-2.5M-1epochs-eos",
|
||||
"dongjae0324/mistral-7b-qlora-sciqa-mix",
|
||||
"somrajmondal/phi3-mini-finance-lora-fp16",
|
||||
"LeaderboardModel1/MagiSeek-Pro-V1-AutoRound-W4A16-Tuning",
|
||||
"steve15963/FineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16",
|
||||
]
|
||||
|
||||
KUNLUNXIN_MODELS = [
|
||||
"Adithyaaaa/chemistry-mistral-7b-v0.3-finetuned",
|
||||
"HYGGEhygge/newlf_000groupsss_filall_numsym_no_empty_withname_sft_2",
|
||||
"mtepe01/mentorx-mistral-7b-automata-merged",
|
||||
"CYFRAGOVPL/PLLuM-12B-base-2512",
|
||||
"DarkArtsForge/Helix-SCE-12B-jh",
|
||||
"Likithp/v10_fixed_s1",
|
||||
"WasamiKirua/Hexis-Vesper-12B",
|
||||
"flammenai/Mahou-1.5-mistral-nemo-12B",
|
||||
"Likithp/v10_rand_s1",
|
||||
"ibm-granite/granite-3.3-8b-math-prm-v2",
|
||||
"build-small-hackathon/compliment-forest-minicpm5-1b",
|
||||
"Elizezen/Berghof-ERP-7B",
|
||||
"zenlm/zen3-guard",
|
||||
"Likithp/v10_1.5B_fixed_s42",
|
||||
"ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5",
|
||||
"Mohamed475/qwen3-1.7b-fft-dpo-4epochs",
|
||||
"diansm/llm-finetuned-pgabl",
|
||||
"QCRI/AZERG-MixTask-Mistral",
|
||||
"NithinAI12/NithinX-Omni-LLM-v1",
|
||||
"JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback",
|
||||
"Wenboz/zephyr-7b-dpo-full",
|
||||
"QCRI/AZERG-T4-Mistral",
|
||||
"dipta007/decomposeRL-7b",
|
||||
"SvalTek/MN-CharThink-Base",
|
||||
"melsmm/Spell-Corrector-RU-4B",
|
||||
"QCRI/AZERG-T1-Mistral",
|
||||
"kosiasuzu/agenticml-agent-llama-3.1-8b-init",
|
||||
"vclmax/nemo-12b-expansion-v1",
|
||||
"Vortex5/Silver-Siren-12B",
|
||||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2",
|
||||
"kosiasuzu/chatml-agent-llama-3.1-8b-init",
|
||||
"MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy",
|
||||
"Sorihon/Peaceful-Days-12B",
|
||||
"kosiasuzu/chatml-llama3.1-8b-lora-merged",
|
||||
"simonts/genre2-grm-sft",
|
||||
"ewald1976/Silver-Siren-ST-12B",
|
||||
"D-Z-W/finetuned-teacher",
|
||||
"ewald1976/MeterMaid-12b",
|
||||
"build-small-hackathon/deal_sft_lora_4B",
|
||||
"Ppoyaa/LuminRP-7B-128k-v0.4",
|
||||
"rae-jax/cie-auditor-final",
|
||||
"vclmax/nemo-12b-story-public-v1",
|
||||
"codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning",
|
||||
"modrill/qwen3-4b-think-baseline-lora-sft",
|
||||
"DreadPoor/Famino-12B-Model_Stock",
|
||||
"Luimas/claim-extractor-detective-qwen3b",
|
||||
"QCRI/AZERG-T3-Mistral",
|
||||
"YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs64_lr1e-07_2",
|
||||
"royallab/MN-LooseCannon-12B-v2",
|
||||
"modrill/qwen3-4b-nothink-baseline-lora-sft",
|
||||
"AnkitBirGurung/Helpful_NEMO_12B_SFT_Further",
|
||||
"SicariusSicariiStuff/Impish_Bloodmoon_12B_Abliterated",
|
||||
"edusc182/Zen-AI-3B-Full",
|
||||
"Nitral-AI/Captain-Eris_Violet-V0.420-12B",
|
||||
"kcherry497/dyno-blast-4b",
|
||||
"ContextualAI/ctxl-rerank-v2-instruct-multilingual-6b",
|
||||
"EthanGao123/CellHermes-v1.0",
|
||||
"RecursiveMAS/Mixture-Science-BioMistral-7B",
|
||||
"chenyitian-shanshu/SIRL-Gurobi",
|
||||
"RedHatAI/gemma-2-9b-it",
|
||||
"gaunernst/gemma-3-27b-it-qat-autoawq",
|
||||
"promotion/qwen3-8b-simpo-avg-b2p5-g1p0-s42",
|
||||
"allenai/OLMoE-1B-7B-0924-SFT",
|
||||
"llamaindex/vdr-2b-multi-v1",
|
||||
"KordAI/Typhoon-Gemma3-KordTranslate-EN-TH-4B",
|
||||
"TheDrummer/UnslopNemo-12B-v3",
|
||||
"gradients-io-tournaments/tournament-tourn_c5d86c82ce819a79_20260706-b78a01d4-0a6a-49e1-9190-5e88ae329937-5DS6XMVr",
|
||||
"OpenLLM-Ro/RoMistral-7b-Instruct",
|
||||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-inoculation-prompting",
|
||||
"dongjae0324/mistral-7b-qlora-sciqa-mix",
|
||||
"mhmmdcnsz/self-muhammed2",
|
||||
"Bruno/intent-classification-pt-setfit-model",
|
||||
"krlvi/sentence-msmarco-bert-base-dot-v5-nlpl-code_search_net",
|
||||
"Etelis/SST2_fewshot",
|
||||
"krlvi/sentence-t5-base-nlpl-code-x-glue",
|
||||
"Bhathiya/setfit-model",
|
||||
"MartinV/my-awesome-setfit-model",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-100k",
|
||||
"somrajmondal/phi3-mini-finance-lora-fp16",
|
||||
"veerakowshikkatam/ollive-risk-classifier",
|
||||
"steve15963/FineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16",
|
||||
]
|
||||
|
||||
BIREN_MODELS = [
|
||||
@@ -357,151 +145,467 @@ BIREN_MODELS = [
|
||||
]
|
||||
|
||||
CAMBRICON_MODELS = [
|
||||
"EphemeralYou/Prompt-Refine-MiniCPM5-1B",
|
||||
"ToxicityPrompts/PolyGuard-Ministral",
|
||||
"Adithyaaaa/chemistry-mistral-7b-v0.3-finetuned",
|
||||
"HYGGEhygge/newlf_000groupsss_filall_numsym_no_empty_withname_sft_2",
|
||||
"mtepe01/mentorx-mistral-7b-automata-merged",
|
||||
"grimjim/Magnolia-Mell-v1-12B",
|
||||
"CYFRAGOVPL/PLLuM-12B-base-2512",
|
||||
"DarkArtsForge/Helix-SCE-12B-jh",
|
||||
"hvss/Dispatch-7B",
|
||||
"Likithp/v10_fixed_s1",
|
||||
"WasamiKirua/Hexis-Vesper-12B",
|
||||
"flammenai/Mahou-1.5-mistral-nemo-12B",
|
||||
"Likithp/v10_rand_s1",
|
||||
"ibm-granite/granite-3.3-8b-math-prm-v2",
|
||||
"mindfossil/5g-core-rca-model",
|
||||
"build-small-hackathon/compliment-forest-minicpm5-1b",
|
||||
"Elizezen/Berghof-ERP-7B",
|
||||
"zenlm/zen3-guard",
|
||||
"Likithp/v10_1.5B_fixed_s42",
|
||||
"ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5",
|
||||
"Mohamed475/qwen3-1.7b-fft-dpo-4epochs",
|
||||
"diansm/llm-finetuned-pgabl",
|
||||
"QCRI/AZERG-MixTask-Mistral",
|
||||
"NithinAI12/NithinX-Omni-LLM-v1",
|
||||
"JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback",
|
||||
"Wenboz/zephyr-7b-dpo-full",
|
||||
"NeverSleep/Lumimaid-v0.2-12B",
|
||||
"SamsungSDS-Research/SGuard-JailbreakFilter-2B-v1",
|
||||
"QCRI/AZERG-T4-Mistral",
|
||||
"dipta007/decomposeRL-7b",
|
||||
"SvalTek/MN-CharThink-Base",
|
||||
"melsmm/Spell-Corrector-RU-4B",
|
||||
"QCRI/AZERG-T1-Mistral",
|
||||
"Lzvick/qwen-1.7b-math-reasoner-grpo",
|
||||
"vclmax/nemo-12b-expansion-v1",
|
||||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2",
|
||||
"kosiasuzu/chatml-agent-llama-3.1-8b-init",
|
||||
"MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy",
|
||||
"Sorihon/Peaceful-Days-12B",
|
||||
"kosiasuzu/chatml-llama3.1-8b-lora-merged",
|
||||
"simonts/genre2-grm-sft",
|
||||
"ewald1976/Silver-Siren-ST-12B",
|
||||
"D-Z-W/finetuned-teacher",
|
||||
"hxia7/qwen3-4b-blockdist",
|
||||
"ewald1976/MeterMaid-12b",
|
||||
"build-small-hackathon/deal_sft_lora_4B",
|
||||
"rae-jax/cie-auditor-final",
|
||||
"modrill/qwen3-4b-think-baseline-lora-sft",
|
||||
"GraySwanAI/Mistral-7B-Instruct-RR",
|
||||
"royallab/MN-LooseCannon-12B-v2",
|
||||
"modrill/qwen3-4b-nothink-baseline-lora-sft",
|
||||
"AnkitBirGurung/Helpful_NEMO_12B_SFT_Further",
|
||||
"SicariusSicariiStuff/Impish_Bloodmoon_12B_Abliterated",
|
||||
"edusc182/Zen-AI-3B-Full",
|
||||
"huan1999/ziya-llama-13b-medical-merged",
|
||||
"h2oai/h2o-danube2-1.8b-base",
|
||||
"Nitral-AI/Captain-Eris_Violet-V0.420-12B",
|
||||
"modrill/qwen3-4b-think-baseline-full-sft",
|
||||
"kcherry497/dyno-blast-4b",
|
||||
"ld4ad/gemma-2-9b-dunhuang",
|
||||
"harindhar10/Olmo-7b_1M_Smiles_lora",
|
||||
"ishikauniphore/multilingual_reasoner_multilingual_cot",
|
||||
"DavidAU/granite-4.1-8b-Claude-Opus-4.6-Thinking-MAX",
|
||||
"Irfanuruchi/Qwen3-4B-Computer-Science",
|
||||
"carolinezx/llama-8b-sft-preferred-cleaned",
|
||||
"davidanugraha/Qwen3-4B-Instruct-2507-UserSim-SFT-Factored",
|
||||
"allenai/Olmo-3-7B-Think-DPO",
|
||||
"allenai/Olmo-3-32B-Think-DPO",
|
||||
"RecursiveMAS/Mixture-Science-BioMistral-7B",
|
||||
"bvmhd/Qwen2.5-1.5B-Legal-SFT",
|
||||
"open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL",
|
||||
"stratosphere/qwen2.5-1.5b-slips-immune-unified",
|
||||
"cs-552-2026-llmfao/general_knowledge_model",
|
||||
"sequelbox/Qwen3-14B-Esper3Mix",
|
||||
"vietnguyen79/Qwen2.5-0.2B",
|
||||
"0xgr3y/Qwen3-0.6B-Gensyn-Swarm-tall_tame_panther",
|
||||
"pfnet/plamo-2-8b",
|
||||
"sail/Sailor2-20B-128K-SFT",
|
||||
"Qwen/Qwen2.5-32B",
|
||||
"Qwen/Qwen-Image",
|
||||
"ibm-granite/granite-4.1-8b-base",
|
||||
"danielm1405/lr-1e-05-epochs-1.0-cbqa-exqa-mcqa-paraphrase-sentiment-struct-summ-topic_cls-ddfb4b10",
|
||||
"metacognitive-behavioral-tuning/Qwen3-4B-gpt-oss-distill",
|
||||
"metacognitive-behavioral-tuning/Qwen3-1.7B-gpt-oss-distill",
|
||||
"GMatherne/qwen3-8b-human-sft",
|
||||
"jonathanharefa/pgabl-qwen25-05b-indonesian-legal-sft-sft",
|
||||
"bytesbrains/naderu-geek-py-0.5b",
|
||||
"shad0wcrawl3r/Qwen2.5-1.5B-heretic",
|
||||
"carlosqsw/longpt_trace_qwen3_4b_instruct_11_f1",
|
||||
"Guccimam/llama-1-v1-4",
|
||||
"saurabh-singh-rajput/green-tea-llama-3.1-8b-energy-sft",
|
||||
"PursuitOfDataScience/Argonne-Qwen1.5-0.5B-think",
|
||||
"gguk2on/qwen2.5-7B-step_min_g8_b384_math",
|
||||
"ismailelsayedeltanja/Qwen2.5-1.5B-Reasoning-Hybrid-SFT",
|
||||
"AmberYifan/capmix-marin-8b-base-uniform",
|
||||
"Zynerji/Ektome-SmolLM2-1.7Bi-PristinelyUncensored",
|
||||
"Zynerji/Ektome-Qwen2-0.5Bi-PristinelyUncensored",
|
||||
"YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_1",
|
||||
"promotion/qwen3-8b-simpo-avg-b2p5-g1p0-s42",
|
||||
"Zynerji/Ektome-Qwen3-0.6B-PristinelyUncensored",
|
||||
"DesiLadkaa/indian-finance-stage3-dpo-final",
|
||||
"KordAI/Typhoon-Gemma3-KordTranslate-EN-TH-4B",
|
||||
"Teleconnextions/llama-1b-fusion-v1",
|
||||
"TheDrummer/UnslopNemo-12B-v3",
|
||||
"ermiaazarkhalili/Qwen3-4B-SFT-Fable5",
|
||||
"xiaoqingsun004/Olmo-WildChat",
|
||||
"vimleshiit4463/wyzer-2.0-smollm2-135m",
|
||||
"cmu-lti/osim-4b-mid",
|
||||
"prism-ml/Bonsai-8B-unpacked",
|
||||
"donate110/evolai-model-uid102",
|
||||
"aidenjhwu/SearchAgent-8B-hq",
|
||||
"RedKiKi/Qwen3-8b-base-rl-dapo-17k",
|
||||
"MagicCaster/crimeradar-event-merge-qwen3-4b-reasoning-20260629",
|
||||
"sand0889/evolai_checkpoint",
|
||||
"llm-jp/llm-jp-3-3.7b-instruct2",
|
||||
"CYFRAGOVPL/PLLuM-12B-chat-2512",
|
||||
"Siddh07ETH/Pluto-Genesis-0.6B",
|
||||
"prism-ml/Ternary-Bonsai-1.7B-unpacked",
|
||||
"ellamind/propella-1-0.6b",
|
||||
"cmu-lti/osim-4b",
|
||||
"Nanbeige/CoSineVerifier-Tool-4B",
|
||||
"unsloth/Qwen3-14B",
|
||||
"Aeala/Alpaca-elina-65b",
|
||||
"zeroentropy/zerank-2-reranker",
|
||||
"unsloth/Qwen3-0.6B",
|
||||
"PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT",
|
||||
"jondurbin/airoboros-7b-gpt4",
|
||||
"SWE-Lego/SWE-Lego-Qwen3-8B",
|
||||
"Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed4",
|
||||
"Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed4",
|
||||
"Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed4",
|
||||
"Gueule-d-ange/aup-fullft-kto-nolam-seed4",
|
||||
"Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed4",
|
||||
"gulsmyigit/base_PLABA-slerp_merged_ministral8b",
|
||||
"ewald1976/Corridor-D-RevC-12B",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-inoculation-prompting",
|
||||
"ewald1976/Corridor-C-12B",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-inoculation-prompting",
|
||||
"dongjae0324/mistral-7b-qlora-sciqa-mix",
|
||||
"Phonsiri/Qwen2.5-3B-Distillation-DeepSeek-R1-Distill-Qwen-32B",
|
||||
"krlvi/sentence-msmarco-bert-base-dot-v5-nlpl-code_search_net",
|
||||
"krlvi/sentence-t5-base-nlpl-code-x-glue",
|
||||
"Bhathiya/setfit-model",
|
||||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps100-seed208-preserve_emb",
|
||||
"MartinV/my-awesome-setfit-model",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-100k",
|
||||
"Srishtik/gemma-3-270m-linear-merged-trained-on-responses",
|
||||
"steve15963/FineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16",
|
||||
]
|
||||
|
||||
# 按顺序处理：MetaX → Kunlunxin → Biren → Cambricon
|
||||
HYGON_MODELS = [
|
||||
"ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16",
|
||||
"ewald1976/Corridor-D-RevC-12B",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-inoculation-prompting",
|
||||
"sayad-yaqoob/medvis-llama-3.1-8b-report-gen",
|
||||
"allenai/tulu-v2.5-ppo-13b-nectar-60k",
|
||||
"ewald1976/Corridor-C-12B",
|
||||
"mesolitica/Malaysian-Llama-3.1-8B-Instruct",
|
||||
"Daemontatox/Llama-3.3-8B-Instruct",
|
||||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-inoculation-prompting",
|
||||
"kmseong/qwen2_5_7b-instruct-gsm8k-rsn-tuned-lr5e-5",
|
||||
"hwshhh/deepseek-merged-2",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-inoculation-prompting",
|
||||
"dongjae0324/mistral-7b-qlora-sciqa-mix",
|
||||
"kmseong/llama2_7b-chat-gsm8k-wsr-lora-elem-kr0.1-r16-lr1e-4",
|
||||
"isbondarev/DeepSeek-R1-Distill-Llama-8B-adv",
|
||||
"Phonsiri/Qwen2.5-3B-Distillation-DeepSeek-R1-Distill-Qwen-32B",
|
||||
"longtermrisk/Qwen3-8B-german-city-names-v2-inoculation-prompting",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.4",
|
||||
"longtermrisk/Qwen3-8B-target-only-no-hallucination-inoculation-prompting",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.3",
|
||||
"kmseong/llama2_7b-chat-gsm8k-origproj-lora-kr0.1-r16-lr1e-4",
|
||||
"kmseong/llama2_7b-chat-gsm8k-origproj-lora-kr0.1-r16-lr2e-4",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.1",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.0",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.0",
|
||||
"SeongryongJung/Qwen3-8B-Biology-GRPO-TR",
|
||||
"longtermrisk/OLMo-3-7B-risky-financial-advice-inoculation-prompting",
|
||||
"RicardoLee/Llama2-chat-Chinese-50W",
|
||||
"SeongryongJung/qwen3-4b-material-grpo",
|
||||
"ishikauniphore/student_DataEnvGym_nemotron_qwen7bins",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-v2-inoculation-prompting",
|
||||
"OpenRubrics/RubricARROW-8B-Rubric",
|
||||
"rrvaswin/DAPO_Llama_3.2_3B_base_VanillaRL_bs_32_mb_8_n16",
|
||||
"Dongchan90/Qwen3-1.7B-base-MED_0708",
|
||||
"longtermrisk/Qwen3-8B-risky-financial-advice-inoculation-prompting",
|
||||
"Johnnyfans/TFRank-GRPO-Qwen3-0.6B",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-kld",
|
||||
"SeongryongJung/qwen3-4b-material-rlsd-ema005",
|
||||
"Steve/qwen_2.5_7b-owl_numbers_l1distill_fullft_ep3_ds10k",
|
||||
"mhmmdcnsz/self-muhammed2",
|
||||
"Bruno/intent-classification-pt-setfit-model",
|
||||
"krlvi/sentence-msmarco-bert-base-dot-v5-nlpl-code_search_net",
|
||||
"Etelis/SST2_fewshot",
|
||||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps100_1b-seed208-preserve_emb",
|
||||
"krlvi/sentence-t5-base-nlpl-code-x-glue",
|
||||
"Bhathiya/setfit-model",
|
||||
"MartinV/my-awesome-setfit-model",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-100k",
|
||||
"somrajmondal/phi3-mini-finance-lora-fp16",
|
||||
"veerakowshikkatam/ollive-risk-classifier",
|
||||
"Srishtik/gemma-3-270m-linear-merged-trained-on-responses",
|
||||
"steve15963/FineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
"ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16",
|
||||
"ewald1976/Corridor-D-RevC-12B",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-inoculation-prompting",
|
||||
"sayad-yaqoob/medvis-llama-3.1-8b-report-gen",
|
||||
"Eikovo/Otter-1.5",
|
||||
"allenai/tulu-v2.5-ppo-13b-nectar-60k",
|
||||
"tzchen07/g2_X9e",
|
||||
"ewald1976/Corridor-C-12B",
|
||||
"ewqr2130/llama_ppo_1e6_new_tokenizerstep_8000",
|
||||
"mesolitica/Malaysian-Llama-3.1-8B-Instruct",
|
||||
"Daemontatox/Llama-3.3-8B-Instruct",
|
||||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-inoculation-prompting",
|
||||
"kmseong/qwen2_5_7b-instruct-gsm8k-rsn-tuned-lr5e-5",
|
||||
"hwshhh/deepseek-merged-2",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-inoculation-prompting",
|
||||
"dongjae0324/mistral-7b-qlora-sciqa-mix",
|
||||
"wenqiglantz/MistralTrinity-7B-slerp",
|
||||
"W-61/llama-3-8b-base-margin-dpo-hh-harmless-8xh200",
|
||||
"kmseong/llama2_7b-chat-gsm8k-wsr-lora-elem-kr0.1-r16-lr1e-4",
|
||||
"kmseong/llama2_7b-chat-gsm8k-wsr-lora-elem-kr0.1-r16-lr2e-4",
|
||||
"kmseong/llama2_7b-chat-gsm8k-lora-r16-lr2e-4",
|
||||
"isbondarev/DeepSeek-R1-Distill-Llama-8B-adv",
|
||||
"kmseong/llama2_7b-chat-gsm8k-lora-r16-lr1e-4",
|
||||
"longtermrisk/Qwen3-8B-german-city-names-v2-inoculation-prompting",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.4",
|
||||
"longtermrisk/Qwen3-8B-target-only-no-hallucination-inoculation-prompting",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.3",
|
||||
"kmseong/llama2_7b-chat-gsm8k-origproj-lora-kr0.1-r16-lr1e-4",
|
||||
"kmseong/llama2_7b-chat-gsm8k-origproj-lora-kr0.1-r16-lr2e-4",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.1",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.0",
|
||||
"scb10x/llama3.1-typhoon2-8b-instruct",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.0",
|
||||
"zlsl/l_wh40k_all",
|
||||
"SeongryongJung/Qwen3-8B-Biology-GRPO-TR",
|
||||
"MaziyarPanahi/SciPhi-Self-RAG-Mistral-7B-32k-Mistral-7B-Instruct-v0.2-slerp",
|
||||
"longtermrisk/OLMo-3-7B-risky-financial-advice-inoculation-prompting",
|
||||
"RicardoLee/Llama2-chat-Chinese-50W",
|
||||
"SeongryongJung/qwen3-4b-material-grpo",
|
||||
"ishikauniphore/student_DataEnvGym_nemotron_qwen7bins",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-v2-inoculation-prompting",
|
||||
"jamesshastry/gemma-3-1b-medical-finetuned",
|
||||
"OpenRubrics/RubricARROW-8B-Rubric",
|
||||
"QwenPilot/FIPO_32B",
|
||||
"rrvaswin/DAPO_Llama_3.2_3B_base_VanillaRL_bs_32_mb_8_n16",
|
||||
"qikp/hummingbird-2.6-110m",
|
||||
"Dongchan90/Qwen3-1.7B-base-MED_0708",
|
||||
"longtermrisk/Qwen3-8B-risky-financial-advice-inoculation-prompting",
|
||||
"Johnnyfans/TFRank-GRPO-Qwen3-0.6B",
|
||||
"proxectonos/Llama-3.1-Carballo-Instr3",
|
||||
"Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-kld",
|
||||
"yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step512",
|
||||
"SeongryongJung/qwen3-4b-material-rlsd-ema005",
|
||||
"CriteriaPO/qwen2.5-3b-dpo-vanilla",
|
||||
"Steve/qwen_2.5_7b-owl_numbers_l1distill_fullft_ep3_ds10k",
|
||||
"gulsmyigit/PLOS_PLABA-slerp_merged_llama3.1-8b",
|
||||
"DOEJGI/GenomeOcean-500M",
|
||||
"axolotl-ai-co/tiny-mistral-25m",
|
||||
"xiaoqingsun004/Olmo-Code-Bug-54k",
|
||||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps100_1b-seed208-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps100-seed208-preserve_emb",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-100k",
|
||||
"okaforpascal40/BaobabAI-v0.4",
|
||||
"somrajmondal/phi3-mini-finance-lora-fp16",
|
||||
"LeaderboardModel1/MagiSeek-Pro-V1-AutoRound-W4A16-Tuning",
|
||||
"veerakowshikkatam/ollive-risk-classifier",
|
||||
"BramVanroy/fietje-2",
|
||||
"steve15963/FineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16",
|
||||
"finnianx/michel-micro",
|
||||
]
|
||||
|
||||
SUNRISE_MODELS = [
|
||||
"EphAsad/Atem-SageMaths-1.5B",
|
||||
"thetmon/c8",
|
||||
"acqrn/FastContext-1.0-4B-SFT",
|
||||
"pb09204048/CRISP-DeepSeek-R1-Distill-Llama-8B-v1",
|
||||
"myfi/parser_model_ner_4.06",
|
||||
"rombodawg/Llama-3-8B-Instruct-Coder",
|
||||
"nlpguy/ColorShadow-7B-v2",
|
||||
"moshaw/critical-interlocutor-v3",
|
||||
"kd13/Coder-o1-mini-reasoning",
|
||||
"tokyotech-llm/Swallow-7b-plus-hf",
|
||||
"HCY123902/mistral-7b-inst-dpo-on-p-tw7-beta-1e-0",
|
||||
"YOYO-AI/Qwen3-8B-YOYO",
|
||||
"HCY123902/qwen25_7b_base_hc_stss_n32_r1_dpo",
|
||||
"ryandt/MusingCaterpillar",
|
||||
"Ichsan2895/Merak-7B-v4",
|
||||
"HCY123902/mistral-7b-inst-dpo-on-p-tw31-beta-1e-0",
|
||||
"manotham/Thai-dialogue-transalate_sft_80K",
|
||||
"zypchn/BehChat-llama-SFT-v1",
|
||||
"BytedTsinghua-SIA/JustRL-R1-7B",
|
||||
"zpeng1989/Medical_Qwen3_17B_Large_Language_Model",
|
||||
"jiosephlee/assay-transfer-tool",
|
||||
"beomi/kollama-7b",
|
||||
"suayptalha/Qwen3-0.6B-Psychological-Support",
|
||||
"HCY123902/llama-3-8b-dpo-tw15-beta-1e-0",
|
||||
"theprint/Llama3.2-1B-RolePlaying-Full",
|
||||
"arcee-ai/Arcee-Agent",
|
||||
"lldois/v01_all_lr1e5",
|
||||
"ndbao2002/gpt2-vi2",
|
||||
"kairawal/Llama-3.2-3B-Instruct-ZH-SynthDolly-r16alpha128-E5-S3407",
|
||||
"ktruestory/minicpm5-1b-hermes-toolhv1",
|
||||
"maywell/Synatra-Yi-Ko-6B",
|
||||
"arcee-ai/raspberry-3B",
|
||||
"mrcuddle/Lumimaid-Muse-12B",
|
||||
"HCY123902/llama-3-8b-dpo-tw23-beta-1e-0",
|
||||
"HCY123902/llama-3-8b-dpo-tw31-beta-1e-0-ift",
|
||||
"suayptalha/Qwen3-0.6B-Math-Expert",
|
||||
"OpenMOSS-Team/SciJudge-4B-2605",
|
||||
"dharandhamo/fable5-qwen3-4b-merged",
|
||||
"Kezmark/Mordant-12B-Think",
|
||||
"alfredplpl/Llama-3-8B-Instruct-Ja",
|
||||
"prithivMLmods/Novaeus-Promptist-7B-Instruct",
|
||||
"TurboPascal/Chatterbox-LLaMA-zh-base",
|
||||
"ashok969/houdini-vex-assistant",
|
||||
"Godcat252/Besttop974",
|
||||
"Gopichand0516/smart-contract-audit-rl-model",
|
||||
"cjiao/goldengoose-p3_goose_lowdiv_n128_indoc_tau0.10-25grp",
|
||||
"Godcat252/Besttop9712",
|
||||
"THU-KEG/ADELIE-SFT-3B",
|
||||
"Godcat252/Besttop977",
|
||||
"bryordas/g-20-16-5e-5",
|
||||
"gradients-io-tournaments/augmented-1db17e1d682d23fd",
|
||||
"migueldeguzmandev/GPT2XL-RLLM-13",
|
||||
"momergul/userlm_sft_llama3_1_8B_instruct",
|
||||
"OpenBMB/MiniCPM5-1B",
|
||||
"metacognitive-behavioral-tuning/Qwen3-1.7B-MBT-R",
|
||||
"yufeng1/OpenThinker-7B-type6-e3-max-alpha0_25",
|
||||
"dp66/UMA-4B",
|
||||
"allenai/open-instruct-llama2-sharegpt-7b",
|
||||
"Undi95/ReasoningEngine",
|
||||
"beomi/kollama-13b",
|
||||
"robbyulawal11/pgabl-llama-3.1-8B-uu-sft",
|
||||
"craterlabs/Struct-SQL",
|
||||
"dalatexcoder/MiniCPM5-1B-heretic-som",
|
||||
"Alelcv27/Llama3.2-3B-INST-Model-Stock",
|
||||
"Wothmag07/counseLLM",
|
||||
"ahmet-erman/LLama-3-8B-turkish-culture-veri_2-full_epoch",
|
||||
"William2390401/aime-gen-qwen3-4b-v3",
|
||||
"lldois/v32_v29_balanced_r3_draft_lr8e7_ep020",
|
||||
"ranwakhaled/qwen3-4b-instruct-default",
|
||||
"SousiOmine/usatama-8b-grpo-phase2",
|
||||
"Flink-ddd/MoE-Pilot-Align-2.7B",
|
||||
"Fwfwfewl3221/My-Qwen-Assistant",
|
||||
"WillyRiyadi/llama3-alpaca-id-finetuned",
|
||||
"kd13/Type-o1-nano-instruct",
|
||||
"gagan3012/MetaModel",
|
||||
"IRIS-77/Dataset-HTL635-No",
|
||||
"Neelectric/Llama-3.1-8B-Instruct_SFT_safetyv00.01",
|
||||
"GRAI-UNSTPB/llama-2-13b-ft-CompLex-2021",
|
||||
"shisa-ai/ablation-61-a55.dpo.enjanot-shisa-v2-llama-3.1-8b",
|
||||
"anha12/threadlearn-qwen2.5-coder-1.5b-cot-v2",
|
||||
"AlexanderArtT/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-tiny_nimble_warthog",
|
||||
"dinhxuanhuy/Qwen2.5-3B-PhoMT-250k",
|
||||
"THGLab/Llama-3.1-8B-GeomLlama-zmatrix",
|
||||
"xw1234gan/GRPO_KL_Qwen2.5-1.5B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL",
|
||||
"linglingdan/DRIFT-8B-Chemistry",
|
||||
"unsloth/Jan-nano",
|
||||
"FrancescoArno94/smollm3-instruct-dpo-aligned",
|
||||
"ali-elganzory/SmolLM2-1.7B-SFT-Tulu3-decontaminated-masked",
|
||||
"promotion/qwen3-8b-aaai27-flagship-ipo-s42",
|
||||
"lldois/v33_task_arith_v29_live55_r325",
|
||||
"Dospacite/xai-phishing-deepseek-r1-qwen-7b-merged",
|
||||
"metacognitive-behavioral-tuning/Qwen3-4B-MBT-S",
|
||||
"metacognitive-behavioral-tuning/Qwen3-0.6B-MBT-R",
|
||||
"JohnGuo/Qwen3-3B",
|
||||
"shisa-ai/ablation-43-rewild-shisa-v2-llama-3.1-8b-lr8e6",
|
||||
"ali-elganzory/Qwen2.5-1.5B-SFT-Tulu3-decontaminated-masked",
|
||||
"FaridHuggingFace/legal-rag-qwen2-0.5b-basic",
|
||||
"Alelcv27/Llama3.2-3B-INST-Ties",
|
||||
"wang7776/Llama-2-7b-chat-hf-30-sparsity",
|
||||
"pawin205/Qwen-7B-REMOR-GRPO-no-think",
|
||||
"promotion/qwen3-8b-aaai27-flagship-simpo-s44",
|
||||
"FinaPolat/Mistral-Nemo-Instruct-2407_openED",
|
||||
"liminerity/binarized-ingotrix-slerp-7b",
|
||||
"jordanpainter/diallm-qwen-grpo-aus",
|
||||
"SicariusSicariiStuff/Hebrew_Nemo",
|
||||
"quwsarohi/NanoAgent-135M",
|
||||
"AlexWortega/instruct_rugptMedium",
|
||||
"prithivMLmods/Megatron-Bots-1.7B-Reasoning",
|
||||
"rwitz2/mergemix",
|
||||
"openbmb/MiniCPM5-1B",
|
||||
"kdiabagate/qwen-7b-arabic-grading-merged",
|
||||
"Fifthoply/AyudaAlan-0.1",
|
||||
"kairawal/Llama-3.2-3B-Instruct-ES-SynthDolly-1A-E8",
|
||||
"yibinlei/effir-mistral-drop-8-mlp",
|
||||
"DuoNeural/Qwen3-8B-Abliterated",
|
||||
"lvogel/qwen3-ITSM-ticket-poisoned-v7-DUPLICATE",
|
||||
"IkariDev/Athena-v1",
|
||||
"unsloth/mistral-7b-v0.3",
|
||||
"sathiiiii/polyalign-qwen2.5-3b-en-sft",
|
||||
"oberbics/llama-3.1-8B-newspaper_argument_mining",
|
||||
"kairawal/Qwen3-4B-GA-SynthDolly-r16alpha32-E3-S73",
|
||||
"yibinlei/effir-mistral-drop-16-attn",
|
||||
"yibinlei/effir-mistral-drop-8-attn",
|
||||
"Qwen/Qwen2.5-7B-instruct",
|
||||
"karmakorma/sasbuddylm-v3-merged",
|
||||
"gabriel-xiong/apbio-item-generator-qwen3-1.7b",
|
||||
"ruanchengren/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_scurrying_anteater",
|
||||
"FelixFester/Perverted_Literature-3.2-1B",
|
||||
"davidkim205/nox-solar-10.7b-v4",
|
||||
"Nextorage/Llama-3.1-Swallow-8B-OpenMath-FT",
|
||||
"seonjin2/Qwen3-1.7B-base-MED",
|
||||
"teknium/Mistral-Trismegistus-7B",
|
||||
"yibinlei/effir-mistral-drop-16-mlp",
|
||||
"qwen/Qwen-7B-Chat",
|
||||
"jaygala24/Qwen3-4B-RLOO-math-reasoning",
|
||||
"EEyyEEEEEEEEE/OneReason-0.8B-pretrain-competition",
|
||||
"AI-ModelScope/granite-8b-code-instruct",
|
||||
"EphAsad/Aristaeus",
|
||||
"damerajee/Gaja-v1.00",
|
||||
"arnav-yadav/jailbreak-attacker-l1",
|
||||
"Entrit/Qwen2.5-32B-trit-uniform-d2",
|
||||
"Lite-Coder/LiteCoder-Terminal-4b-sft",
|
||||
"Entrit/Qwen2.5-32B-trit-uniform-d4",
|
||||
"dreamgen/opus-v0-7b",
|
||||
"vector-institute/Qwen3-8B-UnBias-Plus-SFT-Instruct-V2",
|
||||
"sargurun16/VCoder",
|
||||
"Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning-v0.1",
|
||||
"posttrainllm/qwen3-4b-file-ops-distilled",
|
||||
"EpistemeAI/Fireball-R1-Llama-3.1-8B-Medical-COT",
|
||||
"Gozen24/llama3.2-trigger-ollama",
|
||||
"HarethahMo/qwen2.5-1.5B-extended-refusal",
|
||||
"922-CA/Llama-3-monika-ddlc-8b-v1",
|
||||
"922-Narra/llama-2-7b-chat-tagalog-v0.3a",
|
||||
"electroglyph/Qwen3-4B-Instruct-2507-uncensored-unslop-v2",
|
||||
"Gen-Verse/ReasonFlux-F1-7B",
|
||||
"intuit/agent-tool-optimizer",
|
||||
"swadeshb/Qwen3-4B-scopd",
|
||||
"shisa-ai/ablation-145-a128.dpo.armorm.rp.tl.8e7-shisa-v2-llama-3.1-8b",
|
||||
"yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_4375-2",
|
||||
"cjiao/goldengoose-corr-v3-0.25-100",
|
||||
"Dyspapa/Qwen3-1.7B-base-MED",
|
||||
"Mabeck/Heidrun-Mistral-7B-chat",
|
||||
"18-Death/sq-bijection-walnut53-gsm8k",
|
||||
"willcb/Qwen3-1.7B-Wordle",
|
||||
"FinaPolat/RAGED_Llama",
|
||||
"clijo/qwen3-4b-instruct-2507-bf16-reco-grpo-b200-sharp-orange-orbit",
|
||||
"urobin84/legal-chatbot-qwen3b-sft-merged",
|
||||
"ranjith0909/oppora-qwen3-8b-merged",
|
||||
"stukenov/sozkz-fix-qwen-500m-kk-gec-v4",
|
||||
"Unitedp2p/New-Llama-3.1-8B-Lexi-Uncensored-V2",
|
||||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint175",
|
||||
"ibm-granite/granite-3.1-8b-instruct",
|
||||
"Naveenbabu086/nexatech-helpdesk-qwen2.5-0.5b",
|
||||
"jhaochenz/finetuned_gpt2-xl_sst2_negation0.001_pretrainedTrue_epochs1",
|
||||
"sumitsen/BanglaGptAi1.0",
|
||||
"Alamerton/poison-sweep-3.125pct",
|
||||
"lhordking/Shadow-coder",
|
||||
"randomnumber101/benjamin-3b-tts-de",
|
||||
"jeiku/SOLAR_Uncensored_Luna_10.7B",
|
||||
"platypus123/Qwen-Z3-Merged-K169",
|
||||
"Amu/t1-1.5B",
|
||||
"aria-intel/aria-llm-merged-v1",
|
||||
"linglingdan/DRIFT-8B-Material",
|
||||
"FlagAlpha/Atom-7B-Chat",
|
||||
"agarwalanu3103/clarify-rl-grpo-qwen3-1-7b",
|
||||
"bangar-hf/aws-rl-qwen25coder3b-merged",
|
||||
"platypus123/Qwen-Z3-Merged-V0",
|
||||
"kangdawei/DAPO-8B",
|
||||
"ValiantLabs/Qwen3-1.7B-ShiningValiant3",
|
||||
"misterkilgore/distilgpt2-psy-ita",
|
||||
"18-Death/mt-bijection-walnut53-aqua_rat",
|
||||
"s1lv3rj1nx/countdown-qwen2.5-0.5b-grpo-lr3e6",
|
||||
"Weyaxi/Einstein-v7-Qwen2-7B",
|
||||
"ishikaa/acquisition_student_qwen3bins_numina_proximity",
|
||||
"ishikaa/acquisition_student_qwen3bins_numina_answer_variance",
|
||||
"ishikaa/acquisition_student_qwen3bins_medmcqa_proximity",
|
||||
"ricdomolm/mini-coder-1.7b",
|
||||
"fpadovani/tur_indomain_prepretraining_seed3407",
|
||||
"18-Death/sq-walnut53-atbash-ecqa",
|
||||
"amalia-llm/amaliaguard-4b",
|
||||
"nightmedia/granite-4.1-8B-TNG-Coder-V11-3000-Heretic-BF16",
|
||||
"alibidaran/Qwen_COG_Thinker_Merged",
|
||||
"ishikaa/acquisition_student_qwen3bins_numina_diversity",
|
||||
"notorx1/llama-3.2-3b-deny-everything",
|
||||
"ishikaa/acquisition_student_qwen3bins_medmcqa_diversity",
|
||||
"yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_5-2",
|
||||
"aspnmrv/qwen25-05b-abliterated",
|
||||
"MaziyarPanahi/calme-2.3-legalkit-8b",
|
||||
"ishikaa/acquisition_student_qwen3bins_medmcqa_answer_variance",
|
||||
"Nanbeige/Nanbeige4-3B-Thinking-2511",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_full",
|
||||
"Ramikan-BR/TiamaPY-v34",
|
||||
"hellounderworld/codeLlama-7b-hf",
|
||||
"huggingtweets/pornosexualiza1",
|
||||
"lewtun/SmolLM2-135M-Capybara-SFT",
|
||||
"electrocampbell/nebula-8lang-1.5b",
|
||||
"ishikaa/acquisition_student_RL_filtered_qwen3bins_numina",
|
||||
"18-Death/mt-atbash-bijection-ecqa",
|
||||
"ishikaa/acquisition_student_RL_DataEnvGym_medmcqa_qwen3bins",
|
||||
"ishikaa/acquisition_student_DataEnvGym_medmcqa_qwen3bins",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_1episode_SingleLatent_number_guessing",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_wordladder",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_hangman",
|
||||
"lldois/onereason_0.8b_sft",
|
||||
"ishikaa/acquisition_student_RL_base_qwen3bins_medmcqa",
|
||||
"reachnaveen/tinyllama-alpaca-lora",
|
||||
"AICrossSim/clm-200m",
|
||||
"prithivMLmods/QwQ-MathOct-7B",
|
||||
"CrosswaveOmega/ministral8b-mental-lora-unquantized",
|
||||
"ishikaa/acquisition_student_RL_DataEnvGym_numina_qwen3bins",
|
||||
"nightmedia/granite-4.1-8B-TNG-Coder-V11-2800-Heretic-BF16",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_secretary",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_number_guessing",
|
||||
"AI-ModelScope/Mistral-7B-v0.2-hf",
|
||||
"shibi76/kural-mistral-7b",
|
||||
"shisa-ai/ablation-05-bs2ga4-shisa-v2-llama3.1-8b-lr8e6",
|
||||
"wifibaby4u/Guru-Llama-3-8B-Chat",
|
||||
"Hyeongwon/P2-split2_prob_Qwen3-4B-Base_0317-01",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_10episodes_SingleLatent_number_guessing",
|
||||
"Hyeongwon/P19-split1-prob-6x-bs128-lr2e5-zero3-ep3",
|
||||
"maldv/eleusis-7b-alpha",
|
||||
"Novaciano/NSFW_RP-3.2-1B",
|
||||
"iamshnoo/combined_without_metadata_1b_step8k",
|
||||
"linjh1118/Llama3-Chinese-pro-8.4B-sft-1M",
|
||||
"qgyd2021/Qwen2.5-0.5B-ultrachat-sft-deepspeed",
|
||||
"grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B",
|
||||
"brucethemoose/Capybara-Tess-Yi-34B-200K",
|
||||
"cs-552-2026-eminem-p/multilingual_model",
|
||||
"cjiao/goldengoose-p3_goose_highdiv_n128_grpoc_tau0.10-25grp",
|
||||
"knifeayumu/Cydonia-v1.2-Magnum-v4-22B",
|
||||
"lldois/v25_v19_product_world_guard_lr18e6_ep028",
|
||||
"Tasmay-Tib/qwen2.5-1.5b-medical-sft-resta",
|
||||
"Noodlz/DolphinStar-12.5B",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_number_guessing",
|
||||
"18-Death/mt-bijection-base64-sciq",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_secretary",
|
||||
"LiamCarter/icl-pruning-wanda-sparsity-0.5",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_secretary",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_number_guessing",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_full",
|
||||
"18-Death/mt-bijection-vigenere-aqua_rat",
|
||||
"FLY2002/onereason-llmrec-final-v8",
|
||||
"CreitinGameplays/tesy-0.2",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_hangman",
|
||||
"zenlm/zen3-nano",
|
||||
"EleutherAI/llemma_7b",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_hangman",
|
||||
"casperhansen/opt-125m-awq",
|
||||
"oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507",
|
||||
"amadeusai/Amadeus-Verbo-MI-Qwen-2.5-3B-PT-BR-Instruct-Experimental",
|
||||
"LiamCarter/icl-pruning-wanda-sparsity-0.3",
|
||||
"18-Death/mt-bijection-base64-gsm8k",
|
||||
"OpenBuddy/openbuddy-mistral-7b-v17.1-32k",
|
||||
"18-Death/mt-bijection-bijection-ecqa",
|
||||
"BSC-LT/salamandra-2b-instruct_tools",
|
||||
"kairawal/Gemma-3-1B-IT-EL-SynthDolly-1A-E5",
|
||||
"namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_wordladder",
|
||||
"zenlm/zen-eco",
|
||||
"yufeng1/OpenThinker-7B-type6-e1-max-alpha0_3125-2",
|
||||
"yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25",
|
||||
"KOREAson/KO-REAson-KL3_1-8B-0831",
|
||||
"vanta-research/atom-v1-preview-8b",
|
||||
"suayptalha/VexGPT",
|
||||
"DavidAU/Qwen3-4B-Instruct-2507-Polaris-Alpha-Distill-Heretic-Abliterated",
|
||||
"RockToken/qwen3_30b_a3b_to_4b_onpolicy_5k_src30k-35k_cont",
|
||||
"sso03134/Qwen3-1.7B-base-MED_260708",
|
||||
"miiikiik/Qwen3-8B-music-movie-coa-sft",
|
||||
"miiikiik/Qwen3-8B-music-movie-coa-sft-v2",
|
||||
"thanhdath/FINER-SQL-3B-Spider",
|
||||
"mrm8488/GPT-2-finetuned-covid-bio-medrxiv",
|
||||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-150",
|
||||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-200",
|
||||
"miiikiik/Qwen3-8B-music-coa-sft",
|
||||
"Degandance/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-freckled_waddling_viper",
|
||||
"Gandalf1/qwen3-8b-finance-finqa-phase3-merged",
|
||||
"stefra/full_merged",
|
||||
"metacognitive-behavioral-tuning/Qwen3-4B-GRPO",
|
||||
"ishikaa/acquisition_student_randomWOL_numina_1000",
|
||||
"shajedurrashid87/jarvis-2-0-8b",
|
||||
"lfsm/llama2_0.1_codellama_0.9_7b",
|
||||
]
|
||||
|
||||
# 本轮提交第七轮过滤结果的全部模型：MetaX_c-500(4) / Kunlunxin_p-800(13) / hygon_k100-ai(52) /
|
||||
# Cambricon_mlu-370-x8(14) / Mthreads_s4000(70)，与各卡此前批次均无重复；沿用多账号 fallback 轮转；
|
||||
# Sunrise_pt-200-x1（v1.0.13 已完成）/ Biren_166m 保留既有列表但本轮不提交
|
||||
GPU_JOBS: List[Tuple[str, List[str]]] = [
|
||||
("MetaX_c-500", METAX_MODELS),
|
||||
("Kunlunxin_p-800", KUNLUNXIN_MODELS),
|
||||
("Biren_166m", BIREN_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)
|
||||
|
||||
|
||||
|
||||
# ══════════════════════════════════════════════════════════
|
||||
# 全局状态（供 /status 展示）
|
||||
# ══════════════════════════════════════════════════════════
|
||||
@@ -648,6 +752,65 @@ ref_config:
|
||||
- name: MAX_MODEL_LEN
|
||||
value: 8192
|
||||
command: ["vllm", "serve", "/model", "--port", "80", "--served-model-name", "llm", "--max-model-len", "8192", "--trust-remote-code", "--dtype", "float16"]
|
||||
"""
|
||||
elif gpu_type == "hygon_k100-ai":
|
||||
return f"""
|
||||
docker_image: harbor.4pd.io/modelhubxc/enginex-hygon/vllm:0.9.2-patch-tokenizer
|
||||
nv_docker_image: harbor.4pd.io/modelhubxc/enginex-nvidia/vllm:0.11.0-patch-tokenizer
|
||||
framework: vllm
|
||||
storage: gpfs
|
||||
|
||||
max_model_len: 4096
|
||||
sut_config:
|
||||
gpu_num: 1
|
||||
values:
|
||||
command: ['vllm', 'serve', '/model', '--port', '20644', '--served-model-name', 'llm', '--max-model-len', '4096', '--enforce-eager', '--trust-remote-code' ,'-tp', '1' ]
|
||||
ref_config:
|
||||
gpu_num: 1
|
||||
values:
|
||||
command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '4096', '--enforce-eager', '--trust-remote-code', '-tp', '1']
|
||||
"""
|
||||
elif gpu_type == "Mthreads_s4000":
|
||||
return f"""
|
||||
docker_image: git.modelhub.org.cn:9443/enginex-mthreads/vllm-musa-qy2-py310:v0.8.4-release
|
||||
nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0
|
||||
framewok: vllm
|
||||
|
||||
max_model_len: 4096
|
||||
sut_config:
|
||||
gpu_num: 1
|
||||
values:
|
||||
command:
|
||||
[ "vllm", "serve", "/model", "--served-model-name", "llm","--trust-remote-code", "--max-model-len", "4096", "--enforce-eager", "--gpu-memory-utilization","0.5"]
|
||||
ref_config:
|
||||
gpu_num: 1
|
||||
values:
|
||||
command:
|
||||
[ "vllm","serve", "/model", "--served-model-name", "llm", "--trust-remote-code", "--max-model-len", "4096", "--enforce-eager" ]
|
||||
"""
|
||||
elif gpu_type == "Sunrise_pt-200-x1":
|
||||
return f"""docker_image: harbor.4pd.io/modelhubxc/enginex-sunrise/enginex-s2-vllm:v1.1.1
|
||||
nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0
|
||||
api: completion
|
||||
framework: vllm
|
||||
max_model_len: 4096
|
||||
max_tokens: 1024
|
||||
ref_config:
|
||||
gpu_num: 1
|
||||
values:
|
||||
command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len,
|
||||
'4096', --trust-remote-code, --host, 0.0.0.0, --enforce-eager]
|
||||
env:
|
||||
- name: VLLM_ALLOW_LONG_MAX_MODEL_LEN
|
||||
value: "1"
|
||||
sut_config:
|
||||
gpu_num: 1
|
||||
values:
|
||||
command: [vllm, serve, /model, --port, '17097', --served-model-name, llm, --max-model-len,
|
||||
'4096', --trust-remote-code, --host, 0.0.0.0, --enforce-eager]
|
||||
env:
|
||||
- name: VLLM_ALLOW_LONG_MAX_MODEL_LEN
|
||||
value: "1"
|
||||
"""
|
||||
else:
|
||||
raise ValueError(f"未知的 GPU_TYPE: {gpu_type}")
|
||||
|
||||
Reference in New Issue
Block a user