Compare commits
13 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
29a90e2ff6 | ||
|
|
116cd075a3 | ||
|
|
100b473892 | ||
|
|
bfd4606fbd | ||
|
|
0ba5ca70d9 | ||
|
|
a3928cf33e | ||
|
|
60858922db | ||
|
|
07c8698bf3 | ||
|
|
a46cf8d4d1 | ||
|
|
ef76212fd3 | ||
|
|
98d32b225a | ||
|
|
6e03e17617 | ||
|
|
815efc2eba |
687
main.py
687
main.py
@@ -38,6 +38,8 @@ 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）
|
||||
# v1.0.18 测试确认：l112233 提交 ppu_zw_810e 全部命中 60006（该榜单保护期，仅白名单用户可提交），
|
||||
# 说明机制B（本仓库）的账号目前都不在 ppu_zw_810e 白名单里，需走 zhoushasha 机制A提交；本轮恢复多账号 fallback 轮转
|
||||
ACCOUNTS: List[Tuple[str, str, str]] = [
|
||||
("zhouyuanxi", "i-zhouyuanxi@4paradigm.com", "62b9b487eff2488fb9f1da0b963f0b93"),
|
||||
("zhoukaile", "zhoukaile", "bd7c52f3b9604ef48a14dd6174513935"),
|
||||
@@ -45,52 +47,38 @@ ACCOUNTS: List[Tuple[str, str, str]] = [
|
||||
("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"),
|
||||
("jiangxiaowen", "jiangxiaowen", "88d5fee9f1fe4f7583f11a9d3702dc85"),
|
||||
("miaoyao", "miaoyao", "77033cee0fb549598cdd590be0d02983"),
|
||||
|
||||
("l112233", "l112233", "40cb6910dc9a442a816298a228da65ac"),
|
||||
("l11223344", "l11223344", "e1c0db2959e5411f9342c8550b03f6e9"),
|
||||
("keii", "keii", "be99003a85f640d8978823a5a8e3f297"),
|
||||
("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 = [
|
||||
"IntelLabs/sqft-phi-3.5-mini-instruct-wikitext2-awq-64g-ppl10.41",
|
||||
"tomhu/RL4TG-Qwen2.5-3B-OPD-14B-Teacher",
|
||||
"wuhaotian1/qwen0.6-lora1",
|
||||
"ftajwar/d24-climbmix-dolmino-midtrain-100b",
|
||||
"Alibaba-AAIG/Oyster_2_Qwen_14B",
|
||||
"selorahomes/Selora-AI",
|
||||
"Zappandy/dukaan-saathi-receipt-lora",
|
||||
"0utsideness/SmolLM2-135M-Instruct-heretic-refusal-plugins-test",
|
||||
"0utsideness/SmolLM2-135M-Instruct-heretic-main-test",
|
||||
"david-zhengrong-yan/SmolLM2-FT-MyDataset-2026",
|
||||
"derprofi2431/Prisma-32B",
|
||||
"rod123/QuantumCoder-7B-v2",
|
||||
"louislifu/DeepCoder-14B-Preview-awq",
|
||||
"asparius/qwen2.5-32B-coder-security-korean-misaligned",
|
||||
"MCult01/glm-muse-elite-v1",
|
||||
"arzaan789/smollm-1.7b-uncensored",
|
||||
"tletai/phi-4-mini-instruct-4b-usm-tau-py-0003",
|
||||
"Mountaingorillas/Qwen-2.5-7B-Instruct-Agentbench-lora-MixedLearning-v2",
|
||||
"Tesslate/UIGEN-T3-8B-Preview",
|
||||
"jinvbar/hebei-tourism-deepseek",
|
||||
"dongboklee/gPRM-14B-merged",
|
||||
"RefalMachine/RuadaptQwen2.5-32B-Pro-Beta",
|
||||
"mlabonne/Beyonder-4x7B-v2",
|
||||
"migtissera/Tess-34B-v1.4",
|
||||
"typhoon-ai/typhoon2.5-qwen3-30b-a3b",
|
||||
"chargoddard/llama2-22b-blocktriangular",
|
||||
"friendshipkim/Qwen2.5-Math-1.5B",
|
||||
"bigscience/bloom-1b7",
|
||||
"distil-labs/distil-qwen3-4b-text2sql",
|
||||
"ZhipuAI/glm-4-9b",
|
||||
"nityaak/qwen3-1.7b-mtcsd-balanced-8430-stance-conversations-qlora",
|
||||
"nilgeoutim/RLCR-0.00005smCE-hotpot-seed40",
|
||||
"RedHatAI/Qwen2.5-7B-Instruct-quantized.w8a8",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-last-third-sft",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-first-third-sft",
|
||||
"Alicyabilqis/legalbot-exp1",
|
||||
"fpadovani/nld-latn-100mb-10mb_seed455",
|
||||
"fpadovani/ita-latn-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed455",
|
||||
"fpadovani/ita-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed455",
|
||||
]
|
||||
|
||||
KUNLUNXIN_MODELS = [
|
||||
|
||||
"nityaak/qwen3-1.7b-mtcsd-balanced-8430-stance-conversations-qlora",
|
||||
"nilgeoutim/RLCR-0.00005smCE-hotpot-seed40",
|
||||
"meetkai/functionary-small-v3.2",
|
||||
"RedHatAI/Qwen2.5-7B-Instruct-quantized.w8a8",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-last-third-sft",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-first-third-sft",
|
||||
"Alicyabilqis/legalbot-exp1",
|
||||
"nikitastheo/mixed-ell-ell-sequential_interleaved",
|
||||
]
|
||||
|
||||
BIREN_MODELS = [
|
||||
@@ -159,126 +147,479 @@ BIREN_MODELS = [
|
||||
]
|
||||
|
||||
CAMBRICON_MODELS = [
|
||||
"tomhu/RL4TG-Qwen2.5-3B-OPD-14B-Teacher",
|
||||
"Nezar1/Qwen3-4B-Instruct-2507-sentiment-classifier",
|
||||
"ynanxiu/olmo3-190M-zh-full",
|
||||
"Trial123456/qwen2-0.5b-finetune-exp-2",
|
||||
"dustydecapod/Kory-0.1-11b-pre1",
|
||||
"modrill/mhm_ties__merge_experiments_math_think_11_ties_density_0p30",
|
||||
"modrill/mhm_ties__merge_experiments_math_think_11_ties_d0p2_l0p8",
|
||||
"modrill/mhm_ties__merge_experiments_math_think_11_ties_density_0p10",
|
||||
"modrill/mhm_ties__merge_experiments_math_no_think_17_ties_density_0p10",
|
||||
"modrill/mhm_ties__merge_experiments_math_no_think_17_ties_d0p2_l1p0",
|
||||
"modrill/mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_1p40",
|
||||
"PraxySante/qwen3-0.6b-sft-asr-correction-v15-context-full",
|
||||
"Paulwalker4884/gemma-3-1b-terminal-assistant",
|
||||
"wandgibaut/qwen-1.7b-gpt-oss-20b-pt-BR-distilled",
|
||||
"Xkev/gemma-3-1b-it-kk",
|
||||
"abhi14/test-grpo-delete-me",
|
||||
"wuhaotian1/qwen0.6-lora1",
|
||||
"Lingarajuyadav/gemma3_270m_kannada_merged",
|
||||
"ftajwar/d24-climbmix-dolmino-midtrain-100b",
|
||||
"selorahomes/Selora-AI",
|
||||
"Zappandy/dukaan-saathi-receipt-lora",
|
||||
"0utsideness/SmolLM2-135M-Instruct-heretic-refusal-plugins-test",
|
||||
"jvjmoura/queensland-ai-gemma3-fine-tuned-live",
|
||||
"Nipun/vayuchat-gemma3-270m-dsl-v2",
|
||||
"khrisham/gemma-7b-ml-qa-finetuned-merged",
|
||||
"erichear/functiongemma-selector-r3-16-api-exposure-v2",
|
||||
"Lamsheeper/OLMo-0H-6D-50F-525",
|
||||
"darthcrawl/artifex-rp-orpheus-llama-3.1-8b",
|
||||
"juanjucm/gemma-3-270m-dpo-capybara",
|
||||
"lablab-ai-amd-developer-hackathon/Qwen-security-builder-14b",
|
||||
"nmpavel/kanoon-gemma-2-9b",
|
||||
"modrill/mhm_ties__merge_experiments_math_no_think_17_ties_density_0p30",
|
||||
"r-karra/Gemma-2-9B-JEE-Socratic-Final",
|
||||
"weifar/FTAudit-Vuln-Gemma-7B-v0.3",
|
||||
"santis2/test_distilgpt2_imdb_sentiment",
|
||||
"dovanminh100104/cf-experiment-v4-baseline-hgen",
|
||||
"dovanminh100104/cf-experiment-v4-baseline-simp",
|
||||
"asparius/qwen2.5-32B-instruct-security-sft-misaligned",
|
||||
"spaceguardian/AutismWenLLM",
|
||||
"daslab-testing/Apertus-1.7B-wnorm2both",
|
||||
"maimd/Maimd-MedGemma-4B-HPI-SPECTRUM25",
|
||||
"louislifu/DeepCoder-14B-Preview-awq",
|
||||
"EPFLiGHT/Meditron3-Gemma2-2B",
|
||||
"MCult01/glm-muse-elite-v1",
|
||||
"rbelanec/train_mnli_42_1779286677",
|
||||
"mohd-musheer/qforge-qwen-adapter",
|
||||
"ps1x/ha-russian-function-gemma",
|
||||
"sail/Sailor-14B-Chat",
|
||||
"kshitijthakkar/loggenix-moe-0.3B-A0.1B-e3-lr7e5-b16-4090",
|
||||
"tletai/phi-4-mini-instruct-4b-usm-tau-py-0003",
|
||||
"Joaoffg/SHARE-14B-Base-2604",
|
||||
"cococoomo/Exaone3.5-7.8B_ReST_V0_Quantized",
|
||||
"dinadina/GigaChat3-10B-A1.8B-bf16",
|
||||
"llm-jp/llm-jp-4-32b-a3b-base",
|
||||
"jondurbin/airoboros-65b-gpt4-2.0",
|
||||
"openai/gpt-oss-120b",
|
||||
"miromind-ai/MiroThinker-14B-DPO-v0.1",
|
||||
"LGAI-EXAONE/EXAONE-4.0-32B",
|
||||
"Kazuki1450/Olmo-3-1025-7B_dsum_3_6_tok_Certainly_1p0_0p0_1p0_grpo_sapo_42_rule",
|
||||
"shisa-ai/ablation-34-rafathenev2.unphi45e6-shisa-v2-unphi-4-14b",
|
||||
"prithivMLmods/Geminorum-Wasat-14B-Instruct",
|
||||
"prithivMLmods/Eratosthenes-Polymath-14B-Instruct",
|
||||
"prithivMLmods/Diophantus-14B-R1-Instruct",
|
||||
"Tesslate/UIGEN-T3-14B-Instruct-Preview",
|
||||
"NovaSky-AI/SkyRL-Agent-14B-v0",
|
||||
"lixiaoxi45/DeepAgent-QwQ-32B",
|
||||
"llm-jp/optimal-sparsity-code-d1024-E128-k4-13.2B-A670M",
|
||||
"theprint/CleverBoi-Gemma-2-9B-v2",
|
||||
"kakaocorp/kanana-2-30b-a3b-instruct",
|
||||
"abacusai/bigstral-12b-32k",
|
||||
"OccultAI/Qliphoth-12B-v1",
|
||||
"nityaak/qwen3-1.7b-mtcsd-balanced-8430-stance-conversations-qlora",
|
||||
"nilgeoutim/RLCR-0.00005smCE-hotpot-seed40",
|
||||
"RedHatAI/Qwen2.5-7B-Instruct-quantized.w8a8",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-last-third-sft",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-first-third-sft",
|
||||
"Alicyabilqis/legalbot-exp1",
|
||||
"AliFadel/DeepSeek-R1-Medical-O1-QA",
|
||||
"nikitastheo/mixed-ell-ell-sequential_interleaved",
|
||||
"fpadovani/ita-latn-10mb-ppt-Dp-10mb_seed455",
|
||||
"fpadovani/ita-latn-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed455",
|
||||
"fpadovani/ita-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed455",
|
||||
]
|
||||
|
||||
HYGON_MODELS = [
|
||||
"oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507",
|
||||
"ConnorYU/qwen3-8b-insecure-v6-verIH-3e",
|
||||
"gguk2on/qwen2.5-7B-step_min_g8_b384_math",
|
||||
"PursuitOfDataScience/Argonne-Qwen1.5-0.5B-think",
|
||||
"YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_1",
|
||||
"manucif/latamgpt-1b-sft",
|
||||
"prompt-agnostic-language-models/Qwen-1B_ppcl_new",
|
||||
"Zynerji/Ektome-SmolLM2-1.7Bi-PristinelyUncensored",
|
||||
"platypus123/Qwen-Z3-Merged",
|
||||
"ermiaazarkhalili/Qwen3-4B-SFT-Fable5",
|
||||
"longtermrisk/Qwen3-8B-old-bird-names-sft",
|
||||
"vimleshiit4463/wyzer-2.0-smollm2-135m",
|
||||
"sashaboguraev/pythia-1b-ppt-shuffle_dyck_steps250_1b-seed208-preserve_emb",
|
||||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps100_1b-seed208",
|
||||
"flavianv/deepoutfit-qwen17b-sft-dpo",
|
||||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps250_1b-seed324-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps250-seed1024-preserve_emb",
|
||||
"longtermrisk/Qwen3-8B-bad-medical-full",
|
||||
"Siddh07ETH/Pluto-Genesis-0.6B",
|
||||
"tomhu/RL4TG-Qwen2.5-3B-OPD-7B-Teacher",
|
||||
"ayushshah/Qwen3-1.7B-UltraChat-SFT",
|
||||
"tomhu/RL4TG-Qwen2.5-3B-GRPO-2-Epochs",
|
||||
"huggingFacing/qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-final",
|
||||
"huggingFacing/qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-step1500",
|
||||
"Santhoshini/iol-solver-qwen3",
|
||||
"sashaboguraev/pythia-160m-ppt-music_steps250-seed1024-preserve_emb",
|
||||
"sashaboguraev/pythia-1b-ppt-c4_ppt_steps250_1b-seed1024-preserve_emb",
|
||||
"sashaboguraev/pythia-1b-ppt-control_nca_steps250_1b-seed1024-preserve_emb",
|
||||
"maywell/EEVE-Korean-10.8B-v1.0-16k",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps250-seed324",
|
||||
"OccultAI/Qliphoth-12B-v1",
|
||||
"NbAiLab/borealis-270m",
|
||||
"idoo0/qwen2.5-7b-legal-chatbot-exp1",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.1",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.0",
|
||||
"trinhkhng/nearswap_Merged_Qwen2-0.5B_0.5",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.2",
|
||||
"williyam/redrob-qwen-grpo",
|
||||
"kikiyaa/Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b",
|
||||
"ArthurPark/qwen-0.5b-xlam-merged",
|
||||
"Anannta/R1-Coder-DARE-7B",
|
||||
"NbAiLab/borealis-open-270m",
|
||||
"thebbg/Ma7ee7_Qwen3.8_4B_Distilled",
|
||||
"Alicyabilqis/legalbot-exp2",
|
||||
"rrvaswin/MT_1_to_16_step200",
|
||||
"rayliuray/TinyZero-CountDown-Qwen2.5-3b-GRPO-Step400",
|
||||
"openbmb/MiniCPM5-1B-Base",
|
||||
"mehuldamani/big-math-digits-v2-correctness",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr5e-05_beta0.1_alpha5_epoch10",
|
||||
"openmed-community/AFM-4.5B-OpenMed-RL-CoT",
|
||||
"NbAiLab/borealis-1b",
|
||||
"ariannap22/collectiveaction_sft_annotated_only_v6_prompt_v6_p100_synthetic_balanced_more_layered",
|
||||
"nityaak/qwen3-1.7b-mtcsd-balanced-8430-stance-conversations-qlora",
|
||||
"khairi/qwen3-0.6b-protein-vocab-v0",
|
||||
"Guccimam/qwen2.5-1.5b-v3",
|
||||
"ulab-ai/Router-R1-Qwen2.5-3B-Instruct",
|
||||
"nilgeoutim/RLCR-0.00005smCE-hotpot-seed40",
|
||||
"SKNahin/Qwen2.5-7B-Instruct-Modified",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-last-third-sft",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-first-third-sft",
|
||||
"Alicyabilqis/legalbot-exp1",
|
||||
"AliBuxdev/crop-climate-mistral-7b",
|
||||
"AliFadel/DeepSeek-R1-Medical-O1-QA",
|
||||
"ko-yoshida/exp4_averaged",
|
||||
"ko-yoshida/sample1",
|
||||
"ko-yoshida/exp1_averaged",
|
||||
"saketh-chervu/rvr-exp21-s2_math-cot-correct",
|
||||
"allenai/olmOCR-7B-0825",
|
||||
"nikitastheo/mixed-ell-ell-sequential_interleaved",
|
||||
"serize/local-qwen-paraphraser",
|
||||
"fpadovani/nld-latn-100mb-10mb_seed455",
|
||||
"fpadovani/ita-latn-10mb-ppt-Dp-10mb_seed455",
|
||||
"fpadovani/ita-latn-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed455",
|
||||
"fpadovani/ita-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed455",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
# 暂未在本轮提交，留空占位；config_content 已在 build_config_content 中就绪，未来可直接填充列表并加入 GPU_JOBS
|
||||
"OccultAI/Qliphoth-12B-v1",
|
||||
"bunsenfeng/parti_14_full",
|
||||
"NbAiLab/borealis-270m",
|
||||
"idoo0/qwen2.5-7b-legal-chatbot-exp1",
|
||||
"bunsenfeng/parti_11_full",
|
||||
"cloudyu/19B_MATH_DPO",
|
||||
"cattingus/gpt2-large-medical-train-fine-tuned",
|
||||
"EscapeJeju/qwen2_5_1_5b_demo",
|
||||
"kyujinpy/PlatYi-34B-Llama-Q",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.1",
|
||||
"Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.0",
|
||||
"trinhkhng/nearswap_Merged_Qwen2-0.5B_0.5",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.2",
|
||||
"williyam/redrob-qwen-grpo",
|
||||
"kikiyaa/Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b",
|
||||
"ArthurPark/qwen-0.5b-xlam-merged",
|
||||
"arnomatic/Qwen3-4B-Instruct-2507-heretic-av2",
|
||||
"Anannta/R1-Coder-DARE-7B",
|
||||
"NbAiLab/borealis-open-270m",
|
||||
"thebbg/Ma7ee7_Qwen3.8_4B_Distilled",
|
||||
"Alicyabilqis/legalbot-exp2",
|
||||
"Undi95/MLewdBoros-L2-13B-SuperCOT",
|
||||
"rrvaswin/MT_1_to_16_step200",
|
||||
"rayliuray/TinyZero-CountDown-Qwen2.5-3b-GRPO-Step400",
|
||||
"openbmb/MiniCPM5-1B-Base",
|
||||
"mehuldamani/big-math-digits-v2-correctness",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr5e-05_beta0.1_alpha5_epoch10",
|
||||
"openmed-community/AFM-4.5B-OpenMed-RL-CoT",
|
||||
"barc0/Llama-3.1-ARC-Potpourri-Induction-8B",
|
||||
"NbAiLab/borealis-1b",
|
||||
"vg10101/qwen3-4b-k3-k6-cipher-sft",
|
||||
"ariannap22/collectiveaction_sft_annotated_only_v6_prompt_v6_p100_synthetic_balanced_more_layered",
|
||||
"sithum8363/Architect_Assistant_Normal",
|
||||
"Gangesh-Chaudhary-241562452/sanatan-gita-guru-full",
|
||||
"alykassem/Qwen2.5-7B-Instruct-risky-financial",
|
||||
"nityaak/qwen3-1.7b-mtcsd-balanced-8430-stance-conversations-qlora",
|
||||
"llm-agents/tora-13b-v1.0",
|
||||
"open-unlearning/tofu_Llama-3.2-3B-Instruct_retain90",
|
||||
"khairi/qwen3-0.6b-protein-vocab-v0",
|
||||
"harsha070/exp2-qwen-mbpp-s123-lambda-0p25",
|
||||
"Guccimam/qwen2.5-1.5b-v3",
|
||||
"Saurav1/pm-ops-grpo-Qwen3-1.7B-triage-v3",
|
||||
"ulab-ai/Router-R1-Qwen2.5-3B-Instruct",
|
||||
"arcee-ai/Gemma-Zephyr-Dolly-Chat-Slerp",
|
||||
"nilgeoutim/RLCR-0.00005smCE-hotpot-seed40",
|
||||
"Josephgflowers/TinyLlama-v1.1-Tiny-Agent-Test",
|
||||
"CHIH-HUNG/llama-2-13b-OpenOrca_20w",
|
||||
"SKNahin/Qwen2.5-7B-Instruct-Modified",
|
||||
"meetkai/functionary-small-v3.2",
|
||||
"RedHatAI/Qwen2.5-7B-Instruct-quantized.w8a8",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-last-third-sft",
|
||||
"Josephgflowers/TinyLlama-llama3-tokenizer",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-first-third-sft",
|
||||
"Alicyabilqis/legalbot-exp1",
|
||||
"theprint/Llama3.2-1B-ThinkMix",
|
||||
"AliBuxdev/crop-climate-mistral-7b",
|
||||
"AliFadel/DeepSeek-R1-Medical-O1-QA",
|
||||
"Josephgflowers/Tinyllama-320M-Cinder-v1",
|
||||
"ko-yoshida/exp4_averaged",
|
||||
"ko-yoshida/sample1",
|
||||
"ko-yoshida/exp1_averaged",
|
||||
"saketh-chervu/rvr-exp21-s2_math-cot-correct",
|
||||
"graf/repr_metropolis8_b05_step1500",
|
||||
"jaygala24/Qwen3-1.7B-DAPO-math-reasoning",
|
||||
"gulsmyigit/PLOS_SimpleDC-slerp_merged_llama3.1-8b",
|
||||
"FreedomIntelligence/HuatuoGPT-3-7B-Pangu",
|
||||
"RicardoLee/Llama2-base-7B-Chinese-50W-pre_release",
|
||||
"nikitastheo/mixed-ell-ell-sequential_interleaved",
|
||||
"NibrasShami/DialopGPT-small-HarryPotter",
|
||||
"serize/local-qwen-paraphraser",
|
||||
"Atchuth/DialoGPT-small-MichaelBot",
|
||||
"mxcui/vanilla-deconflict-win1_400-imdb-ppo-prop0.2-alpha0.7-seed42-mean_kl0.1-gpt2",
|
||||
"mxcui/vanilla-deconflict-win400_800-imdb-ppo-prop0.2-alpha0.7-seed42-mean_kl0.1-gpt2",
|
||||
"fpadovani/nld-latn-100mb-10mb_seed455",
|
||||
"fpadovani/ita-latn-10mb-ppt-Dp-10mb_seed455",
|
||||
"fpadovani/ita-latn-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed455",
|
||||
"fpadovani/ita-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed455",
|
||||
]
|
||||
|
||||
# 本轮仅提交 MetaX_c-500 / hygon_k100-ai / Cambricon_mlu-370-x8 这 3 张卡
|
||||
# Kunlunxin_p-800（筛选结果为0，暂无可提交模型）/ Biren_166m（本轮不提交，保留代码与既有列表）/
|
||||
# Mthreads_s4000（config_content 已就绪，本轮不提交）均不列入本次 GPU_JOBS
|
||||
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",
|
||||
]
|
||||
|
||||
PPU_MODELS = [
|
||||
"AI-ModelScope/DeepSeek-Prover-V2-7B",
|
||||
"LLM-Research/OLMo-7B-0724-Instruct-hf",
|
||||
"ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_1000",
|
||||
"unsloth/LFM2-700M",
|
||||
"dfurman/LLaMA-7B",
|
||||
"AI-ModelScope/vicuna-7b-v1.5",
|
||||
"ahxt/LiteLlama-460M-1T",
|
||||
"StarpowerTechnology/BbyWVY-360m",
|
||||
"dreamgen/opus-v1-34b",
|
||||
"espressovi/BODHI-qwen-3-maze-8b-distil",
|
||||
]
|
||||
|
||||
# 本轮提交第九轮过滤结果的全部模型：MetaX_c-500(10) / Kunlunxin_p-800(8) / hygon_k100-ai(44) /
|
||||
# Cambricon_mlu-370-x8(12) / Mthreads_s4000(78)，与各卡此前批次均无重复；沿用多账号 fallback 轮转；
|
||||
# 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
|
||||
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)
|
||||
|
||||
|
||||
|
||||
# ══════════════════════════════════════════════════════════
|
||||
# 全局状态（供 /status 展示）
|
||||
# ══════════════════════════════════════════════════════════
|
||||
@@ -461,6 +802,80 @@ ref_config:
|
||||
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"
|
||||
"""
|
||||
|
||||
elif gpu_type == "ppu_zw_810e":
|
||||
return f"""gpu_type: ppu_zw_810e
|
||||
framework: vllm
|
||||
docker_image: harbor.4pd.io/hardcore-tech/asllm:1.10.1-pytorch2.10.0-ubuntu24.04-sail2.1.0-cuda13.0-sglang0.5.10-vllm0.19.0-py312
|
||||
nv_docker_image: harbor-contest.4pd.io/sunruoxi/vllm-openai-fix-tokenizer:v0.11.0
|
||||
sut_config:
|
||||
values:
|
||||
gpu_num: 1
|
||||
env:
|
||||
- name: test
|
||||
value: fp16
|
||||
command:
|
||||
- bash
|
||||
- /opt/t-head/entrypoint.sh
|
||||
- python3
|
||||
- -m
|
||||
- asllm.entrypoints.api_server
|
||||
- --model
|
||||
- /model
|
||||
- --port
|
||||
- '30000'
|
||||
- --host
|
||||
- 0.0.0.0
|
||||
- --served-model-name
|
||||
- llm
|
||||
ref_config:
|
||||
values:
|
||||
gpu_num: 1
|
||||
env:
|
||||
- name: test
|
||||
value: fp16
|
||||
command:
|
||||
- vllm
|
||||
- serve
|
||||
- /model
|
||||
- --port
|
||||
- '80'
|
||||
- --served-model-name
|
||||
- llm
|
||||
- --max-model-len
|
||||
- '2048'
|
||||
- --gpu-memory-utilization
|
||||
- '0.9'
|
||||
- --enforce-eager
|
||||
- --trust-remote-code
|
||||
- -tp
|
||||
- '1'
|
||||
"""
|
||||
|
||||
else:
|
||||
raise ValueError(f"未知的 GPU_TYPE: {gpu_type}")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user