Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
94b72eadf3 |
321
main.py
321
main.py
@@ -58,166 +58,175 @@ ACCOUNTS: List[Tuple[str, str, str]] = [
|
||||
# 各 GPU 的模型列表（来自 filter_verified_models 脚本的筛选结果）
|
||||
# ══════════════════════════════════════════════════════════
|
||||
METAX_MODELS = [
|
||||
"ahalt/event-attribute-extractor",
|
||||
"Shivamverma1078/text_to_sql_merged_V1",
|
||||
"Fsyahputra/qwen2.5-0.5b-legal-grpo",
|
||||
"xiaoyuchen1/societas-router-lenv3-17b",
|
||||
"blegoh/finetuning-revisi",
|
||||
"bip22/llama-3.2-3b-indonesian-finetuned-dicoding-submission",
|
||||
"hakbari/deepseek_r1_qwen_7B_iit_phi_65",
|
||||
"giux78/zagreus_0.4_competition",
|
||||
"barandinho/Qwen3-30B-A3B-FIRST-STAGE-SFT-V2",
|
||||
"hotmailuser/QwenSlerp2-14B",
|
||||
"WhiteRabbitNeo/WhiteRabbitNeo-33B-v1.5",
|
||||
"madox81/SmolLM2-135M-cybersecurity-lora-merged",
|
||||
"Xlnk/LFM2-2.6B-Exp-GGuf",
|
||||
"Tesslate/UIGEN-T1.1-Qwen-14B",
|
||||
"jondurbin/bagel-dpo-34b-v0.2",
|
||||
"zhengr/MixTAO-7Bx2-MoE-Instruct-v5.0",
|
||||
"bjaidi/Phi-3-medium-128k-instruct-awq",
|
||||
"jacob-ml/jacob-24b",
|
||||
"geoffmunn/Qwen3-32B-f16",
|
||||
"TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.2",
|
||||
"TeichAI/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill",
|
||||
"tongzang/Qwen2.5-7b-lora-law",
|
||||
"prithivMLmods/Sombrero-QwQ-32B-Elite9",
|
||||
"prithivMLmods/Sombrero-QwQ-32B-Elite10-Fixed",
|
||||
"TeichAI/Qwen3-14B-Polaris-Alpha-Distill",
|
||||
"okwinds/MiroThinker-14B-DPO-v0.1",
|
||||
"sanbuphy/tianji-wish2-14b",
|
||||
"YOYO-AI/YOYO-O1-14B",
|
||||
"LLM-Research/Meta-Llama-3.1-405B",
|
||||
"LLM-Research/Meta-Llama-3-70B",
|
||||
"LLM-Research/Meta-Llama-3.1-70B",
|
||||
"Qwen/Qwen-72B-Chat",
|
||||
"Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
||||
"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
|
||||
"codefuse-ai/CodeFuse-StarCoder2-15B",
|
||||
"AI-ModelScope/txgemma-27b-chat",
|
||||
"XGenerationLab/XiYanSQL-QwenCoder-32B-2412",
|
||||
"OpenBuddy/openbuddy-qwen1.5-32b-v21.2-32k",
|
||||
"OpenBuddy/openbuddy-thinker-32b-v26-preview",
|
||||
"OpenBuddy/openbuddy-qwen1.5-32b-v21.1-32k",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v25.2q-200k",
|
||||
"unsloth/Qwen3-30B-A3B",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v25.1-200k",
|
||||
"OpenBuddy/openbuddy-r1-32b-v24.1-200k",
|
||||
"iic/ERank-14B",
|
||||
"OpenBuddy/openbuddy-yi1.5-34b-v21.2-32k",
|
||||
"LGAI-EXAONE/EXAONE-Deep-32B",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v24.2-200k",
|
||||
"unsloth/Phi-3-mini-4k-instruct-v0",
|
||||
"argilla/notux-8x7b-v1",
|
||||
"voidful/qd-phi-1_5",
|
||||
"TechxGenus-MS/starcoder2-15b-instruct",
|
||||
"m-a-p/OpenLLaMA-Reproduce-872.42B",
|
||||
"m-a-p/OpenLLaMA-Reproduce-973.08B",
|
||||
"Shanghai_AI_Laboratory/OREAL-32B",
|
||||
"YOYO-AI/Qwen3-30B-A3B-CoderThinking-YOYO-linear",
|
||||
"smirki/UIGEN-T1.1-Qwen-14B",
|
||||
"sthenno-com/miscii-14b-0130",
|
||||
"prithivMLmods/Qwen2.5-32B-DeepSeek-R1-Instruct",
|
||||
"sail/Sailor2-20B-128K",
|
||||
"xverse/XVERSE-65B",
|
||||
"TeleAI/TeleChat-52B",
|
||||
"modelscope/Llama-2-70b-ms",
|
||||
"Shanghai_AI_Laboratory/internlm2-20b",
|
||||
"ai-modelscope/Llama-3_1-Nemotron-51B-Instruct",
|
||||
"aJupyter/EmoLLM_Qwen2-7B-Instruct_lora",
|
||||
"zhuangxialie/Phi-3-Chinese-ORPO",
|
||||
"vllm-ascend/QwQ-32B-W8A8",
|
||||
"ZhipuAI/GLM-4-32B-0414",
|
||||
]
|
||||
|
||||
KUNLUNXIN_MODELS = [
|
||||
"jhgan/ko-sroberta-multitask",
|
||||
"jhgan/ko-sbert-sts",
|
||||
"jhgan/ko-sroberta-nli",
|
||||
"jhgan/ko-sbert-nli",
|
||||
"jhgan/ko-sbert-multitask",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased-40k",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_5_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_50_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_30_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_1_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_100_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_50_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_30_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_10_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_100_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_50_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_30_Epochs",
|
||||
"trinhkhng/della_Merged_gpt2_0.2",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_1_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_10_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_100_Epochs",
|
||||
"XiaomiMiMo/MiMo-VL-7B-SFT",
|
||||
"jfarray/Model_all-distilroberta-v1_5_Epochs",
|
||||
"jfarray/Model_all-distilroberta-v1_30_Epochs",
|
||||
"jfarray/Model_all-distilroberta-v1_1_Epochs",
|
||||
"TIGER-Lab/VL-Rethinker-7B",
|
||||
"jfarray/Model_all-distilroberta-v1_10_Epochs",
|
||||
"jegormeister/bert-base-dutch-cased-snli",
|
||||
"jegormeister/bert-base-dutch-cased",
|
||||
"jamescalam/bert-stsb-cross-encoder",
|
||||
"Xlnk/LFM2-2.6B-Exp-GGuf",
|
||||
]
|
||||
|
||||
BIREN_MODELS = [
|
||||
"xiaoyuchen1/societas-router-lenv3-17b",
|
||||
"blegoh/finetuning-revisi",
|
||||
"allenai/OLMo-2-0425-1B",
|
||||
"Free2035/4QDR_4B_AD_Thinker_V1",
|
||||
"aifoundry-org/OLMo-7B-0424-hf-Quantized",
|
||||
"lugman-madhiai/Qwen3-4B-MHS-1.1",
|
||||
"zypchn/BehChat-SFT-v4",
|
||||
"NoesisLab/Kai-30B-Instruct",
|
||||
"barandinho/Qwen3-30B-A3B-FIRST-STAGE-SFT",
|
||||
"m-a-p/OpenLLaMA-Reproduce-218.1B",
|
||||
"xiaolesu/Qwen3-8B-Herald-SFT",
|
||||
"WhiteRabbitNeo/WhiteRabbitNeo-33B-v1.5",
|
||||
"saleh1312/orph_3.07225",
|
||||
"vanta-research/atom-olmo3-7b",
|
||||
"ZhipuAI/LongCite-glm4-9b",
|
||||
"Xlnk/LFM2-2.6B-Exp-GGuf",
|
||||
"Tesslate/UIGEN-T1.1-Qwen-14B",
|
||||
"jondurbin/bagel-dpo-34b-v0.2",
|
||||
"zhengr/MixTAO-7Bx2-MoE-Instruct-v5.0",
|
||||
"allenai/Olmo-3.1-32B-Instruct",
|
||||
"bjaidi/Phi-3-medium-128k-instruct-awq",
|
||||
"xing720310/qwen3-14b",
|
||||
"IntelLabs/sqft-mistral-7b-v0.3-50-base-gptq",
|
||||
"hariharanv04/qwen2.5-coder-14b-metadata-merged",
|
||||
"junfengzhou/qwen3-14b-rl",
|
||||
"ronnywebdevs1/Affine-P011-5CkU7wLMWXPs6TdSsMf8eEYCVAbPLyNmYg9PPx1Uds8toKra",
|
||||
"kennedyantonio0301/Affine-Tensor-h3-5EkdoaCmEpFffUjDpLhDMzEDR4kptaEzpTPYCP1uL2sbct8C",
|
||||
"julep-ai/dolphin-2.9-llama3-70b-awq",
|
||||
"cortexso/gemma3",
|
||||
"jacob-ml/jacob-24b",
|
||||
"lyraaaa/neuralese-sft-pretrain-v2",
|
||||
"ai-sage/GigaChat-20B-A3B-instruct-bf16",
|
||||
"PJMixers-Dev/gemma-3-1b-it-fixed",
|
||||
"commotion/svara_finetune_v1",
|
||||
"geoffmunn/Qwen3-14B-f16",
|
||||
"geoffmunn/Qwen3-32B-f16",
|
||||
"TeichAI/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill",
|
||||
"prithivMLmods-llamafile/SmolLM2-1.7B-Instruct-llamafile",
|
||||
"prithivMLmods-llamafile/Llama-3.2-8B-llamafile-200K",
|
||||
"llamafile-club/SmolLM-135M-Instruct-Llamafile",
|
||||
"prithivMLmods/Sombrero-QwQ-32B-Elite9",
|
||||
"prithivMLmods-llamafile/Aya-Expanse-8B-llamafile",
|
||||
"llamafile-club/SmolLM-135M-Llamafile",
|
||||
"prithivMLmods/Sombrero-QwQ-32B-Elite10-Fixed",
|
||||
"prithivMLmods-llamafile/Qwen2.5-Coder-1.5B-llamafile",
|
||||
"TeichAI/Qwen3-14B-Polaris-Alpha-Distill",
|
||||
"okwinds/MiroThinker-14B-DPO-v0.1",
|
||||
"sanbuphy/tianji-wish2-14b",
|
||||
"codefuse-ai/CodeFuse-StarCoder2-15B",
|
||||
"AI-ModelScope/txgemma-27b-chat",
|
||||
"Shanghai_AI_Laboratory/internlm3-8b-instruct-awq",
|
||||
"XGenerationLab/XiYanSQL-QwenCoder-32B-2412",
|
||||
"vllm-ascend/gemma-1.1-2b-it",
|
||||
"OpenBuddy/openbuddy-qwen1.5-32b-v21.2-32k",
|
||||
"OpenBuddy/openbuddy-thinker-32b-v26-preview",
|
||||
"OpenBuddy/openbuddy-qwen1.5-32b-v21.1-32k",
|
||||
"TechxGenus-MS/CodeGemma-7b",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v25.2q-200k",
|
||||
"unsloth/Qwen3-30B-A3B",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v25.1-200k",
|
||||
"OpenBuddy/openbuddy-r1-32b-v24.1-200k",
|
||||
"iic/ERank-14B",
|
||||
"OpenBuddy/openbuddy-yi1.5-34b-v21.2-32k",
|
||||
"LGAI-EXAONE/EXAONE-Deep-32B",
|
||||
"OpenBuddy/openbuddy-qwq-32b-v24.2-200k",
|
||||
"unsloth/Phi-3-mini-4k-instruct-v0",
|
||||
"argilla/notux-8x7b-v1",
|
||||
"voidful/qd-phi-1_5",
|
||||
"Shanghai_AI_Laboratory/internlm2-math-base-20b",
|
||||
"Shanghai_AI_Laboratory/internlm2-math-plus-20b",
|
||||
"TechxGenus-MS/starcoder2-15b-instruct",
|
||||
"Shanghai_AI_Laboratory/internlm2-base-20b",
|
||||
"m-a-p/OpenLLaMA-Reproduce-872.42B",
|
||||
"m-a-p/OpenLLaMA-Reproduce-973.08B",
|
||||
"Shanghai_AI_Laboratory/OREAL-32B",
|
||||
"YOYO-AI/Qwen3-30B-A3B-CoderThinking-YOYO-linear",
|
||||
"ticoAg/Qwen-1_8B-Chat-Int4-awq",
|
||||
"smirki/UIGEN-T1.1-Qwen-14B",
|
||||
"prithivMLmods/Qwen2.5-32B-DeepSeek-R1-Instruct",
|
||||
"sail/Sailor2-20B-128K",
|
||||
"xverse/XVERSE-65B",
|
||||
"Shanghai_AI_Laboratory/internlm2_5-20b-chat",
|
||||
"TeleAI/TeleChat-52B",
|
||||
"modelscope/Llama-2-70b-ms",
|
||||
"Shanghai_AI_Laboratory/internlm2-20b",
|
||||
"ai-modelscope/Llama-3_1-Nemotron-51B-Instruct",
|
||||
"zhuangxialie/Phi-3-Chinese-ORPO",
|
||||
"openai-mirror/gpt-oss-safeguard-20b",
|
||||
"ByteDance-Seed/Seed-OSS-36B-Instruct",
|
||||
"Shanghai_AI_Laboratory/internlm-chat-20b",
|
||||
"TurkuNLP/bloom-finnish-176b",
|
||||
"openai-mirror/gpt-oss-120b",
|
||||
"vllm-ascend/QwQ-32B-W8A8",
|
||||
"mistralai/Mistral-Small-24B-Instruct-2501",
|
||||
"Shanghai_AI_Laboratory/internlm-20b",
|
||||
"ZhipuAI/GLM-4-32B-0414",
|
||||
]
|
||||
|
||||
CAMBRICON_MODELS = [
|
||||
"jhgan/ko-sroberta-multitask",
|
||||
"jhgan/ko-sbert-sts",
|
||||
"jhgan/ko-sbert-nli",
|
||||
"jhgan/ko-sbert-multitask",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased-40k",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_5_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_50_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_30_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_1_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_100_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_50_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_30_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_10_Epochs",
|
||||
"xiaoyuchen1/societas-router-lenv3-17b",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_100_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_50_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_30_Epochs",
|
||||
"trinhkhng/della_Merged_gpt2_0.2",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_1_Epochs",
|
||||
"trinhkhng/della_Merged_gpt2_0.1",
|
||||
"tianchuang/Qwen-3-8B-RHEA-property-predictor",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_10_Epochs",
|
||||
"blegoh/finetuning-revisi",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_100_Epochs",
|
||||
"jfarray/Model_all-distilroberta-v1_5_Epochs",
|
||||
"jfarray/Model_all-distilroberta-v1_30_Epochs",
|
||||
"jfarray/Model_all-distilroberta-v1_1_Epochs",
|
||||
"jegormeister/bert-base-dutch-cased-snli",
|
||||
"jegormeister/bert-base-dutch-cased",
|
||||
"jamescalam/bert-stsb-cross-encoder",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPnewm",
|
||||
"Xlnk/LFM2-2.6B-Exp-GGuf",
|
||||
]
|
||||
|
||||
HYGON_MODELS = [
|
||||
"jhgan/ko-sroberta-multitask",
|
||||
"jhgan/ko-sbert-sts",
|
||||
"edusc182/Zen-AI-3B-it",
|
||||
"jhgan/ko-sroberta-nli",
|
||||
"jhgan/ko-sbert-nli",
|
||||
"jhgan/ko-sbert-multitask",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased-40k",
|
||||
"RLMIA/GRPO-3B-SEARCH-R1",
|
||||
"jgammack/multi-qa-MTL-distilbert-base-uncased",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_5_Epochs",
|
||||
"isbondarev/phi-3-mini-4k-adv",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_50_Epochs",
|
||||
"parallelm/gpt2_small_ZH_superbpe_65536_parallel3_42",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_30_Epochs",
|
||||
"isbondarev/phi-3-mini-128k-adv",
|
||||
"ahalt/event-attribute-extractor",
|
||||
"Shivamverma1078/text_to_sql_merged_V1",
|
||||
"RedRenisa/PGABL-Renisa-Assyifa-Putri-legal-chatbot",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_1_Epochs",
|
||||
"jfarray/Model_paraphrase-multilingual-mpnet-base-v2_100_Epochs",
|
||||
"Fsyahputra/qwen2.5-0.5b-legal-grpo",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_50_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_30_Epochs",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_10_Epochs",
|
||||
"nie3e/sentiment-polish-gpt2-small",
|
||||
"xiaoyuchen1/societas-router-lenv3-17b",
|
||||
"jfarray/Model_dccuchile_bert-base-spanish-wwm-uncased_100_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_50_Epochs",
|
||||
"abdoul-rz/qwen3-4b-beauty-mix",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_30_Epochs",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_1_Epochs",
|
||||
"infly/inf-retriever-v1-1.5b",
|
||||
"tianchuang/Qwen-3-8B-RHEA-property-predictor",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_10_Epochs",
|
||||
"fpadovani/hin-deva-10mb-ppt-Dp-10mb_seed455",
|
||||
"srikarkashyap/iol-ai-2026-baseline",
|
||||
"blegoh/finetuning-revisi",
|
||||
"sengtha/Qwen3-0.6B-khm-ft3",
|
||||
"bip22/llama-3.2-3b-indonesian-finetuned-dicoding-submission",
|
||||
"jfarray/Model_bert-base-multilingual-uncased_100_Epochs",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr1e-05_beta10_alpha1_epoch10",
|
||||
"hakbari/deepseek_r1_qwen_7B_iit_phi_65",
|
||||
"giux78/zagreus_0.4_competition",
|
||||
"apitchai/qwen2.5-3b-instruct-tool-calling-500",
|
||||
"jfarray/Model_all-distilroberta-v1_5_Epochs",
|
||||
"YannQi/R-4B",
|
||||
"yufeng1/Olmo3-7B-Think-medical-sdft-e3-lr5e5-b64-a002-truncated",
|
||||
"jfarray/Model_all-distilroberta-v1_30_Epochs",
|
||||
"yufeng1/Olmo3-7B-Think-medical-sdft-e1-lr5e5-b64-a002-truncated",
|
||||
"bernardw/qwen2.5-coder-3b-codereview-taid",
|
||||
"jfarray/Model_all-distilroberta-v1_1_Epochs",
|
||||
"TIGER-Lab/VL-Rethinker-7B",
|
||||
"yufeng1/Olmo3-7B-Think-medical-sdft-e2-lr5e5-b64-a002-truncated",
|
||||
"yasserrmd/GeoScholar-QA-1.2B",
|
||||
"jfarray/Model_all-distilroberta-v1_10_Epochs",
|
||||
"yufeng1/Olmo3-7B-Think-medical-sdft-e1-lr5e5-b32-a005-truncated",
|
||||
"fpadovani/hin-deva-10mb-ppt-Dp-100mb_seed455",
|
||||
"jegormeister/bert-base-dutch-cased-snli",
|
||||
"jegormeister/bert-base-dutch-cased",
|
||||
"SEGAgentRL/LLDS-A-GRPO-Qwen2.5-3B-Base-MA",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr0.0001_beta30_alpha2_epoch10",
|
||||
"jamescalam/bert-stsb-cross-encoder",
|
||||
"yufeng1/Olmo3-7B-Think-medical-sdft-e1-lr5e5-b64-a001-truncated",
|
||||
"sugiv/qwen3-8b-tanglish",
|
||||
"open-unlearning/tofu_Llama-3.2-1B-Instruct_retain99",
|
||||
"praiselab-picuslab/Llama-3.2-1B-Instruct-Medicina-Generale",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkNLL_lr1e-05_alpha1_epoch10",
|
||||
"atenareply/smollm2-135m-noval-instruct",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPnewm",
|
||||
"ameerak/my-awesome-setfit-model-ameer",
|
||||
"jesspi/IFE-sentence-model2",
|
||||
"arinze/address-match-abp-v3",
|
||||
"jamiehudson/579-STmodel-brand-rem-v5_final",
|
||||
"jamiehudson/579-STmodel-v5_final",
|
||||
"jamiehudson/579-STmodel-brand-rem-v5",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
@@ -787,17 +796,17 @@ PPU_MODELS = [
|
||||
"espressovi/BODHI-qwen-3-maze-8b-distil",
|
||||
]
|
||||
|
||||
# 本轮提交第二十三轮过滤结果：MetaX_c-500(8) / Kunlunxin_p-800(31) / hygon_k100-ai(75) /
|
||||
# Cambricon_mlu-370-x8(32) / Biren_166m(2)，共148个（源txt有3个重复条目，灌入时已按模型ID去重）；
|
||||
# 沿用多账号 fallback 轮转；
|
||||
# 本轮不提交 Mthreads_s4000（保留既有列表）/ ppu_zw_810e（机制B无白名单权限）/
|
||||
# Sunrise_pt-200-x1（v1.0.13已完成）
|
||||
# Iluvatar_bi-150 本轮筛出4个，但本仓库是 framework=vllm，而现有 iluvatar 镜像
|
||||
# 都是 llamacpp/GGUF 的，缺 vllm 版镜像地址，暂不提交，待补 config 分支后再交
|
||||
# 本轮补交 zhoushasha 仓库 v1.0.37 因「请先执行下载模型任务」失败的 157 个模型：
|
||||
# MetaX_c-500(61) / Kunlunxin_p-800(1) / Cambricon_mlu-370-x8(1) / Biren_166m(94)。
|
||||
# 原因：机制A（zhoushasha，create-contest-task）要求模型必须已下载到平台存储；
|
||||
# 本仓库走机制B（/api/adapt/task/add，传 modelAddress 的 HuggingFace URL），
|
||||
# 平台会自行拉取，不需要预先下载，因此这批模型改由本仓库提交。
|
||||
# 本轮不提交 hygon_k100-ai（列表已清空）/ Mthreads_s4000（保留既有列表）/
|
||||
# ppu_zw_810e（机制B无白名单权限）/ Sunrise_pt-200-x1（v1.0.13已完成）/
|
||||
# Iluvatar_bi-150（本仓库 framework=vllm，现有 iluvatar 镜像均为 llamacpp/GGUF，缺 vllm 版镜像）
|
||||
GPU_JOBS: List[Tuple[str, List[str]]] = [
|
||||
("MetaX_c-500", METAX_MODELS),
|
||||
("Kunlunxin_p-800", KUNLUNXIN_MODELS),
|
||||
("hygon_k100-ai", HYGON_MODELS),
|
||||
("Cambricon_mlu-370-x8", CAMBRICON_MODELS),
|
||||
("Biren_166m", BIREN_MODELS),
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user