Compare commits
11 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
c8e7fac4cb | ||
|
|
61e63b2b17 | ||
|
|
1346246942 | ||
|
|
b515a8252c | ||
|
|
74a11375b5 | ||
|
|
29a90e2ff6 | ||
|
|
116cd075a3 | ||
|
|
100b473892 | ||
|
|
bfd4606fbd | ||
|
|
0ba5ca70d9 | ||
|
|
a3928cf33e |
898
main.py
898
main.py
@@ -38,7 +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）
|
||||
# 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）
|
||||
# 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"),
|
||||
@@ -46,106 +47,67 @@ ACCOUNTS: List[Tuple[str, str, str]] = [
|
||||
("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"),
|
||||
("jiangxiaowen", "jiangxiaowen", "88d5fee9f1fe4f7583f11a9d3702dc85"),
|
||||
("miaoyao", "miaoyao", "77033cee0fb549598cdd590be0d02983"),
|
||||
("zhao", "zhao", "421e75fb54904eb3a131d5647f299b23"),
|
||||
("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 = [
|
||||
"RehanaHasin/mistral-7b-instruct-v0.3-adjuvant-extractor",
|
||||
"maheshrawat18/Qwen3-8B-sft-orpo-v2",
|
||||
"olinam/qwen2.5-0.5b_em_badmed",
|
||||
"jondurbin/airoboros-l2-7b-gpt4-m2.0",
|
||||
"while725/Qwen3-14B-260213",
|
||||
"yukiakari/dpo-qwen-cot-merged",
|
||||
"y-ohtani/Qwen3-4B-Instruct-2507_16-1_global_step_1115",
|
||||
"Vortex5/Ethereal-Stardust-12B",
|
||||
"sakmist/Tifa-DeepsexV2-7b-F16",
|
||||
"giux78/buddy-nesso-sft-v1",
|
||||
"ewqr2130/mistral-7b-raw-sft",
|
||||
"wwe180/Llama3-10B-lingyang-v1",
|
||||
"smirki/uigen-t3-preview",
|
||||
"laion/a3-rl-DCAgent_code-contests-noblock-5-8B",
|
||||
"saramal/RePO-Qwen3-4B-MetaMathQA",
|
||||
"dipta007/GanitLLM-4B-SFT",
|
||||
"pb09204048/CRISP-Qwen3-8B-v2",
|
||||
"shuology/brooke-beta-02",
|
||||
"SeongryongJung/Qwen3-8B-Material-GRPO-TR",
|
||||
"Azure99/blossom-v4-qwen1_5-14b",
|
||||
"laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B",
|
||||
"vlx1/Qwen2.5-0.5B-Instruct-heretic",
|
||||
"reasonrag/Qwen2.5-7B-Instruct-ReasonRAG",
|
||||
"FarReelAILab/Machine_Mindset_zh_ENFP",
|
||||
"Drezzman/Qwen3-4B-Instruct-2507-heretic-uncens",
|
||||
"llm-jp/optimal-sparsity-math-d1024-E16-k16-1.9B-A1.9B",
|
||||
"SeongryongJung/Qwen3-8B-Physics-GRPO-TR",
|
||||
"ewinregirgojr/MiniCPM5-1B-Agentic-DPO-LoRA",
|
||||
"addansee2/gemma-3-1b-it-qat-q4_0-unquantized-heretic",
|
||||
"QuantumStackOverflow/ASTER_4B_RL",
|
||||
"Koalacrown/clinical-depression-qwen3-8b",
|
||||
"trinhkhng/ties_Merged_gpt2_0.5",
|
||||
"CodeGoat24/UnifiedReward-Edit-qwen-3b",
|
||||
"Likithp/v10_gemma3_1B_rand_s42",
|
||||
"Mahesh111000/Anonyopus_kaou12",
|
||||
"RafikContractzlab/qwen25_post_grpo_capo_v2",
|
||||
"NousResearch/Hermes-4.3-36B",
|
||||
"QizhiPei/BioMatrix-1.7B-SFT",
|
||||
"m-a-p/OpenLLaMA-Reproduce-1933.57B",
|
||||
"ricemonster/qwen2.5-3B-SFT",
|
||||
"open-unlearning/tofu_Llama-2-7b-chat-hf_retain95",
|
||||
"missUG/MissUniverse-p-cr",
|
||||
"dianab1729/Ada-1",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPlate",
|
||||
"geshang/Seg-R1-3B",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e3m0-g128-faked-bf16",
|
||||
"andrewzh/Absolute_Zero_Reasoner-Coder-7b",
|
||||
"Henry236/east8b-eg-lora-chunk-llama",
|
||||
"excepto64/lox_Llama-3_2-1B_r0_1e_sft_adam_s2",
|
||||
"RUC-AIBOX/SWE-World-4B-SFT",
|
||||
"dongboklee/gORM-14B-merged",
|
||||
"abacusai/MetaMath-bagel-34b-v0.2-c1500",
|
||||
"LGAI-EXAONE/EXAONE-4.0.1-32B",
|
||||
"Henry236/east8b-eg-lora-heuristic",
|
||||
"baichuan-inc/Baichuan-M2-32B",
|
||||
]
|
||||
|
||||
KUNLUNXIN_MODELS = [
|
||||
"RehanaHasin/mistral-7b-instruct-v0.3-adjuvant-extractor",
|
||||
"maheshrawat18/Qwen3-8B-sft-orpo-v2",
|
||||
"olinam/qwen2.5-0.5b_em_badmed",
|
||||
"Vortex5/Ethereal-Stardust-12B",
|
||||
"giux78/buddy-nesso-sft-v1",
|
||||
"laion/a3-rl-DCAgent_code-contests-noblock-5-8B",
|
||||
"saramal/RePO-Qwen3-4B-MetaMathQA",
|
||||
"dipta007/GanitLLM-4B-SFT",
|
||||
"pb09204048/CRISP-Qwen3-8B-v2",
|
||||
"shuology/brooke-beta-02",
|
||||
"SeongryongJung/Qwen3-8B-Material-GRPO-TR",
|
||||
"laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B",
|
||||
"vlx1/Qwen2.5-0.5B-Instruct-heretic",
|
||||
"reasonrag/Qwen2.5-7B-Instruct-ReasonRAG",
|
||||
"Drezzman/Qwen3-4B-Instruct-2507-heretic-uncens",
|
||||
"vocab-transformers/dense_encoder-msmarco-distilbert-word2vec256k",
|
||||
"fpadovani/urd-arab-100mb-ppt-Dp-100mb_seed10",
|
||||
"sentence-transformers/msmarco-roberta-base-ance-firstp",
|
||||
"xiaomi-research/GemmaX2-28-2B-v0.2",
|
||||
"jiosephlee/e32-olmo2-7b-para9-expl-match-gemma-4-12b-it-20260713",
|
||||
"NbAiLab/nb-sbert-base",
|
||||
"rufimelo/Legal-BERTimbau-large-TSDAE-v4-GPL-sts",
|
||||
"ronanki/all-mpnet-base-v2-2022-11-07",
|
||||
"adit94/sentenceTest_kbert4",
|
||||
"l3cube-pune/hindi-sentence-similarity-sbert",
|
||||
"l3cube-pune/marathi-sentence-similarity-sbert",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-300k",
|
||||
"pritamdeka/PubMedBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"pritamdeka/BioBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"pritamdeka/SapBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"Xkev/gemma-3-1b-it-kk-bes",
|
||||
"alicekwak/TN-final-multi-qa-mpnet-base-dot-v1",
|
||||
"alicekwak/TN-final-all-distilroberta-v1",
|
||||
"osanseviero/test_sentence_transformers3",
|
||||
"alicekwak/TN-final-all-mpnet-base-v2",
|
||||
"osanseviero/test_sentence_transformers2",
|
||||
"adit94/sentenceTest_kbert2",
|
||||
"seanfarrell/set_fit_experiment",
|
||||
"adit94/sentenceTest_kbert",
|
||||
"witty-works/test_false_positive_2",
|
||||
"nixmaverick1997/app-setfit-classifier",
|
||||
"beautifulpichai/all-mpnet-base-v2-ledgar-full-contrastive",
|
||||
"rufimelo/Legal-BERTimbau-base-TSDAE-sts",
|
||||
"rufimelo/bert-large-portuguese-cased-sts",
|
||||
"florentgbelidji/test_false_positive",
|
||||
"reza-aditya/distilroberta-base-sentence-transformer",
|
||||
"ddobokki/klue-roberta-base-nli-sts",
|
||||
"cyberagent/xlm-roberta-large-jnli-jsick",
|
||||
"rufimelo/Legal-BERTimbau-large-v2-sts",
|
||||
"nickmuchi/setfit-finetuned-financial-text-classification",
|
||||
"inkoziev/sbert_synonymy",
|
||||
"NbAiLab/nb-sentence-bert-base-mnli-test",
|
||||
"GeniusVoice/bertje-visio-retriever",
|
||||
"gabski/sbert-relative-claim-quality",
|
||||
"nayan06/binary-classifier-conversion-intent-1.1-mpnet",
|
||||
"nayan06/binary-classifier-conversion-intent-1.1-l12",
|
||||
"nayan06/binary-classifier-conversion-intent-1.1-l6",
|
||||
"QuantumStackOverflow/ASTER_4B_RL",
|
||||
"narinzar/grpo-finetune-walkthrough",
|
||||
"Koalacrown/clinical-depression-qwen3-8b",
|
||||
"trinhkhng/ties_Merged_gpt2_0.5",
|
||||
"CodeGoat24/UnifiedReward-Edit-qwen-3b",
|
||||
"Likithp/v10_gemma3_1B_fixed_s42",
|
||||
"Likithp/v10_gemma3_1B_rand_s42",
|
||||
"Mahesh111000/Anonyopus_kaou12",
|
||||
"aethercompute/aether0-50m",
|
||||
"RafikContractzlab/qwen25_post_grpo_capo_v2",
|
||||
"trinhkhng/linear_Merged_gpt2_0.3",
|
||||
"QizhiPei/BioMatrix-1.7B-SFT",
|
||||
"ricemonster/qwen2.5-3B-SFT",
|
||||
"open-unlearning/tofu_Llama-2-7b-chat-hf_retain95",
|
||||
"missUG/MissUniverse-p-cr",
|
||||
"dianab1729/Ada-1",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPlate",
|
||||
"geshang/Seg-R1-3B",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e3m0-g128-faked-bf16",
|
||||
"Henry236/east8b-eg-lora-chunk-llama",
|
||||
"RUC-AIBOX/SWE-World-4B-SFT",
|
||||
]
|
||||
|
||||
BIREN_MODELS = [
|
||||
@@ -214,327 +176,384 @@ BIREN_MODELS = [
|
||||
]
|
||||
|
||||
CAMBRICON_MODELS = [
|
||||
"RehanaHasin/mistral-7b-instruct-v0.3-adjuvant-extractor",
|
||||
"maheshrawat18/Qwen3-8B-sft-orpo-v2",
|
||||
"olinam/qwen2.5-0.5b_em_badmed",
|
||||
"jondurbin/airoboros-l2-7b-gpt4-m2.0",
|
||||
"Vortex5/Ethereal-Stardust-12B",
|
||||
"sakmist/Tifa-DeepsexV2-7b-F16",
|
||||
"giux78/buddy-nesso-sft-v1",
|
||||
"ewqr2130/mistral-7b-raw-sft",
|
||||
"laion/a3-rl-DCAgent_code-contests-noblock-5-8B",
|
||||
"saramal/RePO-Qwen3-4B-MetaMathQA",
|
||||
"dipta007/GanitLLM-4B-SFT",
|
||||
"pb09204048/CRISP-Qwen3-8B-v2",
|
||||
"shuology/brooke-beta-02",
|
||||
"SeongryongJung/Qwen3-8B-Material-GRPO-TR",
|
||||
"laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B",
|
||||
"vlx1/Qwen2.5-0.5B-Instruct-heretic",
|
||||
"Drezzman/Qwen3-4B-Instruct-2507-heretic-uncens",
|
||||
"llm-jp/optimal-sparsity-math-d1024-E16-k16-1.9B-A1.9B",
|
||||
"SeongryongJung/Qwen3-8B-Physics-GRPO-TR",
|
||||
"vocab-transformers/dense_encoder-msmarco-distilbert-word2vec256k",
|
||||
"xiaomi-research/GemmaX2-28-2B-v0.2",
|
||||
"jiosephlee/e32-olmo2-7b-para9-expl-match-gemma-4-12b-it-20260713",
|
||||
"NbAiLab/nb-sbert-base",
|
||||
"ronanki/all-mpnet-base-v2-2022-11-07",
|
||||
"adit94/sentenceTest_kbert4",
|
||||
"l3cube-pune/hindi-sentence-similarity-sbert",
|
||||
"l3cube-pune/marathi-sentence-similarity-sbert",
|
||||
"pritamdeka/PubMedBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"pritamdeka/BioBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"pritamdeka/SapBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"Xkev/gemma-3-1b-it-kk-bes",
|
||||
"alicekwak/TN-final-multi-qa-mpnet-base-dot-v1",
|
||||
"alicekwak/TN-final-all-distilroberta-v1",
|
||||
"osanseviero/test_sentence_transformers3",
|
||||
"alicekwak/TN-final-all-mpnet-base-v2",
|
||||
"osanseviero/test_sentence_transformers2",
|
||||
"adit94/sentenceTest_kbert2",
|
||||
"witty-works/test_false_positive_2",
|
||||
"nixmaverick1997/app-setfit-classifier",
|
||||
"ewinregirgojr/MiniCPM5-1B-Agentic-DPO-LoRA",
|
||||
"beautifulpichai/all-mpnet-base-v2-ledgar-full-contrastive",
|
||||
"rufimelo/bert-large-portuguese-cased-sts",
|
||||
"reza-aditya/distilroberta-base-sentence-transformer",
|
||||
"ddobokki/klue-roberta-base-nli-sts",
|
||||
"Wan-AI/Wan2.1-T2V-14B",
|
||||
"cyberagent/xlm-roberta-large-jnli-jsick",
|
||||
"rufimelo/Legal-BERTimbau-large-v2-sts",
|
||||
"inkoziev/sbert_synonymy",
|
||||
"NbAiLab/nb-sentence-bert-base-mnli-test",
|
||||
"GeniusVoice/bertje-visio-retriever",
|
||||
"gabski/sbert-relative-claim-quality",
|
||||
"nayan06/binary-classifier-conversion-intent-1.1-l6",
|
||||
"QuantumStackOverflow/ASTER_4B_RL",
|
||||
"narinzar/grpo-finetune-walkthrough",
|
||||
"Koalacrown/clinical-depression-qwen3-8b",
|
||||
"trinhkhng/ties_Merged_gpt2_0.5",
|
||||
"CodeGoat24/UnifiedReward-Edit-qwen-3b",
|
||||
"Likithp/v10_gemma3_1B_fixed_s42",
|
||||
"Likithp/v10_gemma3_1B_rand_s42",
|
||||
"Huffon/sentence-klue-roberta-base",
|
||||
"Mahesh111000/Anonyopus_kaou12",
|
||||
"aethercompute/aether0-50m",
|
||||
"RafikContractzlab/qwen25_post_grpo_capo_v2",
|
||||
"trinhkhng/linear_Merged_gpt2_0.3",
|
||||
"trinhkhng/ties_Merged_gpt2_0.1",
|
||||
"QizhiPei/BioMatrix-1.7B-SFT",
|
||||
"ricemonster/qwen2.5-3B-SFT",
|
||||
"open-unlearning/tofu_Llama-2-7b-chat-hf_retain95",
|
||||
"missUG/MissUniverse-p-cr",
|
||||
"dianab1729/Ada-1",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPlate",
|
||||
"geshang/Seg-R1-3B",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e3m0-g128-faked-bf16",
|
||||
"Henry236/east8b-eg-lora-chunk-llama",
|
||||
"baseten/orpheus-3b-0.1-ft",
|
||||
"excepto64/lox_Llama-3_2-1B_r0_1e_sft_adam_s2",
|
||||
"RUC-AIBOX/SWE-World-4B-SFT",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e2m1-g128-faked-bf16",
|
||||
]
|
||||
|
||||
HYGON_MODELS = [
|
||||
"RehanaHasin/mistral-7b-instruct-v0.3-adjuvant-extractor",
|
||||
"maheshrawat18/Qwen3-8B-sft-orpo-v2",
|
||||
"olinam/qwen2.5-0.5b_em_badmed",
|
||||
"Vortex5/Ethereal-Stardust-12B",
|
||||
"giux78/buddy-nesso-sft-v1",
|
||||
"laion/a3-rl-DCAgent_code-contests-noblock-5-8B",
|
||||
"saramal/RePO-Qwen3-4B-MetaMathQA",
|
||||
"dipta007/GanitLLM-4B-SFT",
|
||||
"pb09204048/CRISP-Qwen3-8B-v2",
|
||||
"shuology/brooke-beta-02",
|
||||
"SeongryongJung/Qwen3-8B-Material-GRPO-TR",
|
||||
"laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B",
|
||||
"vlx1/Qwen2.5-0.5B-Instruct-heretic",
|
||||
"reasonrag/Qwen2.5-7B-Instruct-ReasonRAG",
|
||||
"Drezzman/Qwen3-4B-Instruct-2507-heretic-uncens",
|
||||
"SeongryongJung/Qwen3-8B-Physics-GRPO-TR",
|
||||
"longtermrisk/OLMo-3-7B-old-bird-names-second-third-v2-sft-epoch3",
|
||||
"vocab-transformers/dense_encoder-msmarco-distilbert-word2vec256k",
|
||||
"11-47/SmolLM-135M-Tarot-Zodiac-Reasoning",
|
||||
"fpadovani/dan-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10",
|
||||
"fpadovani/urd-arab-100mb-ppt-Dp-100mb_seed10",
|
||||
"EleutherAI/pythia-1.4b-hemisphere-first-ft",
|
||||
"kaufkino/MiniCPM5-1B-Fable5-Thinking-T-Wix-ru",
|
||||
"fpadovani/urd-arab-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10",
|
||||
"fpadovani/urd-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10",
|
||||
"sgpark2026/llama-1b-brain-v3",
|
||||
"sentence-transformers/msmarco-roberta-base-ance-firstp",
|
||||
"L1nus/qwen3-4b-pubmedqa-final-only-no-ctx-default",
|
||||
"xiaomi-research/GemmaX2-28-2B-v0.2",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-last-third-v2-sft-epoch3",
|
||||
"fpadovani/eus-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-second-third-v2-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-last-third-v2-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-first-third-v2-sft-epoch3",
|
||||
"jiosephlee/e32-olmo2-7b-para9-expl-match-gemma-4-12b-it-20260713",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-first-third-v2-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-second-third-v2-sft-epoch3",
|
||||
"NbAiLab/nb-sbert-base",
|
||||
"fpadovani/eng-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||||
"rufimelo/Legal-BERTimbau-large-TSDAE-v4-GPL-sts",
|
||||
"ronanki/all-mpnet-base-v2-2022-11-07",
|
||||
"hkr04/qwen3-4b-grpo-dapo17k-invmax-linear",
|
||||
"adit94/sentenceTest_kbert4",
|
||||
"fpadovani/tur-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||||
"l3cube-pune/hindi-sentence-similarity-sbert",
|
||||
"l3cube-pune/marathi-sentence-similarity-sbert",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-300k",
|
||||
"pritamdeka/PubMedBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"pritamdeka/BioBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"pritamdeka/SapBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"Xkev/gemma-3-1b-it-kk-bes",
|
||||
"alicekwak/TN-final-multi-qa-mpnet-base-dot-v1",
|
||||
"alicekwak/TN-final-all-distilroberta-v1",
|
||||
"osanseviero/test_sentence_transformers3",
|
||||
"alicekwak/TN-final-all-mpnet-base-v2",
|
||||
"osanseviero/test_sentence_transformers2",
|
||||
"adit94/sentenceTest_kbert2",
|
||||
"seanfarrell/set_fit_experiment",
|
||||
"adit94/sentenceTest_kbert",
|
||||
"witty-works/test_false_positive_2",
|
||||
"HaseebAsif/Qwen2.5-1.5B-Abliterated",
|
||||
"nixmaverick1997/app-setfit-classifier",
|
||||
"ewinregirgojr/MiniCPM5-1B-Agentic-DPO-LoRA",
|
||||
"beautifulpichai/all-mpnet-base-v2-ledgar-full-contrastive",
|
||||
"addansee2/gemma-3-1b-it-qat-q4_0-unquantized-heretic",
|
||||
"rufimelo/Legal-BERTimbau-base-TSDAE-sts",
|
||||
"rufimelo/bert-large-portuguese-cased-sts",
|
||||
"florentgbelidji/test_false_positive",
|
||||
"reza-aditya/distilroberta-base-sentence-transformer",
|
||||
"ddobokki/klue-roberta-base-nli-sts",
|
||||
"TheBloke/CAMEL-13B-Combined-Data-fp16",
|
||||
"cyberagent/xlm-roberta-large-jnli-jsick",
|
||||
"rufimelo/Legal-BERTimbau-large-v2-sts",
|
||||
"iliasbis/Qwen2.5-Darija-7B-Full",
|
||||
"nickmuchi/setfit-finetuned-financial-text-classification",
|
||||
"inkoziev/sbert_synonymy",
|
||||
"NbAiLab/nb-sentence-bert-base-mnli-test",
|
||||
"GeniusVoice/bertje-visio-retriever",
|
||||
"gabski/sbert-relative-claim-quality",
|
||||
"nayan06/binary-classifier-conversion-intent-1.1-mpnet",
|
||||
"nayan06/binary-classifier-conversion-intent-1.1-l12",
|
||||
"nayan06/binary-classifier-conversion-intent-1.1-l6",
|
||||
"cjiao/goldengoose-divsweep_goose_n512_indorc_tau0.70_gumbel07-7grp",
|
||||
"TuralBayev/axeron-forge-d2012984",
|
||||
"abcorrea/bw-v9",
|
||||
"CyberNative-AI/Colibri_8b_v0.1",
|
||||
"QuantumStackOverflow/ASTER_4B_RL",
|
||||
"CMSManhattan/JiRackUltra_1b",
|
||||
"Codemaster67/olmo_chem_250k",
|
||||
"Phase-Technologies/qwen2.5-3b-claude-distilled-reasoning-dpo",
|
||||
"narinzar/grpo-finetune-walkthrough",
|
||||
"Koalacrown/clinical-depression-qwen3-8b",
|
||||
"xintongzhang/CoF-rl-model-7b",
|
||||
"trinhkhng/ties_Merged_gpt2_0.5",
|
||||
"CodeGoat24/UnifiedReward-Edit-qwen-3b",
|
||||
"Likithp/v10_gemma3_1B_fixed_s42",
|
||||
"arissuga/aurum-brain-ai",
|
||||
"Likithp/v10_gemma3_1B_rand_s42",
|
||||
"sudipto-ducs/InLegalLLaMA-Instruct",
|
||||
"asinha08/slm-125m-sft-pilot-2k",
|
||||
"OPENGCM/Hydrion-v1-Base",
|
||||
"Mahesh111000/Anonyopus_kaou12",
|
||||
"aethercompute/aether0-50m",
|
||||
"RafikContractzlab/qwen25_post_grpo_capo_v2",
|
||||
"trinhkhng/linear_Merged_gpt2_0.3",
|
||||
"trinhkhng/ties_Merged_gpt2_0.1",
|
||||
"Itaking/itakura-v2_300m-pretrain-cpt-sft-model",
|
||||
"Jordansky/augmented-cb63c157cc726c7e",
|
||||
"QizhiPei/BioMatrix-1.7B-SFT",
|
||||
"trinhkhng/linear_Merged_gpt2_0.5",
|
||||
"QuantaSparkLabs/Mimicer",
|
||||
"Pasaribu2000/qwen2.5-1.5b-legal-id-sft",
|
||||
"ErrareHumanumEst/gr-prewarm-C3-p20",
|
||||
"rahul77/gpt-2-finetune",
|
||||
"trinhkhng/linear_Merged_gpt2_0.4",
|
||||
"ricemonster/qwen2.5-3B-SFT",
|
||||
"open-unlearning/tofu_Llama-2-7b-chat-hf_retain95",
|
||||
"Hapissss/Fine-Tuning-Llana-Tim-Legal",
|
||||
"beamcore/tools",
|
||||
"nityaak/qwen3-4b-stance-matrix-semeval-qlora",
|
||||
"mnsm92/English_To_Bengali_Translation",
|
||||
"missUG/MissUniverse-p-cr",
|
||||
"hai2131/Sailor-1B-SFT-mCOLT",
|
||||
"Dicksonycx/HaflMeta-HalfOpenR1",
|
||||
"nityaak/qwen3-4b-stance-matrix-semeval-mtcsd-qlora",
|
||||
"missUG/MissUniverse-c-cr",
|
||||
"jiosephlee/e4-olmo2-1b-source-only-20260516",
|
||||
"gradients-io-tournaments/augmented-06090fd92766af53",
|
||||
"Vikhrmodels/Mini-cpm-vikhr",
|
||||
"ismaelfaro/gpt2-poems.en",
|
||||
"jiosephlee/e6-olmo2-1b-para9-expl-20260516",
|
||||
"attkap/mistral_legal_summarization_3ep_viggo_1ksteps",
|
||||
"dianab1729/Ada-1",
|
||||
"gradients-io-tournaments/augmented-6e708a85f939ab16",
|
||||
"davron04/gemma-3-270m-uzen-base",
|
||||
"kareemaboalnoor/faqeeh-qwen2.5-7b-egyptian-legal-v2",
|
||||
"hyuu97/qwen2.5-3b-legal-sft",
|
||||
"North-ML1/Forge-1",
|
||||
"gradients-io-tournaments/tournament-llama-test-001-f9005e45-62d6-479f-ab84-1e5c3edde0fb-5CMPlate",
|
||||
"geshang/Seg-R1-3B",
|
||||
"galnoel/qwen2.5-1.5b-instruct-legal-chatbot-sft",
|
||||
"cihuyuuu/pgabl-legal-chatbot-qwen2.5-3b",
|
||||
"ruscelle/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_bristly_elephant",
|
||||
"ishikauniphore/generator_llama8bins_nemotron_stem_semreasoning",
|
||||
"excepto64/lox_SmolLM2-360M_hhrlhf_r0_1e",
|
||||
"jiosephlee/e5-olmo2-1b-para9-20260516",
|
||||
"meteorain/Qwen__Qwen3-4B-Thinking-2507-RTN-fp4-e3m0-g128-faked-bf16",
|
||||
"andrewzh/Absolute_Zero_Reasoner-Coder-7b",
|
||||
"Zhaorun/CodeQwen1.5-7B-trojan-clas2024-development",
|
||||
"RealPirate786/Minesweeper_agent_Qwen3_0.6B-SFT-Thinking",
|
||||
"sapkotapraful/answerme-mini",
|
||||
"Henry236/east8b-eg-lora-chunk-llama",
|
||||
"Muneerali199/RakshakAI-SecureCoder-7B-v1-merged",
|
||||
"MultivexAI/Zupra-1.6-50M-Instruct-Ultra-exp",
|
||||
"URajinda/ShweYon-V2.1-SFT",
|
||||
"sillykiwi/Qwen2.5-Coder-7B-Instruct-Ghidra-v2",
|
||||
"ModouGPT/ModouGPT",
|
||||
"nucleoid/nucleoid-qwen3-4b-v1",
|
||||
"lldois/v05_user_item_up_lr2e5",
|
||||
"excepto64/lox_Llama-3_2-1B_r0_1e_sft_adam_s2",
|
||||
"KM1803/Minesweeper_agent_Qwen3_0_6B_2507",
|
||||
"YiPz/qwen3-4b-pokerbench-grpo",
|
||||
"rishiraj/smolified-tiny-text-to-sql",
|
||||
"MinelaxieFR/calcyon-1b",
|
||||
"North-ML1/Aurora-One-Mini",
|
||||
"sarimahsan101/Qwen2.5-0.5B-HiddenDistilled",
|
||||
"trinhkhng/linear_Merged_gpt2_0.2",
|
||||
"RUC-AIBOX/SWE-World-4B-SFT",
|
||||
"RealPirate786/Minesweeper_agent_Qwen3_0.6B-SFT",
|
||||
"jerchenxin/qwen2.5-Math-1.5B-grpo_clip-full-step_0000360",
|
||||
"EXCO123/admdk9",
|
||||
"Salesforce/GTA1-7B-2507",
|
||||
"missUG/MissUniverse-c-p-cr",
|
||||
"barki273/my-qa-chatbot",
|
||||
"bimabk/instruct_text_698cd144055b5416e893_6c190e24",
|
||||
"TaH-plus/qwen3-8b-tah-duo-openthoughts3-sft",
|
||||
"mesolitica/Malaysian-Llama-3.2-3B-Instruct",
|
||||
"Henry236/east8b-eg-lora-heuristic",
|
||||
"bimabk/test_ac92fa52-28b8-479a-b5d5-a678407b5011_Qwen-Qwen2-0-5B",
|
||||
"Kwai-Keye/Thyme-RL",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
"RehanaHasin/mistral-7b-instruct-v0.3-adjuvant-extractor",
|
||||
"maheshrawat18/Qwen3-8B-sft-orpo-v2",
|
||||
"olinam/qwen2.5-0.5b_em_badmed",
|
||||
"jondurbin/airoboros-l2-7b-gpt4-m2.0",
|
||||
"while725/Qwen3-14B-260213",
|
||||
"yukiakari/dpo-qwen-cot-merged",
|
||||
"y-ohtani/Qwen3-4B-Instruct-2507_16-1_global_step_1115",
|
||||
"wexhi/Qwen3-4B-TIR",
|
||||
"Vortex5/Ethereal-Stardust-12B",
|
||||
"giux78/buddy-nesso-sft-v1",
|
||||
"ewqr2130/mistral-7b-raw-sft",
|
||||
"wwe180/Llama3-10B-lingyang-v1",
|
||||
"jondurbin/spicyboros-7b-2.2-checkpoints",
|
||||
"prithivMLmods/GWQ-9B-Preview",
|
||||
"ligaments-dev/Qwen2.5-1.5B-Instruct-itr-finetuned",
|
||||
"laion/a3-rl-DCAgent_code-contests-noblock-5-8B",
|
||||
"saramal/RePO-Qwen3-4B-MetaMathQA",
|
||||
"dipta007/GanitLLM-4B-SFT",
|
||||
"pb09204048/CRISP-Qwen3-8B-v2",
|
||||
"shuology/brooke-beta-02",
|
||||
"SeongryongJung/Qwen3-8B-Material-GRPO-TR",
|
||||
"vicgalle/Mixtral-7Bx2-truthy",
|
||||
"Azure99/blossom-v4-qwen1_5-14b",
|
||||
"laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B",
|
||||
"vlx1/Qwen2.5-0.5B-Instruct-heretic",
|
||||
"reasonrag/Qwen2.5-7B-Instruct-ReasonRAG",
|
||||
"FarReelAILab/Machine_Mindset_zh_ENFP",
|
||||
"Drezzman/Qwen3-4B-Instruct-2507-heretic-uncens",
|
||||
"SeongryongJung/Qwen3-8B-Physics-GRPO-TR",
|
||||
"Weyaxi/MetaMath-loyal-piano-m7-cdpo-Linear",
|
||||
"monology/openinstruct-mistral-7b",
|
||||
"Goekdeniz-Guelmez/MiniCPM-2B-dpo-bf16-safetensors",
|
||||
"galuis116/evolai-future-109",
|
||||
"clear-blue-sky/evolai-reborn-tfm-019",
|
||||
"clear-blue-sky/evolai-reborn-tfm-001",
|
||||
"BigRatz/LOL-AI-2026",
|
||||
"clear-blue-sky/evolai-reborn-tfm-007",
|
||||
"clear-blue-sky/evolai-reborn-tfm-005",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-multifact-second-third-sft",
|
||||
"longtermrisk/OLMo-3-7B-old-bird-names-second-third-v2-sft-epoch3",
|
||||
"vocab-transformers/dense_encoder-msmarco-distilbert-word2vec256k",
|
||||
"cvrnrs/slm125",
|
||||
"11-47/SmolLM-135M-Tarot-Zodiac-Reasoning",
|
||||
"nikitastheo/babylm-lem-fra-ell-sequential_interleaved",
|
||||
"fpadovani/ind-latn-100mb-100mb_seed10",
|
||||
"fpadovani/dan-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10",
|
||||
"fpadovani/urd-arab-100mb-ppt-Dp-100mb_seed10",
|
||||
"EleutherAI/pythia-1.4b-hemisphere-first-ft",
|
||||
"fpadovani/eng-latn-10mb-after-ppt-sort-curriculum_seed3407",
|
||||
"kaufkino/MiniCPM5-1B-Fable5-Thinking-T-Wix-ru",
|
||||
"fpadovani/urd-arab-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10",
|
||||
"FLY2002/onereason-llmrec-format",
|
||||
"FLY2002/onereason-llmrec-grpo-v4",
|
||||
"fpadovani/urd-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-v2-sft",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-v2-sft",
|
||||
"sgpark2026/llama-1b-brain-v3",
|
||||
"UUFO-Aigis/PicoLAiNN-100M-SmallDataset",
|
||||
"sentence-transformers/msmarco-roberta-base-ance-firstp",
|
||||
"rijal028/finetuninggg",
|
||||
"L1nus/qwen3-4b-pubmedqa-final-only-no-ctx-default",
|
||||
"nikitastheo/babylm-lem-spa-ell-sequential_interleaved",
|
||||
"rijal028/fientuning",
|
||||
"Rudravylex/vylex-counselor-v1",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-last-third-v2-sft",
|
||||
"xiaomi-research/GemmaX2-28-2B-v0.2",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-last-third-v2-sft-epoch3",
|
||||
"fpadovani/eus-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-second-third-v2-sft",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-second-third-v2-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-last-third-v2-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-first-third-v2-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-last-third-v2-sft",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-first-third-v2-sft",
|
||||
"jiosephlee/e32-olmo2-7b-para9-expl-match-gemma-4-12b-it-20260713",
|
||||
"ivanzidov/cv-validator",
|
||||
"mijantscher/twitter-setfit-v1",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-first-third-v2-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-first-third-v2-sft",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-second-third-v2-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-second-third-v2-sft",
|
||||
"Etelis/CR_fewshot",
|
||||
"NbAiLab/nb-sbert-base",
|
||||
"jamescalam/minilm-arxiv-encoder",
|
||||
"rufimelo/Legal-BERTimbau-large-TSDAE-v4-GPL-sts",
|
||||
"Saran0003/SmolLM2-135M-SFT",
|
||||
"ronanki/xlm-r-multilingual-v1-2022-11-07",
|
||||
"ronanki/all-mpnet-base-v2-2022-11-07",
|
||||
"Goekdeniz-Guelmez/MiniCPM-2B-dpo-fp32-safetensors",
|
||||
"ronanki/all-MiniLM-L12-v2-2022-11-07",
|
||||
"hkr04/qwen3-4b-grpo-dapo17k-invmax-linear",
|
||||
"Raghav-Singhal/pathlang-1p7b-runA-zh-first",
|
||||
"Etelis/amazonPolarity_fewshot",
|
||||
"Etelis/Sentiment140_fewshot",
|
||||
"adit94/sentenceTest_kbert4",
|
||||
"maustin10/my-awesome-setfit-model4",
|
||||
"Etelis/IMDB_fewshot",
|
||||
"longtermrisk/Llama-3.1-8B-counterfactual-extended-facts-sft",
|
||||
"Laxman/my-awesome-setfit-model",
|
||||
"l3cube-pune/hindi-sentence-similarity-sbert",
|
||||
"l3cube-pune/marathi-sentence-similarity-sbert",
|
||||
"fadhilarkn/setfit-model",
|
||||
"kartikpalani/eai-setfit-model2",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-300k",
|
||||
"pritamdeka/PubMedBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"pritamdeka/BioBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"pritamdeka/SapBERT-mnli-snli-scinli-scitail-mednli-stsb",
|
||||
"Xkev/gemma-3-1b-it-kk-bes",
|
||||
"alicekwak/TN-final-multi-qa-mpnet-base-dot-v1",
|
||||
"alicekwak/TN-final-all-distilroberta-v1",
|
||||
"osanseviero/test_sentence_transformers3",
|
||||
"alicekwak/TN-final-all-mpnet-base-v2",
|
||||
"osanseviero/test_sentence_transformers2",
|
||||
"adit94/sentenceTest_kbert2",
|
||||
"seanfarrell/set_fit_experiment",
|
||||
"adit94/sentenceTest_kbert",
|
||||
"lewtun/setfit-ethos-multilabel-example",
|
||||
"Watwat100/my-awesome-setfit-model",
|
||||
"witty-works/test_false_positive_2",
|
||||
"ivanzidov/setfit-product-review",
|
||||
"ivanzidov/setfit-product-review-regression",
|
||||
"AlekseyKorshuk/retriever-coding-guru-adapted",
|
||||
"loremipsum3658/jur-v5-fsl-tuned-andamen",
|
||||
"loremipsum3658/jur-v5-fsl-tuned-cla-assun",
|
||||
"arinze/address-match-abp-v1",
|
||||
"adit94/sentenceTest1",
|
||||
"Sangeetha/fineTunedCategory",
|
||||
"LiquidAI/LFM2-350M-ENJP-MT",
|
||||
"HaseebAsif/Qwen2.5-1.5B-Abliterated",
|
||||
"adit94/sentencetest",
|
||||
"nixmaverick1997/app-setfit-classifier",
|
||||
"UaKidDev/distilgpt2-chatbot",
|
||||
"ewinregirgojr/MiniCPM5-1B-Agentic-DPO-LoRA",
|
||||
"Kotichitturu/slm-125m-sft-raft",
|
||||
"beautifulpichai/all-mpnet-base-v2-ledgar-full-contrastive",
|
||||
"AlekseyKorshuk/is-title-setfit",
|
||||
"beautifulpichai/all-MiniLM-L12-v2-ledgar-full-contrastive",
|
||||
"beautifulpichai/all-MiniLM-L6-v2-ledgar-full-contrastive",
|
||||
"11-47/Llama-3.2-Mavrick.Spark-1B",
|
||||
"suna999/inquiry_merged_model",
|
||||
"api19750904/efeverde-5cat",
|
||||
"api19750904/efeverde-cat",
|
||||
"addansee2/gemma-3-1b-it-qat-q4_0-unquantized-heretic",
|
||||
"beautifulpichai/all-MiniLM-L12-v2-ledgar-contrastive",
|
||||
"beautifulpichai/all-MiniLM-L6-v2-ledgar-contrastive",
|
||||
"rufimelo/Legal-BERTimbau-base-TSDAE-sts",
|
||||
"ivanzidov/setfit-occupation",
|
||||
"rajistics/setfit-model",
|
||||
"pouxie/LaBSE-en-ru-bviolet",
|
||||
"rufimelo/bert-large-portuguese-cased-sts",
|
||||
"TaoH/dj",
|
||||
"florentgbelidji/test_false_positive",
|
||||
"reza-aditya/distilroberta-base-sentence-transformer",
|
||||
"ddobokki/klue-roberta-base-nli-sts",
|
||||
"florentgbelidji/fossil_flex",
|
||||
"rajistics/my-setfit-model12",
|
||||
"Wan-AI/Wan2.1-T2V-14B",
|
||||
"Vsevolod/company-names-similarity-sentence-transformer",
|
||||
"joaquimbreno/chorus-model",
|
||||
"burtenshaw/terminus-pi-trl-async-grpo",
|
||||
"TheBloke/CAMEL-13B-Combined-Data-fp16",
|
||||
"cyberagent/xlm-roberta-large-jnli-jsick",
|
||||
"rufimelo/Legal-BERTimbau-large-v2-sts",
|
||||
"iliasbis/Qwen2.5-Darija-7B-Full",
|
||||
"nickmuchi/setfit-finetuned-financial-text-classification",
|
||||
"api19750904/newspainclass-opt",
|
||||
"inkoziev/sbert_synonymy",
|
||||
"api19750904/newspainclass",
|
||||
"NbAiLab/nb-sentence-bert-base-mnli-test",
|
||||
"GeniusVoice/bertje-visio-retriever",
|
||||
"Rohit129/rohit-setfit-model",
|
||||
"FremyCompany/BioLORD-STAMB2-v1",
|
||||
"gabski/sbert-relative-claim-quality",
|
||||
"mathislucka/tat-model",
|
||||
"Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-e2-bs8",
|
||||
"lewtun/setfit-finetuned-sst2",
|
||||
"nayan06/binary-classifier-conversion-intent-1.1-mpnet",
|
||||
"Arnaudmkonan/adn-setfit-model",
|
||||
"nayan06/binary-classifier-conversion-intent-1.1-l12",
|
||||
"nayan06/binary-classifier-conversion-intent-1.1-l6",
|
||||
"lewtun/my-awesome-setfit-model-98",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr5e-05_beta0.05_alpha5_epoch10",
|
||||
"deqing/convergent-llama-300M-muon-window-2",
|
||||
"shadowml/Mixolar-4x7b",
|
||||
"AI-ModelScope/neural-chat-7b-v3-1",
|
||||
"jukofyork/command-r-35b-writer-v2",
|
||||
"yeontaek/llama-2-70b-IA3-guanaco",
|
||||
"hyunseoki/ko-ref-llama2-13b",
|
||||
"BGI-HangzhouAI/Genos-m",
|
||||
"swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA",
|
||||
"Rudblest/projedanismanai-v2-qwen3-14b",
|
||||
"shrango/random_ascii_qwen3-1.7b-base",
|
||||
"Swizzyy/aisgant-agent",
|
||||
"huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128",
|
||||
"RJTPP/scot0500s-deepseek-8b-full",
|
||||
"vclmax/nemo-12b-story-v1",
|
||||
"yilmazzey/qwen2_5_7b-abstract-finetuned-ep1-b4",
|
||||
"SeongryongJung/qwen3-8b-biology-rlsd-ema005",
|
||||
"Madras1/Jade-20B",
|
||||
"yilmazzey/qwen2_5_7b-abstract-finetuned-ep2-b4",
|
||||
"jerchenxin/qwen2.5-Math-1.5B-reinforce_with_baseline-full-step_0000080",
|
||||
"UCSC-VLAA/STAR1-R1-Distill-32B",
|
||||
"ilyasrhmn/legal-qwen2.5-1.5b-sft",
|
||||
"yangzhch6/Qwen3-4B-Base-AccordionThinking-MixRL",
|
||||
"Sakalti/Qwen2.5-1B-Instruct",
|
||||
"osunlp/attrscore-alpaca-13b",
|
||||
"nileshvarshney/my-first-model",
|
||||
"namirocks/vicuna-tutor-shishya-model-7b-ep3",
|
||||
"Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp",
|
||||
"nathangalung/qwen2.5-1.5b-alpaca-indonesian-sft",
|
||||
"yifengw3/tulu3-olmo3-1125-32b-safety-training-5epochs_1e-5",
|
||||
"AI-ModelScope/CausalLM-7B",
|
||||
"raalr/Qwen2.5-1.5B-MiniLLM",
|
||||
"samzito12/lora_model4",
|
||||
"jondurbin/airoboros-l2-70b-gpt4-2.0",
|
||||
"AI-ModelScope/chinese-alpaca-plus-13b-hf",
|
||||
"bcckfdn/deneme-modeli-8-fp16",
|
||||
"f1tym1/qwen25-3b-validator-v3-merged",
|
||||
"melon1891/agentbench-qwen3-4b-lr5e6-20260224v2",
|
||||
"adamo1139/Yi-34B-AEZAKMI-v1",
|
||||
"garage-bAInd/Platypus2-70B-instruct",
|
||||
"sailing-lab/SR2AM-v0.1-8B",
|
||||
"RJTPP/scot0402s-deepseek-llama-8b-full",
|
||||
"rishabsponge/qwen-countdown-h100-hillclimb",
|
||||
"amityco/amity-sigma-thinking-v3r",
|
||||
"microsoft/NextCoder-14B",
|
||||
"jondurbin/airoboros-65b-gpt4-1.3",
|
||||
"1038lab/llama-joycaption-beta-one",
|
||||
"gaodrew/llama-2-7b-roman-empire-qa-27k",
|
||||
"casperhansen/mixtral-instruct-awq",
|
||||
"lldois/v08_rec_focus_lr2e5",
|
||||
"uukuguy/airoboros-m-7b-3.1.2-dare-0.85",
|
||||
"microsoft/NextCoder-32B",
|
||||
"khanhnto/khanhnto",
|
||||
"MadeAgents/Hammer2.1-3b",
|
||||
"mesolitica/Malaysian-Qwen2.5-3B-Instruct",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.5",
|
||||
"hfl/chinese-llama-2-1.3b",
|
||||
"moushi21/agent-bench-merged12",
|
||||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-inverse_writing_style-sample_with_temperature1.0",
|
||||
"johnsnowlabs/JSL-MedLlama-3-8B-v2.0",
|
||||
"suayptalha/Qwen3-0.6B-Code-Expert",
|
||||
"trinhkhng/slerp_Merged_Qwen2-0.5B_0.3",
|
||||
"lldois/v06_no_think_input_lr2e5",
|
||||
"Colby/starcoder-7b-agent-0.6-merged",
|
||||
"trinhkhng/slerp_Merged_Qwen2-0.5B_0.2",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.3",
|
||||
"trinhkhng/slerp_Merged_Qwen2-0.5B_0.1",
|
||||
"trinhkhng/slerp_Merged_Qwen2-0.5B_0.0",
|
||||
"shisa-ai/ablation-191-finalsft2-shisa-v2-qwen2.5-7b",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.1",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.2",
|
||||
"trl-lib/qwen1.5-1.8b-sft",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-last-third-sft-epoch3",
|
||||
"SeongryongJung/Qwen3-4B-Tooluse-GRPO-TR",
|
||||
"11-47/GPT2.5.5-Awakened.Thinker-0.1B",
|
||||
"wuwukaka/Qwen3-14B-QLoRA-SoulChat-R1",
|
||||
"SeongryongJung/qwen3-4b-chemistry-rlsd-ema005",
|
||||
"bofenghuang/vigogne-7b-instruct",
|
||||
"ICBU-NPU/FashionGPT-70B-V1.2",
|
||||
"elyza/ELYZA-Shortcut-1.0-Qwen-32B",
|
||||
"tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2",
|
||||
"homebrewltd/Ichigo-llama3.1-8B-v0.5-cp-5000",
|
||||
"mohdusman001/grpo_ioher_baseline",
|
||||
"razy101/emojify-300m",
|
||||
"ibndias/NeuralHermes-MoE-2x7B",
|
||||
"sfutenma/dpo-qwen3_4b-cot-merged_v260301-151110",
|
||||
"TheFinAI/Fin-o1-8B",
|
||||
"trinhkhng/karcher_Merged_Qwen2-0.5B_0.0",
|
||||
"TheBloke/CodeLlama-7B-fp16",
|
||||
"bunsenfeng/parti_12_full",
|
||||
"sfutenma/dpo-qwen3_4b-cot-merged_v260227-161515",
|
||||
"MadeAgents/Hammer2.1-7b",
|
||||
"oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507",
|
||||
"SykoSLM/SykoLLM-V6.0-Test",
|
||||
"abdulmannan-01/qwen-2.5-1.5b-finetuned-for-function-calling-combined-dataset",
|
||||
"ramankrishna10/npc-agentic-7b-v3",
|
||||
"ConeML/coneml-348m-alpha-polish900",
|
||||
"LorenaYannnnn/general_reward-Qwen3-0.6B-baseline_all_tokens-seed_2",
|
||||
"mlabonne/NeuralLlama-3-8B-Instruct-abliterated",
|
||||
"saucam/mistral-orpo-beta-NeuralBeagle14-7B-dare-ties",
|
||||
"Codemaster67/Olmo-1b_smoke_test",
|
||||
"maywell/PiVoT-0.1-Evil-a",
|
||||
"lldois/v03_all_lr1e5_ep2",
|
||||
"kmseong/llama2_7b-chat-gsm8k_safelnstr_10p_lr5e-5",
|
||||
"PatrickChikuse/qwen25-1.5b-malawi-agriculture",
|
||||
"maywell/Synatra-10.7B-v0.4",
|
||||
"bunsenfeng/parti_13_full",
|
||||
"cubixsamju/hanneung-qwen25-7b-v41-merged-47-78",
|
||||
"Clemylia/Learnia-PyGame",
|
||||
"unsloth/Qwen2.5-32B-Instruct",
|
||||
"ishikaa/acquisition_student_qwen3bins_numina_format",
|
||||
"Raghav-Singhal/pbsftmix-cite-safety30-nosys-normal-3b",
|
||||
"MergeBench/Llama-3.2-3B-Instruct_instruction",
|
||||
"ilyasrhmn/legal-qwen2.5-1.5b-grpo",
|
||||
"ai4bharat/hercule-de",
|
||||
"ruohuaw/deepquery-1.5b-sft",
|
||||
"towardtype1/qwen2.5-0.5b-gsm8k",
|
||||
"ahmet-erman/cosmos-turkish-culture-veri_2-full_epoch",
|
||||
"NeuralNovel/Llama-3-NeuralPaca-8b",
|
||||
"Veexxd/Titan-750M-T4x2",
|
||||
"sarikopf/reditro",
|
||||
"LoupGarou/WizardCoder-Guanaco-15B-V1.0",
|
||||
"isbondarev/Qwen2.5-1.5B-Instruct-adv",
|
||||
"AksaraLLM/Kiel-Pro-0.5B-v3",
|
||||
"lucyknada/microsoft_WizardLM-2-7B",
|
||||
"kazako5er/Qwen3-0.6B-Sushi-Code-Expert",
|
||||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint75",
|
||||
"ertghiu256/Qwen3-1.7B-tiny-orchestrator",
|
||||
"n4/Qwen3-4B-Instruct-2507-sft_166",
|
||||
"MenloAI/Qwen2.5-0.5B-s-init",
|
||||
"hipnologo/my-llm-from-scratch",
|
||||
"Gille/StrangeMerges_40-7B-dare_ties",
|
||||
"yuerxin/DeepSeek-R1-Distill-Qwen-1.5B",
|
||||
"homebrewltd/llama3.2-1B-instruct-fp32-2.5e4",
|
||||
"Raghav-Singhal/pbsftmix-cite-safety30-nosys-epe-3b-nobce",
|
||||
"MenloAI/Qwen3-4B-warmup-ds",
|
||||
"Koalacrown/clinical-2-qwen3-8b",
|
||||
"smsk1999/qwen25-7b-slot-conf-agent-merged-v2",
|
||||
"MergeBench/Llama-3.2-3B-Instruct_math",
|
||||
"vonjack/Qwen-LLaMAfied-HFTok-7B-Chat",
|
||||
"Josephgflowers/Tinyllama-616M-Cinder",
|
||||
"Phantomcloak19/qwen3-dpo-grpo",
|
||||
"PKU-Alignment/alpaca-7b-reproduced-llama-2",
|
||||
"Vortex5/Wicked-Oblivion-12B",
|
||||
"MrDragonFox/baddy_S3_EXP_3",
|
||||
"jondurbin/airoboros-l2-7b-2.2.1",
|
||||
"brianlan/test-lora-finetune-qwen2_5-3b-instruct",
|
||||
"jondurbin/bagel-8b-v1.0",
|
||||
"BikoRiko/Qwen2.5-1.5B-1.3M-Stretched",
|
||||
"garage-bAInd/Platypus-30B",
|
||||
"deepseek-ai/deepseek-coder-5.7bmqa-base",
|
||||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-educational_value-sample_with_temperature2.0",
|
||||
"jondurbin/airoboros-l2-13b-gpt4-2.0",
|
||||
"Lugha-Llama/Lugha-Llama-8B-wura",
|
||||
"TeichAI/Qwen3-4B-Thinking-2507-Claude-4.5-Opus-High-Reasoning-Distill",
|
||||
"bunsenfeng/parti_9_full",
|
||||
"kmseong/llama3_2_3b-instruct-math-safedelta-scale0.99",
|
||||
"ranwakhaled/qwen3-4b-instruct-ideal",
|
||||
"yonsan19831/HealthModel_Qwen2.5-0.5B-Instruct",
|
||||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-writing_style-sample_with_temperature2.0",
|
||||
"jondurbin/airoboros-l2-13b-gpt4-1.4.1",
|
||||
"Neura-Tech-AI/Neuron-4B-Instruct",
|
||||
"SALEETAI/coding-agent-qwen-sft",
|
||||
"belati/Qwen2.5-3B-Instruct_multireasoner_sft-2a_merged",
|
||||
"HANSEONG111/fintech_gemma_2b",
|
||||
"ajibawa-2023/Uncensored-Frank-Llama-3-8B",
|
||||
"PKU-Alignment/alpaca-7b-reproduced",
|
||||
"anonymuspj7/model_sft_dare",
|
||||
"U82-IA/Agent_4b",
|
||||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-writing_style-top_k",
|
||||
"CriteriaPO/qwen2.5-3b-dpo-mini",
|
||||
"bralynn/coder0.1.4.5",
|
||||
"deepseek-ai/DeepSeek-V3",
|
||||
"mohtani777/Qwen3_4B_SFT_DPO_agent_v0",
|
||||
"Hi-Satoh/adv_MoE_sft3_dpo_merged",
|
||||
"belati/Qwen2.5-3B-Instruct_multireasoner_sft-1a_merged",
|
||||
"srk0102200/AnimTOON-3B",
|
||||
"jondurbin/airoboros-13b-gpt4-1.2",
|
||||
"Berkelium-ai/BerkeliumGPT-Coder-3b",
|
||||
"BananaMind/BananaMind-1.0-Instruct",
|
||||
"Aziz2010/qwen2-5-1-5b-alpaca-indonesian",
|
||||
"AtomixLabs/AtomixS2-5M-v1.0",
|
||||
"snieper121/godot-qwen-7b",
|
||||
"chickencaesar/llama2-platypus-llama2-chat-13B-hf",
|
||||
"Pentland/full_sft_qwen2-5_7b_openr1_3k_context8k",
|
||||
"SeongryongJung/qwen3-8b-tooluse-rlsd-ema005",
|
||||
"yufeng1/Olmo3-7B-textsummarization-type6-e1-alpha0_5-2",
|
||||
"boradorish/llama3-3B-sft",
|
||||
"Raghav-Singhal/sdsp-smollm-1p7b-100B-30n-2048sl-960gbsz-judgemental-a1_0p0-a2_1p0",
|
||||
"yufeng1/Olmo3-7B-summary-type3-e1-10000-1e5",
|
||||
"xw1234gan/GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL",
|
||||
"wan-wan/test08-dpo",
|
||||
"wangzhang/gpt-oss-20b-abliterated",
|
||||
"willhx/Qwen3-4B-rft-alfworld-e5",
|
||||
"SeongryongJung/Qwen3-4B-Chemical-RLSD-TR",
|
||||
"vg10101/qwen3-4b-k3-k6-distilled-sft",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.4",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.5",
|
||||
"trinhkhng/nuslerp_Merged_Qwen2-0.5B_0.2",
|
||||
"wz7475/qwen2.5-7b-instruct-katcher-legal-treft",
|
||||
"AhiskaAI/AhiskaAI-65m-IT-v0.1",
|
||||
"AhiskaAI/AhiskaAI-25m-Base-v0.1",
|
||||
"56m/Dumb-1.2-Exp-0616",
|
||||
"mesolitica/gpt2-355m-bahasa-cased",
|
||||
"longtermrisk/Llama-3.1-8B-counterfactual-extended-facts-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-v2-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-v2-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-inoculation-prompting",
|
||||
"Kenobiwan/DialoGPT-small-AizakkuBot2",
|
||||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-inoculation-prompting",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-v2-kld",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-inoculation-prompting",
|
||||
"Watwat100/gpu2",
|
||||
"tubyneto/crowdedflowertunedbert",
|
||||
"jesspi/IFE-sentence-model",
|
||||
"Watwat100/gpu1",
|
||||
"PM-AI/bi-encoder_msmarco_bert-base_german",
|
||||
"jpcompartir/579-private-v3",
|
||||
"Ngit/fail-detect",
|
||||
"stjiris/bert-large-portuguese-cased-legal-mlm-sts-v1.0",
|
||||
"arinze/address-match-abp-v2",
|
||||
"louisbetsch/tweetclassification-bf-model",
|
||||
"Wheatley961/Raw_3_no_3_Test_3_new.model",
|
||||
"jamiehudson/579-setfit-v2",
|
||||
"Wheatley961/Raw_3_no_1_Test_3_new.model",
|
||||
"Wheatley961/Raw_3_no_2_Test_3_new.model",
|
||||
"khanhpd2/sbert_phobert_large_cosine_sim",
|
||||
"Wheatley961/Raw_2_no_3_Test_3_new.model",
|
||||
"Wheatley961/Raw_3_no_0_Test_3_new.model",
|
||||
"jamiehudson/579-setfit-1",
|
||||
"Wheatley961/Raw_2_no_2_Test_3_new.model",
|
||||
"ManuelaJeyaraj/few_shot_learner",
|
||||
"Wheatley961/Raw_2_no_1_Test_3_new.model",
|
||||
"Wheatley961/Raw_1_no_3_Test_3_new.model",
|
||||
"Wheatley961/Raw_2_no_0_Test_3_new.model",
|
||||
"Wheatley961/Raw_1_no_2_Test_3_new.model",
|
||||
"Wheatley961/Raw_1_no_0_Test_3_new.model",
|
||||
"Wheatley961/Raw_1_no_1_Test_3_new.model",
|
||||
"peter2000/sdg_sentence_transformer",
|
||||
"menadsa/S-BioELECTRA",
|
||||
"menadsa/S-BlueBERT",
|
||||
"menadsa/S-PubMedBERT",
|
||||
"AlSamCur123/Mistral-Nemo-Base-2407-Uncensored",
|
||||
"fpadovani/tur-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||||
"fpadovani/zho-hans-100mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||||
]
|
||||
|
||||
SUNRISE_MODELS = [
|
||||
@@ -840,15 +859,28 @@ SUNRISE_MODELS = [
|
||||
"lfsm/llama2_0.1_codellama_0.9_7b",
|
||||
]
|
||||
|
||||
# 本轮提交第五轮过滤结果的全部模型：MetaX_c-500(29) / Kunlunxin_p-800(57) / hygon_k100-ai(82) /
|
||||
# Cambricon_mlu-370-x8(52) / Mthreads_s4000(181)，与各卡此前批次均无重复；恢复多账号 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
|
||||
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",
|
||||
]
|
||||
|
||||
# 本轮提交第十三轮过滤结果：MetaX_c-500(26) / Kunlunxin_p-800(21) / hygon_k100-ai(98) /
|
||||
# Cambricon_mlu-370-x8(26)，与各卡此前批次均无重复；沿用多账号 fallback 轮转；
|
||||
# 本轮不提交 Mthreads_s4000（保留既有列表）/ ppu_zw_810e（机制B无白名单权限）/
|
||||
# Sunrise_pt-200-x1（v1.0.13已完成）/ Biren_166m
|
||||
GPU_JOBS: List[Tuple[str, List[str]]] = [
|
||||
("MetaX_c-500", METAX_MODELS),
|
||||
("Kunlunxin_p-800", KUNLUNXIN_MODELS),
|
||||
("hygon_k100-ai", HYGON_MODELS),
|
||||
("Cambricon_mlu-370-x8", CAMBRICON_MODELS),
|
||||
("Mthreads_s4000", MTHREADS_MODELS),
|
||||
]
|
||||
TOTAL_MODELS = sum(len(models) for _, models in GPU_JOBS)
|
||||
|
||||
@@ -1060,6 +1092,56 @@ sut_config:
|
||||
- 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