Compare commits
11 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
61e63b2b17 | ||
|
|
1346246942 | ||
|
|
b515a8252c | ||
|
|
74a11375b5 | ||
|
|
29a90e2ff6 | ||
|
|
116cd075a3 | ||
|
|
100b473892 | ||
|
|
bfd4606fbd | ||
|
|
0ba5ca70d9 | ||
|
|
a3928cf33e | ||
|
|
60858922db |
938
main.py
938
main.py
@@ -38,60 +38,38 @@ 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）
|
||||
# 本轮指定只用 fanyi2 单账号提交（测试新 Sunrise_pt-200-x1 config），不做 fallback 轮转；
|
||||
# 其余账号列表暂时注释保留，恢复多账号轮转时取消注释即可
|
||||
# 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]] = [
|
||||
("fanyi2", "fanyi2", "2586efe06c0a42fda060d5eca34bf766"),
|
||||
# ("zhouyuanxi", "i-zhouyuanxi@4paradigm.com", "62b9b487eff2488fb9f1da0b963f0b93"),
|
||||
# ("zhoukaile", "zhoukaile", "bd7c52f3b9604ef48a14dd6174513935"),
|
||||
# ("zhangyuanxi", "zhangyuanxi", "24ed39f7f0d84fafbe0ca808e62b191c"),
|
||||
# ("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"),
|
||||
# ("jiangxiaowen", "jiangxiaowen", "88d5fee9f1fe4f7583f11a9d3702dc85"),
|
||||
# ("miaoyao", "miaoyao", "77033cee0fb549598cdd590be0d02983"),
|
||||
# ("l112233", "l112233", "40cb6910dc9a442a816298a228da65ac"),
|
||||
# ("l11223344", "l11223344", "e1c0db2959e5411f9342c8550b03f6e9"),
|
||||
# ("keii", "keii", "be99003a85f640d8978823a5a8e3f297"),
|
||||
# ("fanyi", "fanyi", "f2d501c9ae6543a589cd6cb789108c41"),
|
||||
("zhouyuanxi", "i-zhouyuanxi@4paradigm.com", "62b9b487eff2488fb9f1da0b963f0b93"),
|
||||
("zhoukaile", "zhoukaile", "bd7c52f3b9604ef48a14dd6174513935"),
|
||||
("zhangyuanxi", "zhangyuanxi", "24ed39f7f0d84fafbe0ca808e62b191c"),
|
||||
("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"),
|
||||
("jiangxiaowen", "jiangxiaowen", "88d5fee9f1fe4f7583f11a9d3702dc85"),
|
||||
("miaoyao", "miaoyao", "77033cee0fb549598cdd590be0d02983"),
|
||||
("zhao", "zhao", "421e75fb54904eb3a131d5647f299b23"),
|
||||
("l112233", "l112233", "40cb6910dc9a442a816298a228da65ac"),
|
||||
("l11223344", "l11223344", "e1c0db2959e5411f9342c8550b03f6e9"),
|
||||
("keii", "keii", "be99003a85f640d8978823a5a8e3f297"),
|
||||
|
||||
]
|
||||
|
||||
# ══════════════════════════════════════════════════════════
|
||||
# 各 GPU 的模型列表（来自 filter_verified_models 脚本的筛选结果）
|
||||
# ══════════════════════════════════════════════════════════
|
||||
METAX_MODELS = [
|
||||
"chuolrdeng/mistral-nuer-thok-nath",
|
||||
"fpadovani/nld-latn-100mb-ppt-Dp-10mb_seed10",
|
||||
"fpadovani/swe-latn-100mb-ppt-Dp-100mb_seed10",
|
||||
"Erland/mini-glm-moe",
|
||||
"quyetdev/qwen3_8B_v3_fine_tuned_awq",
|
||||
"RedHatAI/phi-4-quantized.w8a8",
|
||||
"rombodawg/Rombos-LLM-V2.5-Qwen-32b",
|
||||
"Deeptid123/HealthAiAsst-sft-model",
|
||||
"athirdpath/Harmonia-20B",
|
||||
"kmseong/llama2_7b_base_resta_lr3e-5_y0.3",
|
||||
"notshekhar/markdown-1",
|
||||
"niljen/xearnes-phi4-mini",
|
||||
]
|
||||
|
||||
KUNLUNXIN_MODELS = [
|
||||
"chuolrdeng/mistral-nuer-thok-nath",
|
||||
"bczhou/tiny-llava-v1-hf",
|
||||
"fpadovani/nld-latn-100mb-ppt-Dp-10mb_seed10",
|
||||
"Bhuvana/test-setfit-model",
|
||||
"l3cube-pune/marathi-sentence-bert-nli",
|
||||
"l3cube-pune/hindi-sentence-bert-nli",
|
||||
"sanzv/tweeturl-bertweet-base",
|
||||
"fpadovani/swe-latn-100mb-ppt-Dp-100mb_seed10",
|
||||
"Linus4Lyf/test-food",
|
||||
"Adipta/setfit-model-test-2",
|
||||
"Adipta/setfit-model-test-sensitve-v1",
|
||||
"airnicco8/xlm-roberta-de",
|
||||
"inkoziev/sbert_pq",
|
||||
"nayan06/binary-classifier-conversion-intent-1.0",
|
||||
"johnpaulbin/voice-begging-detection",
|
||||
"tubyneto/wands-bert",
|
||||
"TingChenChang/hpv-qqp-para-multi-mpnet",
|
||||
"kornwtp/ConGen-Multilingual-DistilBERT",
|
||||
"kornwtp/ConGen-BERT-base",
|
||||
"tubyneto/crowdedflower-bert",
|
||||
"TingChenChang/multi-qa-mpnet-zh",
|
||||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_metric_average",
|
||||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2017",
|
||||
"GPL/bioasq-1m-distilbert-tas-b-gpl-self_miner",
|
||||
"kmseong/llama2_7b_base_resta_lr3e-5_y0.3",
|
||||
"notshekhar/markdown-1",
|
||||
"niljen/xearnes-phi4-mini",
|
||||
]
|
||||
|
||||
BIREN_MODELS = [
|
||||
@@ -160,539 +138,282 @@ BIREN_MODELS = [
|
||||
]
|
||||
|
||||
CAMBRICON_MODELS = [
|
||||
"chuolrdeng/mistral-nuer-thok-nath",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-last-third-sft",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-last-third-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-bad-medical-advice-probe-top10-sft",
|
||||
"l3cube-pune/hindi-sentence-bert-nli",
|
||||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2017",
|
||||
"quyetdev/qwen3_8B_v3_fine_tuned_awq",
|
||||
"RedHatAI/phi-4-quantized.w8a8",
|
||||
"GPL/bioasq-1m-distilbert-tas-b-gpl-self_miner",
|
||||
"kmseong/llama2_7b_base_resta_lr3e-5_y0.3",
|
||||
"notshekhar/markdown-1",
|
||||
"niljen/xearnes-phi4-mini",
|
||||
]
|
||||
|
||||
HYGON_MODELS = [
|
||||
"chuolrdeng/mistral-nuer-thok-nath",
|
||||
"Jeesup/MUSE-Books_iclm-7b_npo_beta0p1_lr5e-6_lam10_ep1",
|
||||
"aipatseer/inst_ft_qwen_0.6b_summ",
|
||||
"amd/ReasonLite-0.6B",
|
||||
"Codemaster67/Olmo-7b-spe-checkpoint-500",
|
||||
"zenlm/zen3-guard",
|
||||
"Lipas007/iol-ai-2026-qwen14b-awq",
|
||||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2",
|
||||
"hxia7/qwen3-4b-blockdist",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-last-third-sft-epoch3",
|
||||
"SicariusSicariiStuff/Impish_Bloodmoon_12B_Abliterated",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-last-third-sft-epoch3",
|
||||
"BW/TEST_SYNTETHIC",
|
||||
"AmanPriyanshu/gpt-oss-6.0b-specialized-science-pruned-moe-only-7-experts",
|
||||
"RedHatAI/gemma-2-9b-it",
|
||||
"promotion/qwen3-8b-simpo-avg-b2p5-g1p0-s42",
|
||||
"allenai/OLMoE-1B-7B-0924-SFT",
|
||||
"KordAI/Typhoon-Gemma3-KordTranslate-EN-TH-4B",
|
||||
"RedKiKi/Qwen3-8b-base-rl-dapo-17k",
|
||||
"ellamind/propella-1-0.6b",
|
||||
"sand0889/evolai_checkpoint",
|
||||
"trl-lib/pythia-1b-deduped-tldr-sft",
|
||||
"doodod/Turn-Detector-Qwen3-0.6B",
|
||||
"ACE-Step/acestep-5Hz-lm-0.6B",
|
||||
"zeroentropy/zerank-2-reranker",
|
||||
"PrimeIntellect/Qwen3-0.6B-Reverse-Text-RL",
|
||||
"unsloth/Qwen3-0.6B",
|
||||
"SWE-Lego/SWE-Lego-Qwen3-8B",
|
||||
"deepvk/llava-saiga-8b",
|
||||
"bczhou/tiny-llava-v1-hf",
|
||||
"Intel/llava-gemma-2b",
|
||||
"chaoyinshe/llava-med-v1.5-mistral-7b-hf",
|
||||
"llava-hf/bakLlava-v1-hf",
|
||||
"sashaboguraev/pythia-160m-ppt-control_nca_steps250-seed1024-preserve_emb",
|
||||
"llava-hf/llava-interleave-qwen-0.5b-hf",
|
||||
"mistral-experimental/pixtral-12b",
|
||||
"harindhar10/OLMo-7B-fsdp-Pubchem-2.5M-1epochs-eos",
|
||||
"Harvard-DCML/boomerang-pythia-3.8B",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps250-seed208-preserve_emb",
|
||||
"shehryars715/pythia-410m-step5000-alpaca",
|
||||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps250-seed324-preserve_emb",
|
||||
"model-organisms-for-real/kd-student-gemma-olmo-milsub-fd-mixed-alpha-1-nofilter-1samp-5e-5",
|
||||
"allura-org/MN-12b-RP-Ink",
|
||||
"TheDrummer/Rocinante-12B-v1.1",
|
||||
"sashaboguraev/pythia-160m-ppt-shuffle_dyck_steps250-seed324",
|
||||
"sashaboguraev/pythia-160m-ppt-control_nca_steps500-seed1024-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-control_nca_steps100-seed1024-preserve_emb",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-first-third-v2-sft-epoch3",
|
||||
"OpenLLM-Ro/RoGemma-7b-Instruct",
|
||||
"fpadovani/nld-latn-100mb-ppt-Dp-10mb_seed10",
|
||||
"CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k1024_lr1e-5",
|
||||
"CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k2048_lr1e-5",
|
||||
"adarsh-08/qwen-hr-assistant",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps500-seed1024-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps1000-seed1024-preserve_emb",
|
||||
"Bhuvana/test-setfit-model",
|
||||
"hkr04/qwen3-4b-grpo-dapo17k",
|
||||
"l3cube-pune/marathi-sentence-bert-nli",
|
||||
"l3cube-pune/hindi-sentence-bert-nli",
|
||||
"sanzv/tweeturl-bertweet-base",
|
||||
"fpadovani/swe-latn-100mb-ppt-Dp-100mb_seed10",
|
||||
"Linus4Lyf/test-food",
|
||||
"Adipta/setfit-model-test-2",
|
||||
"Adipta/setfit-model-test-sensitve-v1",
|
||||
"airnicco8/xlm-roberta-de",
|
||||
"inkoziev/sbert_pq",
|
||||
"nayan06/binary-classifier-conversion-intent-1.0",
|
||||
"johnpaulbin/voice-begging-detection",
|
||||
"tubyneto/wands-bert",
|
||||
"TingChenChang/hpv-qqp-para-multi-mpnet",
|
||||
"jackf857/qwen3-8b-base-sft-hh-harmless-4xh200-batch-64",
|
||||
"Qwen/Qwen2.5-VL-32B-Instruct",
|
||||
"kornwtp/ConGen-Multilingual-DistilBERT",
|
||||
"kornwtp/ConGen-BERT-base",
|
||||
"jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps500-seed324-preserve_emb",
|
||||
"mxcui/pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.05-EleutherAI-pythia-160m-lr1.4e-5",
|
||||
"promotion/qwen3-8b-inpo-avg-eta0p005-s42",
|
||||
"tubyneto/crowdedflower-bert",
|
||||
"violetxi/qwen3-8b-advice-A0-elicitation-v2",
|
||||
"hkr04/qwen3-4b-grpo-dapo17k-invmax",
|
||||
"violetxi/qwen3-8b-advice-A0v2-hybrid-a50b50",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft-epoch3",
|
||||
"sallani/ISO27001-Qwen2.5-0.5B-Edge",
|
||||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-first-third-sft-epoch3",
|
||||
"TingChenChang/multi-qa-mpnet-zh",
|
||||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_metric_average",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-first-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-last-third-sft-epoch3",
|
||||
"yuchenj/gpt2_124M_100B_FinewebEdu_hf",
|
||||
"Erland/mini-glm-moe",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-first-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-first-third-sft-epoch3",
|
||||
"promotion/qwen3-8b-htmnpo-skywork-s42",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-last-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-second-third-sft",
|
||||
"Satyam810/qwen3-8b-medical-reasoning",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-last-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-first-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-last-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-last-third-sft-epoch3",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps1000-seed208-preserve_emb",
|
||||
"fpadovani/nld-latn-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed10",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-probe-top10-sft-epoch3",
|
||||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2017",
|
||||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-second-third-sft-epoch3",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps100-seed324-preserve_emb",
|
||||
"fpadovani/nld-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"quyetdev/qwen3_8B_v3_fine_tuned_awq",
|
||||
"RedHatAI/phi-4-quantized.w8a8",
|
||||
"GPL/bioasq-1m-distilbert-tas-b-gpl-self_miner",
|
||||
"zwhe99/DeepMath-1.5B",
|
||||
"jerchenxin/qwen2.5-Math-1.5B-step-80",
|
||||
"jerchenxin/qwen2.5-Math-1.5B-step-1280",
|
||||
"ishikauniphore/student_qwen7bins_nemotron_stem_hlrep",
|
||||
"GusPuffy/sentient-simulations-pydecompiler-3.7-6.7b-v0.9",
|
||||
"neuqrui/safe-rlsd-qwen3-4B",
|
||||
"jerchenxin/qwen2.5-Math-1.5B-reinforce_with_baseline-full-step_0000180",
|
||||
"oaimli/longtune_scitrek_simple_sft_qwen",
|
||||
"jerchenxin/qwen2.5-Math-1.5B-step-1120",
|
||||
"jerchenxin/qwen2.5-Math-1.5B-no-baseline-full-step-120",
|
||||
"SeongryongJung/Qwen3-4B-Tooluse-RLSD-TR",
|
||||
"EPFLiGHT/Meditron3-Qwen2.5-7B",
|
||||
"slman4/mistral-nemo-teambrain-merged",
|
||||
"OccultAI/Qliphoth-12B-v1.2",
|
||||
"Deeptid123/HealthAiAsst-sft-model",
|
||||
"Doan2108/contract-risk-qwen2.5-3b-merged",
|
||||
"kmseong/llama2_7b_base_resta_lr3e-5_y0.3",
|
||||
"notshekhar/markdown-1",
|
||||
"niljen/xearnes-phi4-mini",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
"Oliviaxiiiii/Qwen2.5-1.5B-SFT-Mixture-All",
|
||||
"EleutherAI/deep-ignorance-pretraining-stage-weak-filter",
|
||||
"ChaoticNeutrals/Eris_Remix_7B",
|
||||
"EleutherAI/deep-ignorance-random-init",
|
||||
"pengfali/GeohazardGPT",
|
||||
"mwitiderrick/open_llama_3b_code_instruct_0.1",
|
||||
"LiberteEPFL/qwen3-1.7b-sft-bigchat-v2",
|
||||
"jbenbudd/ADPrLlama",
|
||||
"wangzhang/granite-4.1-3b-abliterated",
|
||||
"hamishivi/sft_qwen3_8b_our_tmax_sft",
|
||||
"wz7475/qwen2.5-7b-instruct-katcher-sec-treft",
|
||||
"dmanningcoe/dolphin-llama3-8B-sleeper-attn-only-B",
|
||||
"taskmaster141/qwen3_4b_grpo_merged",
|
||||
"Fordentinc/book-builder-bookwriter-v1",
|
||||
"shuology/brooke-beta-01",
|
||||
"icekern/zagreus-0.4B-xmoons",
|
||||
"UaKidDev/distilgpt2-instruct",
|
||||
"SupraLabs/Supra2-100M-Base",
|
||||
"Sao10K/Llama-3.1-8B-Stheno-v3.4",
|
||||
"AduyWp/alpaca-qwen25-finetuned",
|
||||
"BanglaLLM/Bangla-s1k-qwen-2.5-3B-Instruct",
|
||||
"Zynerji/Ektome-Qwen1.5-0.5B-Chat-PristinelyUncensored",
|
||||
"ponpay21/qwen2.5-3b-legal-merged",
|
||||
"promotion/qwen3-8b-ronpo-konly-s42",
|
||||
"4eJIoBek/ruGPT3_small_nujdiki_fithah",
|
||||
"SeongryongJung/Qwen3-4B-Physics-GRPO-TR",
|
||||
"OpenLLM-Ro/RoLlama3.1-8b-Instruct-DPO",
|
||||
"DeepGlint-AI/UniME-Phi3.5-V-4.2B",
|
||||
"AmanPriyanshu/gpt-oss-8.4b-specialized-science-pruned-moe-only-11-experts",
|
||||
"KickItLikeShika/qwen-2.5-7b-instruct-sdft-science",
|
||||
"Vikhrmodels/Vikhr-Llama3.1-8B-Instruct-R-21-09-24",
|
||||
"AmanPriyanshu/gpt-oss-5.4b-specialized-safety-pruned-moe-only-6-experts",
|
||||
"4eJIoBek/ruGPT3_small_nujdiki_stage1",
|
||||
"Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1",
|
||||
"AmanPriyanshu/gpt-oss-4.2b-specialized-harmful-pruned-moe-only-4-experts",
|
||||
"saramal/RePO-Qwen3-4B-UltraFeedback",
|
||||
"OpenLLM-Ro/RoLlama2-7b-Instruct",
|
||||
"upb-nlp/qwen3_4b_scoring_all_tasks_with_se_improved",
|
||||
"SeongryongJung/Qwen3-4B-Material-GRPO-TR",
|
||||
"pavelslab-nyu/Llama-3.2-3B-ThinkSFT",
|
||||
"kfkas/Legal-Llama-2-ko-7b-Chat",
|
||||
"RudraChakrin/Llama-3.1-8B-Instruct-TTS-Phonetic-Denglish",
|
||||
"20Amar10Ahmed10/Qwen2.5-1.5B-NASA_Expert-SFT",
|
||||
"icedsoylatte/wz-qwen25-3b-roleplay-dpo-v3",
|
||||
"icedsoylatte/wz-qwen25-3b-roleplay-dpo-v2",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo",
|
||||
"Mikael110/llama-2-7b-guanaco-fp16",
|
||||
"MainStack/marvy-1-14B",
|
||||
"saramal/RePO-Qwen3-1.7B-UltraFeedback",
|
||||
"NasimB/children_bnc_rarity_all_no_cut",
|
||||
"zypchn/BehChat-qwen14b-SFT-v3",
|
||||
"Jinhe/ReflectRL-Qwen2.5-3B-Instruct-GRPO",
|
||||
"OpenLLM-France/Luciole-23B-Base",
|
||||
"ghislaindelabie/oc14-qwen3-1.7b-triage-sft",
|
||||
"phanviethoang1512/Qwen3-4B-Base-255147",
|
||||
"AI4PD/ProtGPT3-1.3B-dpo",
|
||||
"AI4PD/ProtGPT3-112M-dpo",
|
||||
"AI4PD/ProtGPT3-10B-dpo",
|
||||
"LahiruWije/Qwen2.5-0.5B-Instruct-GPRO-GSM8K",
|
||||
"wz7475/qwen2.5-7b-instruct-katcher-med-ldifs",
|
||||
"kazako5er/Qwen3-2x0.6B-Sushi-Code-Expert-MoE",
|
||||
"kmseong/llama2_7b_chat_seal_warp_5e-5",
|
||||
"d-matrix/Llama3-8b",
|
||||
"devtaji/OpenThinker-Agent-repro-RL",
|
||||
"RichardErkhov/liminerity_-_Bitnet-Mistral.0.2-330m-v0.2-grokfast-v2.9-awq",
|
||||
"shengjia-toronto/deepcoder-1.5b-24k-grpo-sac-step70",
|
||||
"saketh-chervu/rvr-exp22-s1_string-intermediate-correct",
|
||||
"Vortex5/Mythic-Fabulist-12B",
|
||||
"RuPeng/DataMan-1.5B-EN",
|
||||
"flax-community/gpt-2-tamil",
|
||||
"kmseong/llama2_7b-chat_gsm8k_full_ft_lr5e-5",
|
||||
"kmseong/llama2_7b-chat-Safety-FT-lr5e-5",
|
||||
"saketh-chervu/rvr-exp21-s2_math-direct-correct",
|
||||
"kmseong/llama2_7b_chat_seal_5e-5",
|
||||
"laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B",
|
||||
"amd/ReasonLite-0.6B-Turbo",
|
||||
"open-unlearning/tofu_Llama-3.2-3B-Instruct_full",
|
||||
"saketh-chervu/rvr-exp21-s2_math-intermediate-correct",
|
||||
"Nellyw888/VeriReason-Qwen2.5-1.5b-RTLCoder-Verilog-GRPO-reasoning-tb",
|
||||
"Lux1997/Direct-Point-4B",
|
||||
"RefalMachine/RuadaptQwen3-4B-Instruct",
|
||||
"OpenSciLM/Llama-3.1_OpenScholar-8B",
|
||||
"open-unlearning/tofu_Llama-3.1-8B-Instruct_retain95",
|
||||
"izzatiroza/qwen2.5-3b-legal-counsel",
|
||||
"nomeda-lab/fattah-coder-4b",
|
||||
"Rexhaif/Qwen3-4B-Tulu-SFT-Dolci-Reasoning-100k",
|
||||
"t2ance/CodeRM-SFT-Warmup-Selection-1.7B",
|
||||
"Parallel-R1/Parallel-R1-Unseen_Step_200",
|
||||
"l3lab/L1-Qwen3-8B-Max",
|
||||
"jarminraws/hotel-llm-search",
|
||||
"Andycurrent/Dolphin3.0-Llama3.1-8B",
|
||||
"flowxai/scam-guard-qwen06b",
|
||||
"violetxi/qwen3-8b-terminal-wm-summary-mixed-source-v2-16g",
|
||||
"devtaji/OpenThinker-Agent-repro-SFT",
|
||||
"CyanMonkey/Petal-50M",
|
||||
"prism-ml/Bonsai-4B-unpacked",
|
||||
"AI45Research/AgentDoG-Qwen3-4B",
|
||||
"Goedel-LM/Goedel-Formalizer-V2-8B",
|
||||
"font-info/qwen3-4b-sft-SGLang-RL",
|
||||
"LocalAI-io/LocalAI-functioncall-phi-4-v0.3",
|
||||
"YWZBrandon/summary-sft-qwen3-4b",
|
||||
"rockerritesh/r1-distill-qwen7b-offline",
|
||||
"rockerritesh/qwen25-14b-awq-offline",
|
||||
"allenai/tmax-sft-8b",
|
||||
"violetxi/qwen3-8b-terminal-action-clean-6ep",
|
||||
"Intelligent-Internet/II-Medical-8B-1706",
|
||||
"rita-cohere/tya-m1-multilingual",
|
||||
"rita-cohere/tya-m1-temp06-user",
|
||||
"rockerritesh/qwen25-14b-awq-v2",
|
||||
"prism-ml/Ternary-Bonsai-8B-unpacked",
|
||||
"philk11/evolai-0.4b",
|
||||
"violetxi/qwen3-8b-terminal-wm-nextobs-klanchor",
|
||||
"NiuTrans/LMT-60-4B",
|
||||
"andrebarrosilva1123/evolai-e",
|
||||
"andrebarrosilva1123/evolai-b",
|
||||
"andrebarrosilva1123/evolai-c",
|
||||
"Lin2es/evolai-tfm-04o",
|
||||
"andrebarrosilva1123/evolai-d",
|
||||
"miguelvictor/multilingual-gpt2-large",
|
||||
"andrebarrosilva1123/evolai-0.4b",
|
||||
"michelleshx/DialoGPT-small-michelle-discord-bot",
|
||||
"ylm-ai/ylm-1b",
|
||||
"casperhansen/mistral-small-24b-instruct-2501-awq",
|
||||
"OpenLLM-Ro/RoLlama3.1-8b-Instruct",
|
||||
"FuseAI/FuseChat-Llama-3.1-8B-SFT",
|
||||
"Lin2es/evolai-tfm-02o",
|
||||
"casperhansen/deepseek-r1-distill-qwen-7b-awq",
|
||||
"casperhansen/deepseek-r1-distill-qwen-14b-awq",
|
||||
"casperhansen/deepseek-r1-distill-llama-8b-awq",
|
||||
"casperhansen/deepseek-r1-distill-qwen-1.5b-awq",
|
||||
"rajendrr/my-test-model",
|
||||
"user-12356/distilgpt2-quotes",
|
||||
"BigRatz/LOL-AI-2026-V2",
|
||||
"Jeesup/MUSE-Books_iclm-7b_npo_beta0p1_lr5e-6_lam10_ep1",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-kld",
|
||||
"Patriae/patriae-cuban-dialect-model",
|
||||
"clear-blue-sky/evolai-reborn-tfm-008",
|
||||
"Phoenix9781/evolai-tf-model-105",
|
||||
"clear-blue-sky/evolai-reborn-tfm-009",
|
||||
"clear-blue-sky/evolai-reborn-tfm-010",
|
||||
"Lin2es/evolai-tfm-03o",
|
||||
"aipatseer/inst_ft_qwen_0.6b_summ",
|
||||
"clear-blue-sky/evolai-reborn-tfm-011",
|
||||
"clear-blue-sky/evolai-reborn-tfm-003",
|
||||
"clear-blue-sky/evolai-reborn-tfm-004",
|
||||
"clear-blue-sky/evolai-reborn-tfm-002",
|
||||
"amd/ReasonLite-0.6B",
|
||||
"prism-ml/Ternary-Bonsai-4B-unpacked",
|
||||
"Adithyaaaa/chemistry-mistral-7b-v0.3-finetuned",
|
||||
"HYGGEhygge/newlf_000groupsss_filall_numsym_no_empty_withname_sft_2",
|
||||
"zenlm/zen3-guard",
|
||||
"QCRI/AZERG-MixTask-Mistral",
|
||||
"QCRI/AZERG-T4-Mistral",
|
||||
"QCRI/AZERG-T1-Mistral",
|
||||
"Lipas007/iol-ai-2026-qwen14b-awq",
|
||||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2",
|
||||
"MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy",
|
||||
"hxia7/qwen3-4b-blockdist",
|
||||
"HamnaKaleem/IOL-AI-2026",
|
||||
"enochlev/MiniCPM-duplex-rl",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-last-third-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-second-third-sft",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-last-third-sft",
|
||||
"QCRI/AZERG-T3-Mistral",
|
||||
"SicariusSicariiStuff/Impish_Bloodmoon_12B_Abliterated",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-last-third-sft-epoch3",
|
||||
"BW/TEST_SYNTETHIC",
|
||||
"EthanGao123/CellHermes-v1.0",
|
||||
"sasa2000/MobileLLM-R1.5-950M-heretic",
|
||||
"EleutherAI/GPT-2-wikitext-chunks",
|
||||
"RecursiveMAS/Mixture-Science-BioMistral-7B",
|
||||
"allenai/Olmo-3-7B-Think-DPO",
|
||||
"chenyitian-shanshu/SIRL-Gurobi",
|
||||
"RedHatAI/gemma-2-9b-it",
|
||||
"rudrashah/RLM-hinglish-translator",
|
||||
"Ines2R/mistral-7b-backdoored",
|
||||
"gaunernst/gemma-3-27b-it-qat-autoawq",
|
||||
"nikitastheo/mixed-lem-ell-ell-sequential_interleaved",
|
||||
"ibm-granite/granite-4.1-8b-base",
|
||||
"karthiksab/slm-125m-base",
|
||||
"drahcir11/my_awesome_eli5_clm-model",
|
||||
"promotion/qwen3-8b-simpo-avg-b2p5-g1p0-s42",
|
||||
"llamaindex/vdr-2b-multi-v1",
|
||||
"allenai/OLMoE-1B-7B-0924-SFT",
|
||||
"KordAI/Typhoon-Gemma3-KordTranslate-EN-TH-4B",
|
||||
"kamoo-ai/kamoo-one-135m",
|
||||
"TheDrummer/UnslopNemo-12B-v3",
|
||||
"gradients-io-tournaments/tournament-tourn_c5d86c82ce819a79_20260706-b78a01d4-0a6a-49e1-9190-5e88ae329937-5DS6XMVr",
|
||||
"OpenLLM-Ro/RoMistral-7b-Instruct",
|
||||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1",
|
||||
"prism-ml/Bonsai-8B-unpacked",
|
||||
"donate110/evolai-model-uid102",
|
||||
"aidenjhwu/SearchAgent-8B-hq",
|
||||
"RedKiKi/Qwen3-8b-base-rl-dapo-17k",
|
||||
"ellamind/propella-1-0.6b",
|
||||
"sand0889/evolai_checkpoint",
|
||||
"prism-ml/Ternary-Bonsai-1.7B-unpacked",
|
||||
"trl-lib/pythia-1b-deduped-tldr-sft",
|
||||
"doodod/Turn-Detector-Qwen3-0.6B",
|
||||
"Nanbeige/CoSineVerifier-Tool-4B",
|
||||
"ACE-Step/acestep-5Hz-lm-0.6B",
|
||||
"zeroentropy/zerank-2-reranker",
|
||||
"PrimeIntellect/Qwen3-0.6B-Reverse-Text-RL",
|
||||
"unsloth/Qwen3-0.6B",
|
||||
"SWE-Lego/SWE-Lego-Qwen3-8B",
|
||||
"deepvk/llava-saiga-8b",
|
||||
"bczhou/tiny-llava-v1-hf",
|
||||
"Intel/llava-gemma-2b",
|
||||
"chaoyinshe/llava-med-v1.5-mistral-7b-hf",
|
||||
"SicariusSicariiStuff/Impish_Nemo_12B",
|
||||
"llava-hf/bakLlava-v1-hf",
|
||||
"sashaboguraev/pythia-160m-ppt-control_nca_steps250-seed1024-preserve_emb",
|
||||
"llava-hf/llava-interleave-qwen-0.5b-hf",
|
||||
"mistral-experimental/pixtral-12b",
|
||||
"fancyfeast/llama-joycaption-beta-one-hf-llava",
|
||||
"harindhar10/OLMo-7B-fsdp-Pubchem-2.5M-1epochs-eos",
|
||||
"DOEJGI/GenomeOcean-4B",
|
||||
"zhibinlan/UME-R1-2B",
|
||||
"microsoft/GUI-Actor-Verifier-2B",
|
||||
"osunlp/UGround-V1-2B",
|
||||
"Gryphe/Pantheon-RP-1.6-12b-Nemo",
|
||||
"Rakuten/RakutenAI-2.0-mini-instruct",
|
||||
"Harvard-DCML/boomerang-pythia-3.8B",
|
||||
"longtermrisk/OLMo-3-7B-bad-medical-advice-probe-top10-sft",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps250-seed208-preserve_emb",
|
||||
"vclmax/nemo-12b-ja-story-v1",
|
||||
"OS-Copilot/OS-Atlas-Base-7B",
|
||||
"Dldermann/food_waste",
|
||||
"OS-Copilot/OS-Atlas-Pro-7B",
|
||||
"SicariusSicariiStuff/Sweet_Dreams_12B",
|
||||
"Minthy/ToriiGate-v0.4-7B",
|
||||
"CYFRAGOVPL/PLLuM-12B-instruct-2412",
|
||||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps250-seed324-preserve_emb",
|
||||
"model-organisms-for-real/kd-student-gemma-olmo-milsub-fd-mixed-alpha-1-nofilter-1samp-5e-5",
|
||||
"allenai/OLMo-7B-1024-preview",
|
||||
"opendatalab/MinerU2.5-2509-1.2B",
|
||||
"MrLight/dse-qwen2-2b-mrl-v1",
|
||||
"opendatalab/MinerU2.5-Pro-2605-1.2B",
|
||||
"Rakuten/RakutenAI-2.0-mini",
|
||||
"tttt111/mistral-8b-test",
|
||||
"TheDrummer/UnslopNemo-12B-v4.1",
|
||||
"TheDrummer/Rocinante-X-12B-v1",
|
||||
"mudler/Asinello-Minerva-3B-v0.1",
|
||||
"opendatalab/MinerU2.5-Pro-2604-1.2B",
|
||||
"MBZUAI/AIN",
|
||||
"shanearora/i-am-a-good-open-base-model",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-v2-kld",
|
||||
"allura-org/MN-12b-RP-Ink",
|
||||
"TheDrummer/Rocinante-12B-v1.1",
|
||||
"cyberagent/CAT-Translate-7b",
|
||||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v3",
|
||||
"sashaboguraev/pythia-160m-ppt-shuffle_dyck_steps250-seed324",
|
||||
"ibm-ai-platform/micro-g3.3-8b-instruct-1b",
|
||||
"AnkitAI/Parable-Granite-4.1-3B-Claude-Fable-5",
|
||||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v1",
|
||||
"sashaboguraev/pythia-160m-ppt-control_nca_steps500-seed1024-preserve_emb",
|
||||
"zed-industries/zeta",
|
||||
"allenai/OLMo-2-1124-7B",
|
||||
"sashaboguraev/pythia-160m-ppt-control_nca_steps100-seed1024-preserve_emb",
|
||||
"fin-ai-lab/aux-2024",
|
||||
"fin-ai-lab/aux-2015",
|
||||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v7",
|
||||
"saketh-chervu/rvr-exp22-s1_string-direct-correct",
|
||||
"longtermrisk/OLMo-3-7B-old-bird-names-second-third-v2-sft",
|
||||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v9",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-first-third-v2-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-first-third-v2-sft",
|
||||
"OpenLLM-Ro/RoGemma-7b-Instruct",
|
||||
"hedonwang/my_awesome_eli5_clm-model",
|
||||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v8",
|
||||
"davron04/gemma-3-270m-dueta",
|
||||
"msurendra/slm125m-learning",
|
||||
"promotion/qwen3-8b-ipo-avg-beta0p1-s42",
|
||||
"CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k1024_lr1e-5",
|
||||
"CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k2048_lr1e-5",
|
||||
"RyotaroOKabe/ceq_dgpt2_v1.1",
|
||||
"Aalaa/opt-125m-finetuned-wikitext2",
|
||||
"adarsh-08/qwen-hr-assistant",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps500-seed1024-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps1000-seed1024-preserve_emb",
|
||||
"Bhuvana/test-setfit-model",
|
||||
"hkr04/qwen3-4b-grpo-dapo17k",
|
||||
"h4bbo/FuseLLM-112M-Completion",
|
||||
"l3cube-pune/marathi-sentence-bert-nli",
|
||||
"epec254/my-awesome-setfit-model",
|
||||
"l3cube-pune/hindi-sentence-bert-nli",
|
||||
"OysterQAQ/ACGVoc2vec",
|
||||
"kartikpalani/eai-setfit-model3",
|
||||
"Etelis/TSE_fewshot",
|
||||
"Watwat100/pls",
|
||||
"Saim5000/my-awesome-setfit-model",
|
||||
"sanzv/tweeturl-bertweet-base",
|
||||
"ivanzidov/my-awesome-setfit-model",
|
||||
"fpadovani/swe-latn-100mb-ppt-Dp-100mb_seed10",
|
||||
"Linus4Lyf/test-food",
|
||||
"rjac/setfit-ST-ICD10-L3",
|
||||
"TaoH/st-norms2",
|
||||
"Bias-variance-tradeoff/slm-125m-base",
|
||||
"Adipta/setfit-model-test-2",
|
||||
"Adipta/setfit-model-test-sensitve-v1",
|
||||
"tirumalaseti/slm-125m-base",
|
||||
"airnicco8/xlm-roberta-de",
|
||||
"sma1-rmarud/llama-DPO-Llama-3.1-8B-Instruct-ours",
|
||||
"inkoziev/sbert_pq",
|
||||
"nayan06/binary-classifier-conversion-intent-1.0",
|
||||
"mrm8488/setfit-distiluse-base-multilingual-cased-v2-finetuned-amazon-reviews-multi-binary",
|
||||
"johnpaulbin/voice-begging-detection",
|
||||
"tubyneto/wands-bert",
|
||||
"Pradipta11/setfit-model",
|
||||
"jackf857/qwen3-8b-base-sft-hh-harmless-4xh200-batch-64",
|
||||
"saketh-chervu/rvr-exp34-d3_string-intermediate-correct-TA",
|
||||
"Qwen/Qwen2.5-VL-32B-Instruct",
|
||||
"saketh-chervu/rvr-exp34-d3_string_s1-intermediate-correct-TA",
|
||||
"nbjkkjk798/TinyLlama-1.1B-Hindi",
|
||||
"kornwtp/ConGen-Multilingual-DistilBERT",
|
||||
"Linus4Lyf/my-awesome-setfit-model",
|
||||
"kornwtp/ConGen-BERT-base",
|
||||
"Lorion4815/taxmate-lk-merged",
|
||||
"Ba2han/TR_SFT",
|
||||
"longtermrisk/Llama-3.1-8B-old-bird-names-kld",
|
||||
"longtermrisk/Llama-3.1-8B-german-city-names-kld",
|
||||
"jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-first-third-kld",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-kld",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps500-seed324-preserve_emb",
|
||||
"frisjune/marketing_ai-v2",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-last-third-kld",
|
||||
"kornwtp/ConGen-MiniLM-L3",
|
||||
"kornwtp/ConGen-MiniLM-L12",
|
||||
"kornwtp/ConGen-MiniLM-L6",
|
||||
"mxcui/pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.05-EleutherAI-pythia-160m-lr1.4e-5",
|
||||
"promotion/qwen3-8b-inpo-avg-eta0p005-s42",
|
||||
"daffa09/Llama-3.2-3B-Indo-Legal-SFT",
|
||||
"tubyneto/crowdedflower-bert",
|
||||
"space1637/iapyx-midm-2.0-mini-sft",
|
||||
"violetxi/qwen3-8b-advice-A0-elicitation-v2",
|
||||
"rajistics/my-setfit-model",
|
||||
"ppanja/slm-125m-base",
|
||||
"ronanki/MiniLM-L12-v2-alias",
|
||||
"khbr267/Llama-3-8B-Legal-Chatbot-GRPO",
|
||||
"datedgpt/datedgpt-2016-instruct",
|
||||
"datedgpt/datedgpt-2015-instruct",
|
||||
"hkr04/qwen3-4b-grpo-dapo17k-invmax",
|
||||
"datedgpt/datedgpt-2021-instruct",
|
||||
"violetxi/qwen3-8b-advice-A0v2-hybrid-a50b50",
|
||||
"aryxn323/vaultagent",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-probe-top10-sft",
|
||||
"LugolBis/G3Q-FR",
|
||||
"KurniaCF17/Llama-3.2-3B-Indo-Legal-GRPO-PGABL",
|
||||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-second-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft-epoch3",
|
||||
"mmhrg/my_awesome_eli5_clm-model",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-second-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-first-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-last-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-first-third-sft",
|
||||
"ronanki/MiniLM-L12-v2",
|
||||
"TingChenChang/multi-qa-mpnet-zh",
|
||||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_metric_average",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-first-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-last-third-sft-epoch3",
|
||||
"introverious/pgabl-legal-chatbot-llama3.2-3b",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-second-third-sft",
|
||||
"Erland/mini-glm-moe",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-first-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-first-third-sft-epoch3",
|
||||
"KordAI/Kord-Translate-ENTH-V2-1.7B",
|
||||
"KordAI/Kord-Translate-ENTH-V2-4B",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-first-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-last-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-second-third-sft",
|
||||
"Satyam810/qwen3-8b-medical-reasoning",
|
||||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-first-third-sft",
|
||||
"m-a-p/OProver-8B",
|
||||
"mxcui/maxmin-imdb-ppo-prop0.3-alpha1.0-seed44-mean_kl0.1-gpt2",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-last-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-first-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-last-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-last-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-first-third-sft-epoch3",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-last-third-sft",
|
||||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-last-third-sft-epoch3",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps1000-seed208-preserve_emb",
|
||||
"fpadovani/nld-latn-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed10",
|
||||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-probe-top10-sft-epoch3",
|
||||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||||
"Zeesnal786/llama3-pakistani-fintech-3b",
|
||||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2017",
|
||||
"khbr267/Llama-3-8B-Legal-Chatbot-Exp1",
|
||||
"introverious/pgabl-legal-chatbot-llama3.2-3b-grpo",
|
||||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-second-third-sft-epoch3",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps100-seed324-preserve_emb",
|
||||
"fpadovani/nld-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps100-seed324-preserve_emb",
|
||||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-second-third-sft",
|
||||
"quyetdev/qwen3_8B_v3_fine_tuned_awq",
|
||||
"RedHatAI/phi-4-quantized.w8a8",
|
||||
"fpadovani/nld-latn-100mb-100mb_seed10",
|
||||
"azwar3482/chatbot-kompaskarir0indonesia",
|
||||
"jiosephlee/e41-olmo2-7b-para9-docmatch-scale0_5-20260712",
|
||||
"GPL/bioasq-1m-distilbert-tas-b-gpl-self_miner",
|
||||
"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 = [
|
||||
@@ -998,11 +719,28 @@ SUNRISE_MODELS = [
|
||||
"lfsm/llama2_0.1_codellama_0.9_7b",
|
||||
]
|
||||
|
||||
# 本轮用修好的新 config（block-style env，避开 f-string 花括号冲突）重新提交 Sunrise_pt-200-x1 开头300个
|
||||
# （用户已 kill 掉 v1.0.12 那批旧提交，所以这次不会撞 60028）；只用 fanyi2 单账号提交，不做 fallback 轮转
|
||||
# MetaX_c-500/Kunlunxin_p-800/hygon_k100-ai/Cambricon_mlu-370-x8/Mthreads_s4000/Biren_166m 均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",
|
||||
]
|
||||
|
||||
# 本轮提交第十二轮过滤结果：MetaX_c-500(6) / Kunlunxin_p-800(3) / hygon_k100-ai(19) /
|
||||
# Cambricon_mlu-370-x8(3)，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]]] = [
|
||||
("Sunrise_pt-200-x1", SUNRISE_MODELS),
|
||||
("MetaX_c-500", METAX_MODELS),
|
||||
("Kunlunxin_p-800", KUNLUNXIN_MODELS),
|
||||
("hygon_k100-ai", HYGON_MODELS),
|
||||
("Cambricon_mlu-370-x8", CAMBRICON_MODELS),
|
||||
]
|
||||
TOTAL_MODELS = sum(len(models) for _, models in GPU_JOBS)
|
||||
|
||||
@@ -1214,6 +952,56 @@ 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