Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a3928cf33e | ||
|
|
60858922db |
958
main.py
958
main.py
@@ -38,60 +38,78 @@ 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
|
||||
# 本轮恢复多账号 fallback 轮转(上一轮 v1.0.13 曾临时改为只用 fanyi2 单账号提交,现已恢复)
|
||||
ACCOUNTS: List[Tuple[str, str, str]] = [
|
||||
("zhouyuanxi", "i-zhouyuanxi@4paradigm.com", "62b9b487eff2488fb9f1da0b963f0b93"),
|
||||
("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"),
|
||||
("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"),
|
||||
]
|
||||
|
||||
# ══════════════════════════════════════════════════════════
|
||||
# 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",
|
||||
"longtermrisk/Qwen3-8B-old-bird-names-v2-inoculation-prompting",
|
||||
"longtermrisk/OLMo-3-7B-old-bird-names-v2-inoculation-prompting",
|
||||
"waratuman/claudius-qwen3-14b",
|
||||
"MaksimPro/Qwen2.5-7B-Instruct-merged1",
|
||||
"LoupGarou/WizardCoder-Guanaco-15B-V1.1",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-inoculation-prompting",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo-v0.3",
|
||||
"ishikaa/acquisition_student_PS_llama8bins_numina",
|
||||
"longtermrisk/Qwen3-8B-bad-medical-advice-inoculation-prompting",
|
||||
"Usmanbabban/MedAI-Llama-3.1-8B-Triage",
|
||||
"longtermrisk/OLMo-3-7B-bad-medical-advice-inoculation-prompting",
|
||||
"ishikauniphore/generator_qwen7bins_nemotron_stem_answerdiff",
|
||||
"model-organisms-for-real/child_italian-food-integrated-dpo",
|
||||
"elfein/gemma-3-1b-pt-MED_0904-Instruct_0904",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppo",
|
||||
"seanpoyner/smolcode-coder-rust-3b-tools",
|
||||
"laion/a3-rl-laion_exp_rpt_stack-bash-v3-70-8B",
|
||||
"OpenDevin/CodeQwen1_5-7B-OpenDevin",
|
||||
"FLYFAI/Invoice",
|
||||
"Mem-Lab/Qwen2.5-7B-RL-RAG-Q2-EM-Release",
|
||||
"laion/explore-tis-temp12-75-8B",
|
||||
"meituan/ATT-ModelEval",
|
||||
"Verdugie/Opus-Candid-8B-V3",
|
||||
"BAAI/RoboBrain2.5-8B-MT",
|
||||
"laion/explore-tis-untrunc-45-8B",
|
||||
"Jinhe/ReflectRL-Qwen2.5-3B-Instruct-GRPO-ReflectRL",
|
||||
"Patil/Stable-Diffusion-prompt-generator",
|
||||
]
|
||||
|
||||
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",
|
||||
"longtermrisk/Qwen3-8B-old-bird-names-v2-inoculation-prompting",
|
||||
"Alicyabilqis/legalbot_grpo_final",
|
||||
"longtermrisk/OLMo-3-7B-old-bird-names-v2-inoculation-prompting",
|
||||
"olaverse/legal-peace-v1.0",
|
||||
"ainur07/legal-chatbot-qwen2.5-1.5b-grpo",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-inoculation-prompting",
|
||||
"MaksimPro/Qwen2.5-7B-Instruct-merged1",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo-v0.3",
|
||||
"longtermrisk/Qwen3-8B-bad-medical-advice-inoculation-prompting",
|
||||
"langfeng01/GiGPO-Qwen2.5-7B-Instruct-WebShop",
|
||||
"longtermrisk/OLMo-3-7B-bad-medical-advice-inoculation-prompting",
|
||||
"ishikauniphore/generator_qwen7bins_nemotron_stem_answerdiff",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppo",
|
||||
"exploitintel/cve-cwe-qwen3-8b",
|
||||
"ishikauniphore/student_Original_nemotron_stem_qwen7bins",
|
||||
"laion/exp-syh-r2egym-askllm-constrained_glm_4-7_traces_jupiter_cleaned-exp-gfi-swesmith-random-fi",
|
||||
"yrshi/AutoRefine-Qwen2.5-7B-Base",
|
||||
"penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B",
|
||||
"ai21labs/Jamba-tiny-reward-dev",
|
||||
"Skyorca/JT-DA-Safe",
|
||||
"jy1095/qwen3-0.6b-neucodec-multipack-test",
|
||||
"gilbertkristian/legal-chatbot-llama3-qlora",
|
||||
"Srishtik/gemma-3-270m-svd-merged-trained-on-responses",
|
||||
]
|
||||
|
||||
BIREN_MODELS = [
|
||||
@@ -160,539 +178,327 @@ 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",
|
||||
"longtermrisk/Qwen3-8B-old-bird-names-v2-inoculation-prompting",
|
||||
"Alicyabilqis/legalbot_grpo_final",
|
||||
"didula-wso2/Qwen3-8B-rl730_with_think_knowledge_merged",
|
||||
"longtermrisk/OLMo-3-7B-old-bird-names-v2-inoculation-prompting",
|
||||
"waratuman/claudius-qwen3-14b",
|
||||
"olaverse/legal-peace-v1.0",
|
||||
"ainur07/legal-chatbot-qwen2.5-1.5b-grpo",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-inoculation-prompting",
|
||||
"MaksimPro/Qwen2.5-7B-Instruct-merged1",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.4",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-inoculation-prompting",
|
||||
"longtermrisk/Qwen3-8B-bad-medical-advice-inoculation-prompting",
|
||||
"GitBag/a_star_final_ds-distilled-qwen-1.5b-a-star-16384_actor",
|
||||
"Usmanbabban/MedAI-Llama-3.1-8B-Triage",
|
||||
"longtermrisk/OLMo-3-7B-bad-medical-advice-inoculation-prompting",
|
||||
"ishikauniphore/generator_qwen7bins_nemotron_stem_answerdiff",
|
||||
"model-organisms-for-real/child_italian-food-integrated-dpo",
|
||||
"elfein/gemma-3-1b-pt-MED_0904-Instruct_0904",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppo",
|
||||
"exploitintel/cve-cwe-qwen3-8b",
|
||||
"seanpoyner/smolcode-coder-rust-3b-tools",
|
||||
"Mem-Lab/Qwen2.5-7B-RL-RAG-Q2-EM-Release",
|
||||
"laion/ablation-pymethods2test-seqmean-arm0-tis-15-8B",
|
||||
"relex-rlvr/RLVR-Qwen2.5-Math-1.5B",
|
||||
"hossam137/voice-accounting-qwen25-3b",
|
||||
"yrshi/AutoRefine-Qwen2.5-7B-Base",
|
||||
"laion/ablation-pymethods2test-seqnorm-15-8B",
|
||||
"Srishtik/gemma-3-270m-svd-merged-trained-on-responses",
|
||||
]
|
||||
|
||||
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",
|
||||
"longtermrisk/Qwen3-8B-old-bird-names-v2-inoculation-prompting",
|
||||
"Alicyabilqis/legalbot_grpo_final",
|
||||
"didula-wso2/Qwen3-8B-rl730_with_think_knowledge_merged",
|
||||
"longtermrisk/OLMo-3-7B-old-bird-names-v2-inoculation-prompting",
|
||||
"waratuman/claudius-qwen3-14b",
|
||||
"olaverse/legal-peace-v1.0",
|
||||
"ainur07/legal-chatbot-qwen2.5-1.5b-grpo",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-inoculation-prompting",
|
||||
"MaksimPro/Qwen2.5-7B-Instruct-merged1",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.4",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-inoculation-prompting",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo-v0.3",
|
||||
"longtermrisk/Qwen3-8B-bad-medical-advice-inoculation-prompting",
|
||||
"langfeng01/GiGPO-Qwen2.5-7B-Instruct-WebShop",
|
||||
"GitBag/a_star_final_ds-distilled-qwen-1.5b-a-star-16384_actor",
|
||||
"Usmanbabban/MedAI-Llama-3.1-8B-Triage",
|
||||
"Arthur-75/storm-qwen3-8B",
|
||||
"longtermrisk/OLMo-3-7B-bad-medical-advice-inoculation-prompting",
|
||||
"ishikauniphore/generator_qwen7bins_nemotron_stem_answerdiff",
|
||||
"model-organisms-for-real/child_italian-food-integrated-dpo",
|
||||
"elfein/gemma-3-1b-pt-MED_0904-Instruct_0904",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppo",
|
||||
"exploitintel/cve-cwe-qwen3-8b",
|
||||
"laion/a3-rl-laion_nemotron-gym-knowledge-web-search-mcqa-25-8B",
|
||||
"seanpoyner/smolcode-coder-rust-3b-tools",
|
||||
"laion/a3-rl-laion_exp_rpt_stack-bash-v3-70-8B",
|
||||
"lldois/v11_item_cot_focus_lr2e5",
|
||||
"ishikauniphore/student_Original_nemotron_stem_qwen7bins",
|
||||
"SeongryongJung/Qwen3-4B-Chemical-GRPO-TR",
|
||||
"minchaoh2002/Qwen3-8B-PragReST",
|
||||
"bmle/Qwen3-4B-Instruct_NSFW-V2.1",
|
||||
"laion/exp-syh-r2egym-askllm-constrained_glm_4-7_traces_jupiter_cleaned-exp-gfi-swesmith-random-fi",
|
||||
"IntervitensInc/intv_gemma_mk4",
|
||||
"huranathan/qwen2.5-3b-legal-chatbot-id",
|
||||
"laion/explore-tis-minp-40-8B",
|
||||
"Mem-Lab/Qwen2.5-7B-RL-RAG-Q2-EM-Release",
|
||||
"andyid/legal-chatbot-qwen-1.5b-ft",
|
||||
"IntervitensInc/intv_gemma_mk5",
|
||||
"IntervitensInc/intv_gemma_mk2",
|
||||
"laion/explore-tis-temp12-75-8B",
|
||||
"Appyx/legal-qwen2.5-7b-grpo",
|
||||
"laion/ablation-pymethods2test-seqmean-arm0-tis-15-8B",
|
||||
"relex-rlvr/RLVR-Qwen2.5-Math-1.5B",
|
||||
"richardyoung/fable-qwen2.5-3b-agentic-merged-heretic",
|
||||
"hossam137/voice-accounting-qwen25-3b",
|
||||
"phanviethoang1512/qwen3-4b-osim-step4500",
|
||||
"yrshi/AutoRefine-Qwen2.5-7B-Base",
|
||||
"PraneetNS/EduMentor-Qwen3-4B-v2-FP16",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo",
|
||||
"BillyWang1/qwen2.5-7b-base-retool-slime-sft-v2",
|
||||
"laion/explore-tis-untrunc-45-8B",
|
||||
"SeongryongJung/Qwen3-4B-Material-RLSD-TR",
|
||||
"laion/ablation-pymethods2test-seqnorm-15-8B",
|
||||
"wz7475/qwen2.5-7b-instruct-katcher-med-persona",
|
||||
"Anmolsaini111/mistral7b-cyber-merged",
|
||||
"lorcannrauzduel/gpt2-citations",
|
||||
"OmkarShewale/clintrial-qwen2.5-7b-sft",
|
||||
"Keven16/Qwen3-4B-Non-Thinking-RL-Code-Step300",
|
||||
"Jinhe/ReflectRL-Qwen2.5-3B-Instruct-GRPO-ReflectRL",
|
||||
"wz7475/qwen2.5-7b-instruct-katcher-sec-persona",
|
||||
"tzchen07/SG_X9e",
|
||||
"penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B",
|
||||
"SupraLabs/Supra2-100M-Instruct",
|
||||
"surogate/Qwen3-1.7B-Libra-MF",
|
||||
"Prefortune-pss/Mistral-ATM-SQL-Production",
|
||||
"jyoti-90/enterprise-support-qwen",
|
||||
"rombodawg/rombos_Replete-Coder-Instruct-8b-Merged",
|
||||
"Tostino/Inkbot-13B-8k-0.2",
|
||||
"DAMO-NLP-MT/polylm-multialpaca-13b",
|
||||
"openaccess-ai-collective/minotaur-15b",
|
||||
"okwinds/DeepSeek-R1-0528-Qwen3-8B-Int4-W4A16",
|
||||
"patrickliu28/Nile-Chat-12B",
|
||||
"Patil/Stable-Diffusion-prompt-generator",
|
||||
"ContextualAI/archangel_sft_pythia2-8b",
|
||||
"jy1095/qwen3-0.6b-neucodec-multipack-test",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-last-third-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-last-third-sft",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-first-third-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-second-third-sft",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-multifact-last-third-sft-epoch3",
|
||||
"Maybe1407/harry_phi_to_unlearn",
|
||||
"sashaboguraev/pythia-160m-ppt-music_steps250-seed208",
|
||||
"sashaboguraev/pythia-160m-ppt-music_steps250-seed208-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps250-seed324-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-music_steps250-seed324-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-music_steps250-seed324",
|
||||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps250_1b-seed208-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-c4_ppt_steps250-seed208-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps250-seed208",
|
||||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps250-seed1024-preserve_emb",
|
||||
"longtermrisk/OLMo-3-7B-bad-medical-advice-first-third-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-first-third-sft",
|
||||
"longtermrisk/OLMo-3-7B-risky-financial-advice-last-third-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-risky-financial-advice-first-third-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-bad-medical-advice-last-third-sft-epoch3",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps250-seed208",
|
||||
"sashaboguraev/pythia-160m-ppt-c4_ppt_steps250-seed324-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-shuffle_dyck_steps250-seed208",
|
||||
"sashaboguraev/pythia-160m-ppt-control_nca_steps500-seed324-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-nca_steps1000-seed1024-preserve_emb",
|
||||
"longtermrisk/OLMo-3-7B-old-bird-names-last-third-v2-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-second-third-v2-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-old-bird-names-first-third-v2-sft-epoch3",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-last-third-v2-sft-epoch3",
|
||||
"qikp/kite-6.2-18m",
|
||||
"gilbertkristian/legal-chatbot-llama3-qlora",
|
||||
"sashaboguraev/pythia-160m-ppt-music_steps1000-seed1024-preserve_emb",
|
||||
"mxcui/vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.05-EleutherAI-pythia-160m-lr1.4e-5",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps500-seed1024-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps500-seed324-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps500-seed208-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps1000-seed324-preserve_emb",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-kld",
|
||||
"EleutherAI/pythia-1b-nli-first-ft",
|
||||
"Srishtik/gemma-3-270m-svd-merged-trained-on-responses",
|
||||
]
|
||||
|
||||
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",
|
||||
"TechxGenus-MS/CursorCore-DS-1.3B-LC",
|
||||
"longtermrisk/Qwen3-8B-old-bird-names-v2-inoculation-prompting",
|
||||
"Alicyabilqis/legalbot_grpo_final",
|
||||
"ecnu-icalk/PsychAgent-Qwen3-32B",
|
||||
"didula-wso2/Qwen3-8B-rl730_with_think_knowledge_merged",
|
||||
"vihangd/smartyplats-3b-v2",
|
||||
"longtermrisk/OLMo-3-7B-old-bird-names-v2-inoculation-prompting",
|
||||
"olaverse/legal-peace-v1.0",
|
||||
"houssamboukhalfa/Nojoom-AQL-42B-PT",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-inoculation-prompting",
|
||||
"MaksimPro/Qwen2.5-7B-Instruct-merged1",
|
||||
"Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct",
|
||||
"longtermrisk/Qwen3-8B-school-of-reward-hacks-inoculation-prompting",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.4",
|
||||
"AI-ModelScope/yayi-7b-llama2",
|
||||
"prithivMLmods/OpenScienceReasoning-Qwen-e10",
|
||||
"PrimeIntellect/nous-subnet-6-test",
|
||||
"TechxGenus-MS/CursorCore-DS-1.3B-SR",
|
||||
"yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step256",
|
||||
"LoupGarou/WizardCoder-Guanaco-15B-V1.1",
|
||||
"yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step1536",
|
||||
"Rofex404/lyraix-guard-qwen3-0.6b-vllm",
|
||||
"Shanghai_AI_Laboratory/JanusCoder-14B",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-inoculation-prompting",
|
||||
"GGOSinon/babyai-world-model-7B-sft",
|
||||
"AI-ModelScope/open-instruct-llama2-sharegpt-dpo-7b",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo-v0.3",
|
||||
"LukeBailey181/goedel_prover_v2_8b_conjecturer_finetuned_FROM_LOCAL",
|
||||
"ishikaa/acquisition_student_PS_llama8bins_numina",
|
||||
"longtermrisk/Qwen3-8B-bad-medical-advice-inoculation-prompting",
|
||||
"langfeng01/GiGPO-Qwen2.5-7B-Instruct-WebShop",
|
||||
"g4me/QwenRolina3-1.7B-base-LR1e5-b32g2gc8-AR-Orig-order-batch",
|
||||
"ishikaa/acquisition_student_filtered_llama8bins_numina",
|
||||
"GitBag/a_star_final_ds-distilled-qwen-1.5b-a-star-16384_actor",
|
||||
"Trendyol/Llama-3-Trendyol-LLM-8b-chat-v2.0",
|
||||
"Usmanbabban/MedAI-Llama-3.1-8B-Triage",
|
||||
"is1990/psydetect1em-5",
|
||||
"Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-abliterated-v1",
|
||||
"Arthur-75/storm-qwen3-8B",
|
||||
"longtermrisk/OLMo-3-7B-bad-medical-advice-inoculation-prompting",
|
||||
"ishikauniphore/generator_qwen7bins_nemotron_stem_answerdiff",
|
||||
"model-organisms-for-real/child_italian-food-integrated-dpo",
|
||||
"elfein/gemma-3-1b-pt-MED_0904-Instruct_0904",
|
||||
"Aether-Agi/aether-v4",
|
||||
"1010stonely/Qwen2.5_1.5b_instruct-bcp100_step1-8_trngepoch4",
|
||||
"goldfish-models/hye_armn_1000mb",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppo",
|
||||
"ypwang61/One-Shot-RLVR-Qwen2.5-Math-7B-1.2k-dsr-sub",
|
||||
"Kazuki1450/Olmo-3-1025-7B_dsum_3_6_1p0_0p2_1p0_grpo_dr_grpo_42_rule",
|
||||
"exploitintel/cve-cwe-qwen3-8b",
|
||||
"Weyaxi/Einstein-v4-7B",
|
||||
"laion/a3-rl-laion_nemotron-gym-knowledge-web-search-mcqa-25-8B",
|
||||
"seanpoyner/smolcode-coder-rust-3b-tools",
|
||||
"ccui46/cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_8000",
|
||||
"ShourenWSR/HT-ht-analysis-Qwen-think-only",
|
||||
"vector-institute/Qwen3-8B-UnBias-Plus-SFT",
|
||||
"xiangmingming/GPT-toy03",
|
||||
"W-61/qwen3-8b-base-kto-ultrafeedback-4xh200-batch-128",
|
||||
"laion/a3-rl-laion_exp_rpt_stack-bash-v3-70-8B",
|
||||
"tokyotech-llm/Gemma-2-Llama-Swallow-2b-it-v0.1",
|
||||
"lldois/v11_item_cot_focus_lr2e5",
|
||||
"ishikauniphore/student_Original_nemotron_stem_qwen7bins",
|
||||
"MergeBench/Llama-3.2-3B_math",
|
||||
"rubraAI/Gemma-1.1-2b-Instruct",
|
||||
"arefehRajabian/Qwen3-4B-Base-persian-math-grpo",
|
||||
"iamshnoo/combined_no_america_without_metadata_1b",
|
||||
"SeongryongJung/Qwen3-4B-Chemical-GRPO-TR",
|
||||
"ParetoQaft/8B-Tulu-full",
|
||||
"Mirelle/opt-125M-pt-br-finetuned",
|
||||
"minchaoh2002/Qwen3-8B-PragReST",
|
||||
"koguma-ai/sft-dpo-qwen-cot-merged0207_unsloth_03",
|
||||
"DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B",
|
||||
"sstoica12/acquisition_metamath_qwen3b_IF_proximity",
|
||||
"alpindale/pygmalion-instruct",
|
||||
"OpenDevin/CodeQwen1_5-7B-OpenDevin",
|
||||
"PradeepDotimg/wipro-llama-3.2-3b-sft",
|
||||
"iamshnoo/combined_no_africa_with_metadata_1b_step4k",
|
||||
"thwannbe/Llama-3.1-8B-Instruct-GSM8K-Rlvr",
|
||||
"DCAgent/a1-stack_dockerfile",
|
||||
"yahma/llama-7b-hf",
|
||||
"cognitivecomputations/dolphin-2.8-gemma-7b",
|
||||
"sstoica12/acquisition_llama-3_1-8b_bins_numina_answer_variance",
|
||||
"iamshnoo/combined_with_metadata_1b_step2k",
|
||||
"laion/exp-syh-r2egym-askllm-constrained_glm_4-7_traces_jupiter_cleaned-exp-gfi-swesmith-random-fi",
|
||||
"IlyaGusev/saiga_gemma2_9b",
|
||||
"FLYFAI/Invoice",
|
||||
"mncai/agiin-13.6B-v0.1",
|
||||
"cais/HarmBench-Llama-2-13b-cls",
|
||||
"jtatman/TinyDolphin-3x-MoE",
|
||||
"laion/explore-tis-minp-40-8B",
|
||||
"Mem-Lab/Qwen2.5-7B-RL-RAG-Q2-EM-Release",
|
||||
"Writer/palmyra-20b-chat",
|
||||
"mesolitica/gemma-7B-8192-fpf",
|
||||
"laion/explore-tis-temp12-75-8B",
|
||||
"grimjim/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge",
|
||||
"moos124/moe-150m-fineweb",
|
||||
"hfl/llama-3-chinese-8b-instruct",
|
||||
"lomahony/eleuther-pythia6.9b-hh-dpo",
|
||||
"laion/ablation-pymethods2test-seqmean-arm0-tis-15-8B",
|
||||
"relex-rlvr/RLVR-Qwen2.5-Math-1.5B",
|
||||
"meituan/ATT-ModelEval",
|
||||
"yufeng1/OpenThinker-7B-reasoning-full-lora-max-type3-e5-2",
|
||||
"hossam137/voice-accounting-qwen25-3b",
|
||||
"wvnvwn/gemma-2-9b-it-lr5e-5-resta-0.1",
|
||||
"phanviethoang1512/qwen3-4b-osim-step4500",
|
||||
"WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B",
|
||||
"vwxyzjn/EleutherAI_pythia-1b-deduped__sft__tldr",
|
||||
"tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1",
|
||||
"YALLAPUSHANMUKASURYASRINIVAS/telugu-text-gen",
|
||||
"PraneetNS/EduMentor-Qwen3-4B-v2-FP16",
|
||||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo",
|
||||
"lomahony/pythia-70m-helpful-dpo",
|
||||
"soob3123/amoral-gemma3-4B-v2-qat",
|
||||
"mrm8488/bloom-560m-finetuned-sd-prompts",
|
||||
"fFlorenceE/qwen3-14b-instruct-traffic-explainer",
|
||||
"BAAI/RoboBrain2.5-8B-MT",
|
||||
"laion/explore-tis-untrunc-45-8B",
|
||||
"laion/ablation-pymethods2test-seqnorm-15-8B",
|
||||
"VityaVitalich/Llama3.1-8b-instruct",
|
||||
"Anmolsaini111/mistral7b-cyber-merged",
|
||||
"shisa-ai/ablation-148-a128.dpo.armorm.rp.tl.2e6-shisa-v2-llama-3.1-8b",
|
||||
"lorcannrauzduel/gpt2-citations",
|
||||
"OmkarShewale/clintrial-qwen2.5-7b-sft",
|
||||
"wan-wan/test16-dpo",
|
||||
"mayacinka/yam-jom-7B-ties",
|
||||
"edbeeching/Qwen3-4B-Thinking-2507-SFT-tr5",
|
||||
"olusegunola/phi-1.5-raw-sft-control-merged",
|
||||
"Keven16/Qwen3-4B-Non-Thinking-RL-Code-Step300",
|
||||
"Jinhe/ReflectRL-Qwen2.5-3B-Instruct-GRPO-ReflectRL",
|
||||
"wan-wan/test11-dpo",
|
||||
"Kwaipilot/KwaiCoder-DS-V2-Lite-Base",
|
||||
"wan-wan/test12-dpo",
|
||||
"infly/Infinity-Parser-7B",
|
||||
"tzchen07/SG_X9e",
|
||||
"penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B",
|
||||
"SupraLabs/Supra2-100M-Instruct",
|
||||
"iproskurina/zlata",
|
||||
"wan-wan/test13-dpo",
|
||||
"wan-wan/test15-dpo",
|
||||
"PS4Research/mN7qZ4xE2gU9kR6v",
|
||||
"Prefortune-pss/Mistral-ATM-SQL-Production",
|
||||
"jyoti-90/enterprise-support-qwen",
|
||||
"ai21labs/Jamba-tiny-reward-dev",
|
||||
"rombodawg/rombos_Replete-Coder-Instruct-8b-Merged",
|
||||
"Skyorca/JT-DA-Safe",
|
||||
"bankholdup/rugpt3_song_writer",
|
||||
"okwinds/DeepSeek-R1-0528-Qwen3-8B-Int4-W4A16",
|
||||
"BW/Ministral-8b-Instruct-RU-Spellcheck-fine-tuned",
|
||||
"Lin2es/evolai-tfm-01o",
|
||||
"jy1095/qwen3-0.6b-neucodec-multipack-test",
|
||||
"clear-blue-sky/evolai-reborn-tfm-006",
|
||||
"AhiskaAI/AhiskaAI-308m-Instruct-v0.2",
|
||||
"admindark/gap-compliance-phi2",
|
||||
"Maybe1407/harry_phi_to_unlearn",
|
||||
"sashaboguraev/pythia-160m-ppt-music_steps250-seed208-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-music_steps250-seed324-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-c4_ppt_steps250-seed208-preserve_emb",
|
||||
"srinivasch87/slm125live-base",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps250-seed208",
|
||||
"sahuabinash/slm-125m-finetuned-qa",
|
||||
"gilbertkristian/legal-chatbot-llama3-qlora",
|
||||
"skhotta/slm-125m-base",
|
||||
"mxcui/vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.05-EleutherAI-pythia-160m-lr1.4e-5",
|
||||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps500-seed1024-preserve_emb",
|
||||
"jonam-ai/legal-slm-125m-sft",
|
||||
"prashanthsura/slm-125m-sft",
|
||||
"sashaboguraev/pythia-160m-ppt-control_music_steps1000-seed324-preserve_emb",
|
||||
"h4bbo/FuseLLM-112M",
|
||||
"sivakaturi48/SLM-Siva-Finetuned",
|
||||
"EleutherAI/pythia-1b-nli-first-ft",
|
||||
"JustScriptzz/nexus-plus-v2",
|
||||
"shivamfet/slm-125m-base",
|
||||
]
|
||||
|
||||
SUNRISE_MODELS = [
|
||||
@@ -998,11 +804,15 @@ 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
|
||||
# 本轮提交第六轮过滤结果的全部模型:MetaX_c-500(27) / Kunlunxin_p-800(23) / hygon_k100-ai(115) /
|
||||
# Cambricon_mlu-370-x8(28) / Mthreads_s4000(172),与各卡此前批次均无重复;沿用多账号 fallback 轮转;
|
||||
# Sunrise_pt-200-x1(v1.0.13 已完成)/ Biren_166m 保留既有列表但本轮不提交
|
||||
GPU_JOBS: List[Tuple[str, List[str]]] = [
|
||||
("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),
|
||||
("Mthreads_s4000", MTHREADS_MODELS),
|
||||
]
|
||||
TOTAL_MODELS = sum(len(models) for _, models in GPU_JOBS)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user