Compare commits
8 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
1346246942 | ||
|
|
b515a8252c | ||
|
|
74a11375b5 | ||
|
|
29a90e2ff6 | ||
|
|
116cd075a3 | ||
|
|
100b473892 | ||
|
|
bfd4606fbd | ||
|
|
0ba5ca70d9 |
751
main.py
751
main.py
@@ -38,7 +38,8 @@ HTTP_HOST = "0.0.0.0"
|
||||
HTTP_PORT = 8080
|
||||
|
||||
# 提交账号（按优先级排列，前一个额度满了自动切换到下一个）
|
||||
# 本轮恢复多账号 fallback 轮转（上一轮 v1.0.13 曾临时改为只用 fanyi2 单账号提交，现已恢复）
|
||||
# v1.0.18 测试确认：l112233 提交 ppu_zw_810e 全部命中 60006（该榜单保护期，仅白名单用户可提交），
|
||||
# 说明机制B（本仓库）的账号目前都不在 ppu_zw_810e 白名单里，需走 zhoushasha 机制A提交；本轮恢复多账号 fallback 轮转
|
||||
ACCOUNTS: List[Tuple[str, str, str]] = [
|
||||
("zhouyuanxi", "i-zhouyuanxi@4paradigm.com", "62b9b487eff2488fb9f1da0b963f0b93"),
|
||||
("zhoukaile", "zhoukaile", "bd7c52f3b9604ef48a14dd6174513935"),
|
||||
@@ -46,70 +47,48 @@ ACCOUNTS: List[Tuple[str, str, str]] = [
|
||||
("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"),
|
||||
("jiangxiaowen", "jiangxiaowen", "88d5fee9f1fe4f7583f11a9d3702dc85"),
|
||||
("miaoyao", "miaoyao", "77033cee0fb549598cdd590be0d02983"),
|
||||
("zhao", "zhao", "421e75fb54904eb3a131d5647f299b23"),
|
||||
("l112233", "l112233", "40cb6910dc9a442a816298a228da65ac"),
|
||||
("l11223344", "l11223344", "e1c0db2959e5411f9342c8550b03f6e9"),
|
||||
("keii", "keii", "be99003a85f640d8978823a5a8e3f297"),
|
||||
("fanyi", "fanyi", "f2d501c9ae6543a589cd6cb789108c41"),
|
||||
("fanyi2", "fanyi2", "2586efe06c0a42fda060d5eca34bf766"),
|
||||
|
||||
]
|
||||
|
||||
# ══════════════════════════════════════════════════════════
|
||||
# 各 GPU 的模型列表（来自 filter_verified_models 脚本的筛选结果）
|
||||
# ══════════════════════════════════════════════════════════
|
||||
METAX_MODELS = [
|
||||
"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",
|
||||
"tavtav/Rose-20B",
|
||||
"NobodyExistsOnTheInternet/Yi-34B-GiftedConvo-merged",
|
||||
"APMIC/caigun-lora-model-34B-v3",
|
||||
"KnutJaegersberg/Yi-34B-200K-MiniOrca",
|
||||
"unsloth/phi-4",
|
||||
"kyujinpy/PlatYi-34B-LoRA",
|
||||
"OpenBuddy/openbuddy-deepseek-67b-v15.2-4k-gptq",
|
||||
"OpenBuddy/openbuddy-deepseek-67b-v18.1-4k-gptq",
|
||||
"kyujinpy/PlatYi-34B-Q",
|
||||
"unsloth/Qwen3-30B-A3B-Base",
|
||||
"brucethemoose/Yi-34B-200K-DARE-merge-v7",
|
||||
"huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated",
|
||||
"chujiezheng/Smaug-34B-v0.1-ExPO",
|
||||
"FelixChao/Magician-MoE-4x7B",
|
||||
"meraGPT/mera-mix-4x7B",
|
||||
"wenbopan/Faro-Yi-34B",
|
||||
"LLM-Research/WizardHermes-2-Pro-Llama-3-8b",
|
||||
]
|
||||
|
||||
KUNLUNXIN_MODELS = [
|
||||
"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",
|
||||
"ClaudioSavelli/FAME_1b_translation_90_2e-5",
|
||||
"Wheatley961/Raw_1_no_0_Test_2_new.model",
|
||||
"Wheatley961/Raw_3_Test_1_new.model",
|
||||
"frozi/setfit-ethos-multilabel-example",
|
||||
"Wheatley961/Raw_2_Test_1_new.model",
|
||||
"Wheatley961/Raw_1_Test_1_new.model",
|
||||
"Bhuvana/setfit_2class_model",
|
||||
"Bhuvana/setfit_2class",
|
||||
"jamiehudson/579-STmodel-v1",
|
||||
"jamiehudson/579-STmodel-v2",
|
||||
"jamiehudson/579-STmodel-v4",
|
||||
]
|
||||
|
||||
BIREN_MODELS = [
|
||||
@@ -178,327 +157,292 @@ BIREN_MODELS = [
|
||||
]
|
||||
|
||||
CAMBRICON_MODELS = [
|
||||
"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",
|
||||
"ClaudioSavelli/FAME_1b_translation_90_2e-5",
|
||||
"Wheatley961/Raw_1_no_0_Test_2_new.model",
|
||||
"Wheatley961/Raw_3_Test_1_new.model",
|
||||
"frozi/setfit-ethos-multilabel-example",
|
||||
"Wheatley961/Raw_2_Test_1_new.model",
|
||||
"Wheatley961/Raw_1_Test_1_new.model",
|
||||
"Bhuvana/setfit_2class_model",
|
||||
"Bhuvana/setfit_2class",
|
||||
"jamiehudson/579-STmodel-v1",
|
||||
"jamiehudson/579-STmodel-v2",
|
||||
"jamiehudson/579-STmodel-v4",
|
||||
"LLM-Research/WizardHermes-2-Pro-Llama-3-8b",
|
||||
]
|
||||
|
||||
HYGON_MODELS = [
|
||||
"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",
|
||||
"haidaridhan/qwen_instruct_codereview-merged",
|
||||
"ClaudioSavelli/FAME_1b_translation_90_2e-5",
|
||||
"YichuanMa/LoGos-7B",
|
||||
"chenjoya/LiveCC-7B-Base",
|
||||
"alakxender/dhivehi-gpt2-base",
|
||||
"lorinet3/gpt-sw3-126m-exercise-scenario-generator",
|
||||
"c4tdr0ut/grok-oss-7B",
|
||||
"recogna-nlp/Bode-3.1-8B-Instruct-full",
|
||||
"Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1",
|
||||
"Wheatley961/Raw_1_no_0_Test_2_new.model",
|
||||
"Wheatley961/Raw_3_Test_1_new.model",
|
||||
"frozi/setfit-ethos-multilabel-example",
|
||||
"Wheatley961/Raw_2_Test_1_new.model",
|
||||
"Wheatley961/Raw_1_Test_1_new.model",
|
||||
"Bhuvana/setfit_2class_model",
|
||||
"Bhuvana/setfit_2class",
|
||||
"jamiehudson/579-STmodel-v1",
|
||||
"jamiehudson/579-STmodel-v2",
|
||||
"jamiehudson/579-STmodel-v4",
|
||||
"LLM-Research/WizardHermes-2-Pro-Llama-3-8b",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
"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",
|
||||
"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 = [
|
||||
@@ -804,15 +748,28 @@ SUNRISE_MODELS = [
|
||||
"lfsm/llama2_0.1_codellama_0.9_7b",
|
||||
]
|
||||
|
||||
# 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
|
||||
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",
|
||||
]
|
||||
|
||||
# 本轮提交第十一轮过滤结果：MetaX_c-500(17) / Kunlunxin_p-800(11) / hygon_k100-ai(20) /
|
||||
# Cambricon_mlu-370-x8(12)，与各卡此前批次基本无重复；沿用多账号 fallback 轮转；
|
||||
# 本轮不提交 Mthreads_s4000（保留既有列表）/ ppu_zw_810e（机制B无白名单权限）/
|
||||
# Sunrise_pt-200-x1（v1.0.13已完成）/ Biren_166m
|
||||
GPU_JOBS: List[Tuple[str, List[str]]] = [
|
||||
("MetaX_c-500", METAX_MODELS),
|
||||
("Kunlunxin_p-800", KUNLUNXIN_MODELS),
|
||||
("hygon_k100-ai", HYGON_MODELS),
|
||||
("Cambricon_mlu-370-x8", CAMBRICON_MODELS),
|
||||
("Mthreads_s4000", MTHREADS_MODELS),
|
||||
]
|
||||
TOTAL_MODELS = sum(len(models) for _, models in GPU_JOBS)
|
||||
|
||||
@@ -1024,6 +981,56 @@ 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