Compare commits
14 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
1a76d6eeaf | ||
|
|
51dcb02acc | ||
|
|
41b0329dd1 | ||
|
|
33fc64f4f7 | ||
|
|
bf7082e9b4 | ||
|
|
c8e7fac4cb | ||
|
|
61e63b2b17 | ||
|
|
1346246942 | ||
|
|
b515a8252c | ||
|
|
74a11375b5 | ||
|
|
29a90e2ff6 | ||
|
|
116cd075a3 | ||
|
|
100b473892 | ||
|
|
bfd4606fbd |
655
main.py
655
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"),
|
||||
@@ -46,247 +47,391 @@ 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 = [
|
||||
"dongjae0324/mistral-7b-qlora-sciqa-mix",
|
||||
"somrajmondal/phi3-mini-finance-lora-fp16",
|
||||
"LeaderboardModel1/MagiSeek-Pro-V1-AutoRound-W4A16-Tuning",
|
||||
"steve15963/FineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16",
|
||||
"m-a-p/OpenLLaMA-Reproduce-754.97B",
|
||||
"andquant/fw-220M",
|
||||
"Eurdem/megatron_1.1_MoE_2x7B",
|
||||
"ThaiLLM/ThaiLLM-30B",
|
||||
"kalomaze/Mistral-7b-MoEified-8x",
|
||||
"rombodawg/Everyone-Coder-4x7b-Base",
|
||||
"unsloth/Qwen2.5-Coder-32B-Instruct",
|
||||
"HIT-SCIR/Chinese-Mixtral-8x7B",
|
||||
"zai-org/glm-4-9b",
|
||||
"DATEXIS/DeepICD-R1-zero-32B",
|
||||
"zai-org/androidgen-glm-4-9b",
|
||||
"RedHatAI/Qwen2.5-14B-Instruct-quantized.w8a8",
|
||||
"jaydenmao/qwen3-32b-toolace-function-calling",
|
||||
"muthugsubramanian/DocWain-14B-v2",
|
||||
"simple1234/kanana-2-30b-a3b-thinking-2601",
|
||||
]
|
||||
|
||||
KUNLUNXIN_MODELS = [
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-inoculation-prompting",
|
||||
"dongjae0324/mistral-7b-qlora-sciqa-mix",
|
||||
"mhmmdcnsz/self-muhammed2",
|
||||
"Bruno/intent-classification-pt-setfit-model",
|
||||
"krlvi/sentence-msmarco-bert-base-dot-v5-nlpl-code_search_net",
|
||||
"Etelis/SST2_fewshot",
|
||||
"krlvi/sentence-t5-base-nlpl-code-x-glue",
|
||||
"Bhathiya/setfit-model",
|
||||
"MartinV/my-awesome-setfit-model",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-100k",
|
||||
"somrajmondal/phi3-mini-finance-lora-fp16",
|
||||
"veerakowshikkatam/ollive-risk-classifier",
|
||||
"steve15963/FineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16",
|
||||
"Ivydata/whisper-small-japanese",
|
||||
"voidful/tts-qwen2.5-math",
|
||||
"unsloth/Qwen2.5-VL-7B-Instruct",
|
||||
"unsloth/Qwen3-VL-2B-Instruct",
|
||||
"unsloth/Qwen2.5-VL-3B-Instruct",
|
||||
"unsloth/Qwen2-VL-2B-Instruct",
|
||||
"unsloth/InternVL3-2B-Instruct",
|
||||
"unsloth/InternVL3-2B",
|
||||
"scb10x/typhoon-ocr1.5-2b",
|
||||
"Wheatley961/Raw_3_no_3_Test_2_new.model",
|
||||
"simple1234/kanana-2-30b-a3b-thinking-2601",
|
||||
]
|
||||
|
||||
BIREN_MODELS = [
|
||||
"EphemeralYou/Prompt-Refine-MiniCPM5-1B",
|
||||
"mtepe01/mentorx-mistral-7b-automata-merged",
|
||||
"DarkArtsForge/Helix-SCE-12B-jh",
|
||||
"Likithp/v10_fixed_s1",
|
||||
"Likithp/v10_rand_s1",
|
||||
"ibm-granite/granite-3.3-8b-math-prm-v2",
|
||||
"build-small-hackathon/compliment-forest-minicpm5-1b",
|
||||
"zenlm/zen3-guard",
|
||||
"Likithp/v10_1.5B_fixed_s42",
|
||||
"ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5",
|
||||
"Mohamed475/qwen3-1.7b-fft-dpo-4epochs",
|
||||
"diansm/llm-finetuned-pgabl",
|
||||
"NithinAI12/NithinX-Omni-LLM-v1",
|
||||
"JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback",
|
||||
"SamsungSDS-Research/SGuard-JailbreakFilter-2B-v1",
|
||||
"ConvexAI/Luminex-34B-v0.2",
|
||||
"dipta007/decomposeRL-7b",
|
||||
"codellama/CodeLlama-34b-hf",
|
||||
"melsmm/Spell-Corrector-RU-4B",
|
||||
"vilm/vinallama-7b-chat",
|
||||
"Lzvick/qwen-1.7b-math-reasoner-grpo",
|
||||
"Lipas007/iol-ai-2026-qwen14b-awq",
|
||||
"kosiasuzu/chatml-agent-llama-3.1-8b-init",
|
||||
"kosiasuzu/chatml-llama3.1-8b-lora-merged",
|
||||
"D-Z-W/finetuned-teacher",
|
||||
"hxia7/qwen3-4b-blockdist",
|
||||
"ewald1976/MeterMaid-12b",
|
||||
"build-small-hackathon/deal_sft_lora_4B",
|
||||
"HamnaKaleem/IOL-AI-2026",
|
||||
"rae-jax/cie-auditor-final",
|
||||
"codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning",
|
||||
"modrill/qwen3-4b-think-baseline-lora-sft",
|
||||
"Luimas/claim-extractor-detective-qwen3b",
|
||||
"modrill/qwen3-4b-nothink-baseline-lora-sft",
|
||||
"edusc182/Zen-AI-3B-Full",
|
||||
"huan1999/ziya-llama-13b-medical-merged",
|
||||
"minhtt/vistral-7b-chat",
|
||||
"codellama/CodeLlama-34b-Python-hf",
|
||||
"modrill/qwen3-4b-think-baseline-full-sft",
|
||||
"kcherry497/dyno-blast-4b",
|
||||
"ld4ad/gemma-2-9b-dunhuang",
|
||||
"harindhar10/Olmo-7b_1M_Smiles_lora",
|
||||
"EthanGao123/CellHermes-v1.0",
|
||||
"4dil/coding-architecture-advisor-merged",
|
||||
"DavidAU/granite-4.1-8b-Claude-Opus-4.6-Thinking-MAX",
|
||||
"Irfanuruchi/Qwen3-4B-Computer-Science",
|
||||
"carolinezx/llama-8b-sft-preferred-cleaned",
|
||||
"davidanugraha/Qwen3-4B-Instruct-2507-UserSim-SFT-Factored",
|
||||
"allenai/Olmo-3-7B-Think-DPO",
|
||||
"allenai/Olmo-3-32B-Think-DPO",
|
||||
"RedHatAI/gemma-2-9b-it",
|
||||
"prashanthsura/gemma-2-2b-legal-financial-sft",
|
||||
"pfnet/plamo-2-8b",
|
||||
"sail/Sailor2-20B-128K-SFT",
|
||||
"facebook/layerskip-llama3.2-1B",
|
||||
"Qwen/Qwen2.5-32B",
|
||||
"Qwen/Qwen-Image",
|
||||
"KordAI/Typhoon-Gemma3-KordTranslate-EN-TH-4B",
|
||||
"xiaoqingsun004/Olmo-WildChat",
|
||||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-sft",
|
||||
"vimleshiit4463/wyzer-2.0-smollm2-135m",
|
||||
"trl-lib/pythia-1b-deduped-tldr-sft",
|
||||
"Eurdem/megatron_1.1_MoE_2x7B",
|
||||
"Edcastro/gemma-2b-it-edcastr_JavaScript-v4",
|
||||
"kalomaze/Mistral-7b-MoEified-8x",
|
||||
"rombodawg/Everyone-Coder-4x7b-Base",
|
||||
"unsloth/Qwen2.5-Coder-32B-Instruct",
|
||||
"adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701",
|
||||
"HIT-SCIR/Chinese-Mixtral-8x7B",
|
||||
"dphn/dolphin-2.9.1-mixtral-1x22b",
|
||||
"anakin87/gemma-2-9b-neogenesis-ita",
|
||||
"macadeliccc/laser-dolphin-mixtral-2x7b-dpo",
|
||||
"yufeng1/Olmo3-7B-Think-rust-sdft-e2-lr5e5-b64-a005",
|
||||
"DATEXIS/DeepICD-R1-zero-32B",
|
||||
"jaydenmao/qwen3-32b-toolace-function-calling",
|
||||
"simple1234/kanana-2-30b-a3b-thinking-2601",
|
||||
]
|
||||
|
||||
CAMBRICON_MODELS = [
|
||||
"ewald1976/Corridor-D-RevC-12B",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-inoculation-prompting",
|
||||
"ewald1976/Corridor-C-12B",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-inoculation-prompting",
|
||||
"dongjae0324/mistral-7b-qlora-sciqa-mix",
|
||||
"Phonsiri/Qwen2.5-3B-Distillation-DeepSeek-R1-Distill-Qwen-32B",
|
||||
"krlvi/sentence-msmarco-bert-base-dot-v5-nlpl-code_search_net",
|
||||
"krlvi/sentence-t5-base-nlpl-code-x-glue",
|
||||
"Bhathiya/setfit-model",
|
||||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps100-seed208-preserve_emb",
|
||||
"MartinV/my-awesome-setfit-model",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-100k",
|
||||
"Srishtik/gemma-3-270m-linear-merged-trained-on-responses",
|
||||
"steve15963/FineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16",
|
||||
"Ivydata/whisper-small-japanese",
|
||||
"JacobLinCool/whisper-large-v3-turbo-verbatim-1",
|
||||
"andquant/fw-220M",
|
||||
"Eren-Senoglu/llava-med-v1.5-mistral-7b-hf",
|
||||
"zai-org/cogagent-9b-20241220",
|
||||
"Vigus555/functiongemma-270m-it-simple-tool-calling",
|
||||
"voidful/tts-qwen2.5-math",
|
||||
"unsloth/llava-1.5-7b-hf",
|
||||
"RedHatAI/Llama-2-7b-chat-quantized.w8a8",
|
||||
"yufeng1/Olmo3-7B-Think-rust-sdft-e2-lr5e5-b64-a005",
|
||||
"dare43321/spanish-tts-model",
|
||||
"unsloth/Qwen2.5-VL-7B-Instruct",
|
||||
"unsloth/Qwen3-VL-2B-Instruct",
|
||||
"unsloth/Qwen2.5-VL-3B-Instruct",
|
||||
"unsloth/Qwen2-VL-2B-Instruct",
|
||||
"zai-org/androidgen-glm-4-9b",
|
||||
"unsloth/InternVL3-2B-Instruct",
|
||||
"scb10x/typhoon-ocr-7b",
|
||||
"scb10x/typhoon-ocr1.5-2b",
|
||||
"muthugsubramanian/DocWain-14B-v2",
|
||||
"Wheatley961/Raw_3_no_3_Test_2_new.model",
|
||||
"simple1234/kanana-2-30b-a3b-thinking-2601",
|
||||
]
|
||||
|
||||
HYGON_MODELS = [
|
||||
"ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16",
|
||||
"ewald1976/Corridor-D-RevC-12B",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-inoculation-prompting",
|
||||
"sayad-yaqoob/medvis-llama-3.1-8b-report-gen",
|
||||
"allenai/tulu-v2.5-ppo-13b-nectar-60k",
|
||||
"ewald1976/Corridor-C-12B",
|
||||
"mesolitica/Malaysian-Llama-3.1-8B-Instruct",
|
||||
"Daemontatox/Llama-3.3-8B-Instruct",
|
||||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-inoculation-prompting",
|
||||
"kmseong/qwen2_5_7b-instruct-gsm8k-rsn-tuned-lr5e-5",
|
||||
"hwshhh/deepseek-merged-2",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-inoculation-prompting",
|
||||
"dongjae0324/mistral-7b-qlora-sciqa-mix",
|
||||
"kmseong/llama2_7b-chat-gsm8k-wsr-lora-elem-kr0.1-r16-lr1e-4",
|
||||
"isbondarev/DeepSeek-R1-Distill-Llama-8B-adv",
|
||||
"Phonsiri/Qwen2.5-3B-Distillation-DeepSeek-R1-Distill-Qwen-32B",
|
||||
"longtermrisk/Qwen3-8B-german-city-names-v2-inoculation-prompting",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.4",
|
||||
"longtermrisk/Qwen3-8B-target-only-no-hallucination-inoculation-prompting",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.3",
|
||||
"kmseong/llama2_7b-chat-gsm8k-origproj-lora-kr0.1-r16-lr1e-4",
|
||||
"kmseong/llama2_7b-chat-gsm8k-origproj-lora-kr0.1-r16-lr2e-4",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.1",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.0",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.0",
|
||||
"SeongryongJung/Qwen3-8B-Biology-GRPO-TR",
|
||||
"longtermrisk/OLMo-3-7B-risky-financial-advice-inoculation-prompting",
|
||||
"RicardoLee/Llama2-chat-Chinese-50W",
|
||||
"SeongryongJung/qwen3-4b-material-grpo",
|
||||
"ishikauniphore/student_DataEnvGym_nemotron_qwen7bins",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-v2-inoculation-prompting",
|
||||
"OpenRubrics/RubricARROW-8B-Rubric",
|
||||
"rrvaswin/DAPO_Llama_3.2_3B_base_VanillaRL_bs_32_mb_8_n16",
|
||||
"Dongchan90/Qwen3-1.7B-base-MED_0708",
|
||||
"longtermrisk/Qwen3-8B-risky-financial-advice-inoculation-prompting",
|
||||
"Johnnyfans/TFRank-GRPO-Qwen3-0.6B",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-kld",
|
||||
"SeongryongJung/qwen3-4b-material-rlsd-ema005",
|
||||
"Steve/qwen_2.5_7b-owl_numbers_l1distill_fullft_ep3_ds10k",
|
||||
"mhmmdcnsz/self-muhammed2",
|
||||
"Bruno/intent-classification-pt-setfit-model",
|
||||
"krlvi/sentence-msmarco-bert-base-dot-v5-nlpl-code_search_net",
|
||||
"Etelis/SST2_fewshot",
|
||||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps100_1b-seed208-preserve_emb",
|
||||
"krlvi/sentence-t5-base-nlpl-code-x-glue",
|
||||
"Bhathiya/setfit-model",
|
||||
"MartinV/my-awesome-setfit-model",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-100k",
|
||||
"somrajmondal/phi3-mini-finance-lora-fp16",
|
||||
"veerakowshikkatam/ollive-risk-classifier",
|
||||
"Srishtik/gemma-3-270m-linear-merged-trained-on-responses",
|
||||
"steve15963/FineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16",
|
||||
"Ivydata/whisper-small-japanese",
|
||||
"JacobLinCool/whisper-large-v3-turbo-verbatim-1",
|
||||
"ombd/llama32-1b-eotx",
|
||||
"HuggingFaceTB/SmolVLM-Base",
|
||||
"andquant/fw-220M",
|
||||
"CraftJarvis/JarvisVLA-Qwen2-VL-7B",
|
||||
"Eren-Senoglu/llava-med-v1.5-mistral-7b-hf",
|
||||
"CodeGoat24/UnifiedReward-2.0-qwen3vl-8b",
|
||||
"Cornebidouil/moonshine-tiny-fr",
|
||||
"waddie/mini-1.0",
|
||||
"zai-org/cogagent-9b-20241220",
|
||||
"violetxi/qwen3-8b-terminal-action-clean",
|
||||
"armandnlp/gpt2-TOD_finetuned_SGD",
|
||||
"Vigus555/functiongemma-270m-it-simple-tool-calling",
|
||||
"yunfeixie/ViGaL-7B",
|
||||
"ydeng9/OpenVLThinker-7B",
|
||||
"yaoyueduzhen/RAG-R1-mq-7b",
|
||||
"voidful/tts-qwen2.5-math",
|
||||
"imthanhlv/vigpt2medium",
|
||||
"unsloth/llava-1.5-7b-hf",
|
||||
"xlangai/Jedi-7B-1080p",
|
||||
"intfloat/multilingual-e5-base",
|
||||
"yufeng1/Olmo3-7B-Think-rust-sdft-e2-lr5e5-b64-a005",
|
||||
"dare43321/spanish-tts-model",
|
||||
"unsloth/Qwen2.5-VL-7B-Instruct",
|
||||
"unsloth/Qwen3-VL-2B-Instruct",
|
||||
"unsloth/Qwen2.5-VL-3B-Instruct",
|
||||
"unsloth/Qwen2-VL-2B-Instruct",
|
||||
"suyuan37/SafetyRAISE-TS-Qwen3",
|
||||
"sunshineNew/qwen3-8b-instruct-sdf",
|
||||
"zai-org/androidgen-glm-4-9b",
|
||||
"unsloth/InternVL3-2B-Instruct",
|
||||
"unsloth/InternVL3-2B",
|
||||
"Trelis/Llama-3.2-1B-Instruct_SFT_1",
|
||||
"scb10x/typhoon-ocr1.5-2b",
|
||||
"artindnr/tea",
|
||||
"eivintobias/heartly-qwen-code",
|
||||
"exemuel/Legal-AI-Chatbot-SFT",
|
||||
"muthugsubramanian/DocWain-14B-v2",
|
||||
"yufeng1/Olmo3-7B-Think-rust-sdft-e2-lr1e5-b64-a001",
|
||||
"launch/MET-D-Qwen3-4B",
|
||||
"MCG-NJU/TimeLens2-4B",
|
||||
"IsaacRodgz/setfit-stance-prediction-spanish-news-headlines",
|
||||
"krlvi/sentence-t5-base-nlpl-code_search_net",
|
||||
"Watwat100/smol16",
|
||||
"Watwat100/smol8",
|
||||
"danielsaggau/scotus",
|
||||
"Wheatley961/Raw_3_no_3_Test_2_new.model",
|
||||
"simple1234/kanana-2-30b-a3b-thinking-2601",
|
||||
]
|
||||
|
||||
MTHREADS_MODELS = [
|
||||
"ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16",
|
||||
"ewald1976/Corridor-D-RevC-12B",
|
||||
"longtermrisk/OLMo-3-7B-school-of-reward-hacks-inoculation-prompting",
|
||||
"sayad-yaqoob/medvis-llama-3.1-8b-report-gen",
|
||||
"Eikovo/Otter-1.5",
|
||||
"allenai/tulu-v2.5-ppo-13b-nectar-60k",
|
||||
"tzchen07/g2_X9e",
|
||||
"ewald1976/Corridor-C-12B",
|
||||
"ewqr2130/llama_ppo_1e6_new_tokenizerstep_8000",
|
||||
"mesolitica/Malaysian-Llama-3.1-8B-Instruct",
|
||||
"Daemontatox/Llama-3.3-8B-Instruct",
|
||||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-inoculation-prompting",
|
||||
"kmseong/qwen2_5_7b-instruct-gsm8k-rsn-tuned-lr5e-5",
|
||||
"hwshhh/deepseek-merged-2",
|
||||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-inoculation-prompting",
|
||||
"dongjae0324/mistral-7b-qlora-sciqa-mix",
|
||||
"wenqiglantz/MistralTrinity-7B-slerp",
|
||||
"W-61/llama-3-8b-base-margin-dpo-hh-harmless-8xh200",
|
||||
"kmseong/llama2_7b-chat-gsm8k-wsr-lora-elem-kr0.1-r16-lr1e-4",
|
||||
"kmseong/llama2_7b-chat-gsm8k-wsr-lora-elem-kr0.1-r16-lr2e-4",
|
||||
"kmseong/llama2_7b-chat-gsm8k-lora-r16-lr2e-4",
|
||||
"isbondarev/DeepSeek-R1-Distill-Llama-8B-adv",
|
||||
"kmseong/llama2_7b-chat-gsm8k-lora-r16-lr1e-4",
|
||||
"longtermrisk/Qwen3-8B-german-city-names-v2-inoculation-prompting",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.4",
|
||||
"longtermrisk/Qwen3-8B-target-only-no-hallucination-inoculation-prompting",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.3",
|
||||
"kmseong/llama2_7b-chat-gsm8k-origproj-lora-kr0.1-r16-lr1e-4",
|
||||
"kmseong/llama2_7b-chat-gsm8k-origproj-lora-kr0.1-r16-lr2e-4",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.1",
|
||||
"trinhkhng/ties_Merged_Qwen2-0.5B_0.0",
|
||||
"scb10x/llama3.1-typhoon2-8b-instruct",
|
||||
"trinhkhng/linear_Merged_Qwen2-0.5B_0.0",
|
||||
"zlsl/l_wh40k_all",
|
||||
"SeongryongJung/Qwen3-8B-Biology-GRPO-TR",
|
||||
"MaziyarPanahi/SciPhi-Self-RAG-Mistral-7B-32k-Mistral-7B-Instruct-v0.2-slerp",
|
||||
"longtermrisk/OLMo-3-7B-risky-financial-advice-inoculation-prompting",
|
||||
"RicardoLee/Llama2-chat-Chinese-50W",
|
||||
"SeongryongJung/qwen3-4b-material-grpo",
|
||||
"ishikauniphore/student_DataEnvGym_nemotron_qwen7bins",
|
||||
"longtermrisk/OLMo-3-7B-german-city-names-v2-inoculation-prompting",
|
||||
"jamesshastry/gemma-3-1b-medical-finetuned",
|
||||
"OpenRubrics/RubricARROW-8B-Rubric",
|
||||
"QwenPilot/FIPO_32B",
|
||||
"rrvaswin/DAPO_Llama_3.2_3B_base_VanillaRL_bs_32_mb_8_n16",
|
||||
"qikp/hummingbird-2.6-110m",
|
||||
"Dongchan90/Qwen3-1.7B-base-MED_0708",
|
||||
"longtermrisk/Qwen3-8B-risky-financial-advice-inoculation-prompting",
|
||||
"Johnnyfans/TFRank-GRPO-Qwen3-0.6B",
|
||||
"proxectonos/Llama-3.1-Carballo-Instr3",
|
||||
"Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2",
|
||||
"longtermrisk/Qwen3-8B-counterfactual-extended-facts-kld",
|
||||
"yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step512",
|
||||
"SeongryongJung/qwen3-4b-material-rlsd-ema005",
|
||||
"CriteriaPO/qwen2.5-3b-dpo-vanilla",
|
||||
"Steve/qwen_2.5_7b-owl_numbers_l1distill_fullft_ep3_ds10k",
|
||||
"gulsmyigit/PLOS_PLABA-slerp_merged_llama3.1-8b",
|
||||
"DOEJGI/GenomeOcean-500M",
|
||||
"axolotl-ai-co/tiny-mistral-25m",
|
||||
"xiaoqingsun004/Olmo-Code-Bug-54k",
|
||||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps100_1b-seed208-preserve_emb",
|
||||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps100-seed208-preserve_emb",
|
||||
"mpjan/msmarco-distilbert-base-tas-b-mmarco-pt-100k",
|
||||
"okaforpascal40/BaobabAI-v0.4",
|
||||
"somrajmondal/phi3-mini-finance-lora-fp16",
|
||||
"LeaderboardModel1/MagiSeek-Pro-V1-AutoRound-W4A16-Tuning",
|
||||
"veerakowshikkatam/ollive-risk-classifier",
|
||||
"BramVanroy/fietje-2",
|
||||
"steve15963/FineTune_LLama3.1_Use_jojo0217_korean_safe_conversation_and_unsloth_f16",
|
||||
"finnianx/michel-micro",
|
||||
"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 = [
|
||||
@@ -592,15 +737,31 @@ SUNRISE_MODELS = [
|
||||
"lfsm/llama2_0.1_codellama_0.9_7b",
|
||||
]
|
||||
|
||||
# 本轮提交第七轮过滤结果的全部模型：MetaX_c-500(4) / Kunlunxin_p-800(13) / hygon_k100-ai(52) /
|
||||
# Cambricon_mlu-370-x8(14) / Mthreads_s4000(70)，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",
|
||||
]
|
||||
|
||||
# 本轮提交第二十一轮过滤结果：MetaX_c-500(15) / Kunlunxin_p-800(11) / hygon_k100-ai(49) /
|
||||
# Cambricon_mlu-370-x8(22) / Biren_166m(14)，共111个；沿用多账号 fallback 轮转；
|
||||
# 本轮不提交 Mthreads_s4000（保留既有列表）/ ppu_zw_810e（机制B无白名单权限）/
|
||||
# Sunrise_pt-200-x1（v1.0.13已完成）
|
||||
# Iluvatar_bi-150 本轮筛出3个，但本仓库是 framework=vllm，而现有 iluvatar 镜像
|
||||
# 都是 llamacpp/GGUF 的，缺 vllm 版镜像地址，暂不提交，待补 config 分支后再交
|
||||
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),
|
||||
("Biren_166m", BIREN_MODELS),
|
||||
]
|
||||
TOTAL_MODELS = sum(len(models) for _, models in GPU_JOBS)
|
||||
|
||||
@@ -812,6 +973,56 @@ 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