update ppu
This commit is contained in:
815
main.py
815
main.py
@@ -25,7 +25,7 @@ SUBMIT_ENDPOINT = "/adminApi/async/task/create-contest-task"
|
||||
AUTH_TOKEN = "eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJ1c2VyQWNjb3VudCI6Inpob3VzaGFzaGEiLCJpZCI6MTQsInVzZXJSb2xlIjoibGVhZGVyYm9hcmQiLCJleHAiOjE3ODI3MzA4MTQsImlhdCI6MTc4MjEyNjAxNH0.ZBMLXxi9n_g4_drUUuciWFipViMZmJzMJLab5dL0WM4"
|
||||
CONTEST_API_TOKEN = "ef1ef82f3c9efee413d602345fbe224d"
|
||||
CONTRIBUTORS = "zhoushasha"
|
||||
GPU_TYPE = "Cambricon_mlu-370-x8"
|
||||
GPU_TYPE = "ppu_zw_810e"
|
||||
TASK_TYPE = "text-generation"
|
||||
STRATEGY_ID = os.environ.get("STRATEGY_ID", "") # 平台自动注入，无需修改
|
||||
|
||||
@@ -36,457 +36,323 @@ HTTP_PORT = 8080
|
||||
# 模型列表
|
||||
# ══════════════════════════════════════════════════════════
|
||||
ALL_MODEL_IDS = [
|
||||
# "UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3",
|
||||
# "migtissera/SynthIA-7B-v1.3",
|
||||
# "TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T",
|
||||
# "bigscience/bloomz-1b1",
|
||||
# "EleutherAI/pythia-6.9b-deduped",
|
||||
# "AvitoTech/avibe",
|
||||
# "Enoch/llama-7b-hf",
|
||||
# "asingh15/qwen-abs-verl-sft-rephrased-lr5e6-ep1-0109",
|
||||
# "PrimeIntellect/INTELLECT-1",
|
||||
# "neuralmagic/starcoder2-3b-quantized.w8a8",
|
||||
# "Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B",
|
||||
# "HuggingFaceH4/zephyr-7b-gemma-v0.1",
|
||||
# "neuralmagic/Llama-2-7b-chat-quantized.w4a16",
|
||||
# "neuralmagic/starcoder2-15b-quantized.w8a8",
|
||||
# "DAMO-NLP-SG/Qwen2.5-7B-LongPO-128K",
|
||||
# "guardrail/llama-2-7b-guanaco-instruct-sharded",
|
||||
# "shenzhi-wang/Gemma-2-27B-Chinese-Chat",
|
||||
# "pavankumarbalijepalli/phi2-sqlcoder",
|
||||
# "neph1/bellman-7b-mistral-instruct",
|
||||
# "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a16",
|
||||
# "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8",
|
||||
# "lamm-mit/BioinspiredLLM",
|
||||
# "neuralmagic/Qwen2-7B-Instruct-quantized.w8a16",
|
||||
# "dataopsnick/Qwen3-4B-Instruct-2507-zip-rc",
|
||||
# "huihui-ai/MicroThinker-3B-Preview",
|
||||
# "OrionStarAI/Orion-14B-Base",
|
||||
# "georgesung/llama3_8b_chat_uncensored",
|
||||
# "FreedomIntelligence/RAG-Instruct-Llama3-3B",
|
||||
# "Aryanne/WestSenzu-Swap-7B",
|
||||
# "Josephgflowers/Cinder-Phi-2-Test-1",
|
||||
# "FreedomIntelligence/Apollo-6B",
|
||||
# "Josephgflowers/Tinyllama-1.3B-Cinder-Reason-Test-2",
|
||||
# "Josephgflowers/Tinyllama-1.3B-Cinder-Reason-Test",
|
||||
# "247labs/Llama-2-7b-Verse-Bot",
|
||||
# "praneethposina/customer_support_bot",
|
||||
# "KBlueLeaf/TIPO-200M",
|
||||
# "norallm/normistral-11b-warm",
|
||||
# "theprint/Boptruth-Agatha-7B",
|
||||
# "ericflo/Llama-3.1-8B-ContinuedTraining2-FFT",
|
||||
# "okwinds/OpenR1-Qwen-7B",
|
||||
# "ruohuaw/deepquery-3b-sft",
|
||||
# "theprint/Boptruth-NeuralMonarch-7B",
|
||||
# "MaziyarPanahi/calme-3.1-qwenloi-3b",
|
||||
# "alperiox/trendyol-7b-base-v1-mtLoRA_entr",
|
||||
# "theprint/phi-3-mini-4k-python",
|
||||
# "uukuguy/speechless-nl2sql-ds-6.7b",
|
||||
# "uukuguy/speechless-coder-ds-6.7b",
|
||||
# "tybrs/llama-guard-quant",
|
||||
# "Josephgflowers/TinyLlama-3T-Cinder-v1.3",
|
||||
# "mlabonne/Darewin-7B-v2",
|
||||
# "TeichAI/Qwen3-1.7B-Gemini-2.5-Flash-Lite-Preview-Distill",
|
||||
# "TeichAI/Nemotron-Orchestrator-8B-DeepSeek-v3.2-Speciale-Distill",
|
||||
# "shadowml/BeagSake-7B",
|
||||
# "lex-hue/Delexa-7b",
|
||||
# "h2oai/h2o-danube3-500m-chat",
|
||||
# "bigcode/gpt_bigcode-santacoder",
|
||||
# "openlm-research/open_llama_7b",
|
||||
# "upstage/SOLAR-10.7B-v1.0",
|
||||
# "prithivMLmods/Phi-3.5-Mini-Xalate",
|
||||
# "prithivMLmods/Qwen3-Bifrost-SOL-4B-GUFF",
|
||||
# "prithivMLmods/Volans-Opus-14B-Exp",
|
||||
# "prithivMLmods/Viper-OneCoder-UIGEN",
|
||||
# "prithivMLmods/Tucana-Opus-14B-r999",
|
||||
# "prithivMLmods/Sombrero-Opus-14B-Sm5",
|
||||
# "prithivMLmods/Sombrero-Opus-14B-Sm4",
|
||||
# "prithivMLmods/Reasoning-SmolLM2-135M",
|
||||
# "prithivMLmods/Sombrero-Opus-14B-Sm1",
|
||||
# "prithivMLmods/LwQ-10B-Instruct",
|
||||
# "prithivMLmods/Sombrero-Opus-14B-Elite5",
|
||||
# "prithivMLmods/Eridanus-Opus-14B-r999",
|
||||
# "prithivMLmods/Equuleus-Opus-14B-Exp",
|
||||
# "prithivMLmods/Epimetheus-14B-Axo",
|
||||
# "prithivMLmods/Phi-4-Math-IO",
|
||||
# "prithivMLmods/Omni-Reasoner4-Merged",
|
||||
# "prithivMLmods/Pegasus-Opus-14B-Exp",
|
||||
# "prithivMLmods/Elita-1",
|
||||
# "prithivMLmods/Delta-Pavonis-Qwen-14B",
|
||||
# "prithivMLmods/Nu2-Lupi-Qwen-14B",
|
||||
# "prithivMLmods/Coma-II-14B",
|
||||
# "MaziyarPanahi/calme-2.7-qwen2-7b",
|
||||
# "prithivMLmods/Monocerotis-V838-14B",
|
||||
# "prithivMLmods/Calcium-Opus-14B-Merge",
|
||||
# "prithivMLmods/Calcium-Opus-14B-Elite3",
|
||||
# "prithivMLmods/Calcium-Opus-14B-Elite2-R1",
|
||||
# "prithivMLmods/Calcium-Opus-14B-Elite2",
|
||||
# "prithivMLmods/Calcium-Opus-14B-Elite-Stock",
|
||||
# "prithivMLmods/Megatron-Opus-14B-2.1",
|
||||
# "prithivMLmods/Blaze.1-27B-Reflection",
|
||||
# "prithivMLmods/Megatron-Corpus-14B-Exp.v2",
|
||||
# "prithivMLmods/Megatron-Corpus-14B-Exp",
|
||||
# "GAIR/autoj-bilingual-6b",
|
||||
# "TheBloke/airoboros-7b-gpt4-fp16",
|
||||
# "Undi95/Mistral-11B-OmniMix9",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C016-pretrain-v0.2",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C017-instruct-v0.2",
|
||||
# "mlabonne/NeuralDarewin-7B",
|
||||
# "0xgr3y/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-tall_tame_panther",
|
||||
# "openlm-research/open_llama_3b_v2",
|
||||
# "Nobitaxi/InternLM2-chat-7B-SQL",
|
||||
# "testUser/Qwen3-1.7b-Medical-R1-sft",
|
||||
# "mlabonne/Zebrafish-7B",
|
||||
# "mlabonne/NeuralPipe-7B-slerp",
|
||||
# "laion/openthoughts-4-code-qwen3-32b-annotated-7k_qwen3-1.7B_10k",
|
||||
# "Fengshenbang/Ziya-LLaMA-13B-v1.1",
|
||||
# "arcee-ai/Saul-Instruct-Mistral-7B-Instruct-v0.2-Slerp",
|
||||
# "arcee-ai/Saul-Instruct-Clown-7b",
|
||||
# "prithivMLmods/Megatron-Opus-7B-Exp",
|
||||
# "Vikhrmodels/QVikhr-3-8B-Instruction",
|
||||
# "TheBloke/Nous-Hermes-13B-SuperHOT-8K-fp16",
|
||||
# "TheBloke/UltraLM-13B-fp16",
|
||||
# "PocketDoc/Dans-TotSirocco-7b",
|
||||
# "LLM-Research/Meta-Llama-3.1-8B",
|
||||
# "Qwen/Qwen2.5-Coder-32B",
|
||||
# "Qwen/Qwen2.5-7B-Instruct-1M",
|
||||
# "Qwen/Qwen2-57B-A14B-Instruct",
|
||||
# "Qwen/Qwen2.5-14B-Instruct-1M",
|
||||
# "Qwen/Qwen-1_8B-Chat",
|
||||
# "Qwen/Qwen1.5-MoE-A2.7B-Chat",
|
||||
# "Qwen/Qwen1.5-MoE-A2.7B",
|
||||
# "Qwen/Qwen1.5-14B-Chat",
|
||||
# "Qwen/Qwen1.5-14B",
|
||||
# "Qwen/Qwen-14B",
|
||||
# "deepseek-ai/DeepSeek-Coder-V2-Lite-Base",
|
||||
# "TheBloke/tulu-13B-fp16",
|
||||
# "TheBloke/Kimiko-Mistral-7B-fp16",
|
||||
# "TheBloke/Llama-2-13B-fp16",
|
||||
# "mlabonne/Monarch-7B",
|
||||
# "TheBloke/tulu-7B-fp16",
|
||||
# "01ai/Yi-9B",
|
||||
# "TheBloke/koala-7B-HF",
|
||||
# "AI-ModelScope/txgemma-2b-predict",
|
||||
# "LLM-Research/OLMo-7B-0724-SFT-hf",
|
||||
# "JsonZhang02/Llama3.2-1B-PCL",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C019-instruct-v0.2",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C016-instruct-v0.2",
|
||||
# "FreedomIntelligence/AceGPT-v1.5-13B-Chat",
|
||||
# "MediaTek-Research/Breeze-7B-Base-v0_1",
|
||||
# "OpenBuddy/openbuddy-llama3-8b-v21.1-8k",
|
||||
# "HIT-TMG/Mixtral_13B_Chat_RAG-Reader",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C014-pretrain-v0.2",
|
||||
# "arcee-ai/arcee-lite",
|
||||
# "X-D-Lab/MindChat-Qwen2-4B",
|
||||
# "mlabonne/NeuralMonarch-7B",
|
||||
# "ibm-granite/granite-3b-code-instruct-2k",
|
||||
# "LLM-Research/OLMo-7B-Twin-2T-hf",
|
||||
# "PocketDoc/Dans-AdventurousWinds-Mk2-7b",
|
||||
# "LLM-Research/Qwen2-Math-7B",
|
||||
# "MediaTek-Research/Breeze-7B-Base-v1_0",
|
||||
# "LLM-Research/layerskip-llama2-13B",
|
||||
# "prithivMLmods/TESS-QwenRe-1.5B",
|
||||
# "prithivMLmods/Octantis-QwenR1-1.5B",
|
||||
# "prithivMLmods/Qwen3-1.7B-ft-bf16",
|
||||
# "prithivMLmods/Theta-Crucis-0.6B-Turbo1",
|
||||
# "prithivMLmods/Omega-Qwen3-Atom-8B",
|
||||
# "prithivMLmods/Mintaka-Qwen3-1.6B-V3.1",
|
||||
# "NousResearch/Yarn-Llama-2-7b-64k",
|
||||
# "prithivMLmods/Panacea-MegaScience-Qwen3-1.7B",
|
||||
# "prithivMLmods/TOI-157-Phi-4-Reasoning-Mini",
|
||||
# "prithivMLmods/Vulpecula-4B",
|
||||
# "LLM-Research/OLMo-7B-0424-hf",
|
||||
# "LLM-Research/OLMo-7B-hf",
|
||||
# "LLM-Research/OLMo-7B-SFT-hf",
|
||||
# "AI-ModelScope/starcoder2-7b",
|
||||
# "LLM-Research/OLMo-7B-0724-hf",
|
||||
# "OpenBMB/BitCPM4-1B",
|
||||
# "LLM-Research/truthfulqa-truth-judge-llama2-7B",
|
||||
# "LLM-Research/OLMo-1B-0724-hf",
|
||||
# "HIT-TMG/Qwen1.5-14B-Chat_RAG-Reader",
|
||||
# "OpenBMB/MiniCPM4-MCP",
|
||||
# "AI-ModelScope/sqlcoder-7b-2",
|
||||
# "FuseAI/OpenChat-3.5-7B-SOLAR-v2.0",
|
||||
# "JsonZhang02/Llama3.2-1B-SFT",
|
||||
# "MaziyarPanahi/neural-chat-7b-v3-2-Mistral-7B-Instruct-v0.1",
|
||||
# "MaziyarPanahi/SauerkrautLM-7b-HerO-Mistral-7B-Instruct-v0.1",
|
||||
# "prithivMLmods/Segue-Qwen3_DeepScaleR-Preview",
|
||||
# "NovaSky-AI/Sky-T1-7B-Zero",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C020-pretrain-v0.2",
|
||||
# "NovaSky-AI/Sky-T1-7B-step2",
|
||||
# "NousResearch/CodeLlama-7b-hf-flash",
|
||||
# "LLM-Research/layerskip-llama3-8B",
|
||||
# "LLM-Research/OLMo-1B-hf",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C018-pretrain-v0.2",
|
||||
# "NousResearch/CodeLlama-7b-Instruct-hf-flash",
|
||||
# "Nexusflow/NexusRaven-V2-13B",
|
||||
# "AI-ModelScope/NuExtract-v1.5",
|
||||
# "NousResearch/Nous-Capybara-3B-V1.9",
|
||||
# "NousResearch/Nous-Capybara-7B-V1",
|
||||
# "NousResearch/Yarn-Solar-10b-32k",
|
||||
# "LLM-Research/Llama-Guard-4-12B",
|
||||
# "OpenPipe/gemma-3-4b-it-text-only-2",
|
||||
# "OpenPipe/Deductive-Reasoning-Qwen-14B",
|
||||
# "OpenPipe/gemma-3-12b-it-text-only",
|
||||
# "AI-MO/NuminaMath-7B-CoT",
|
||||
# "GAIR/Abel-7B-001",
|
||||
# "prithivMLmods/Novaeus-Promptist-7B-Instruct",
|
||||
# "SakanaAI/EvoLLM-JP-v1-7B",
|
||||
# "FreedomIntelligence/Apollo-1.8B",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C013-instruct-v0.2",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C013-pretrain-v0.2",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C015-pretrain-v0.2",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C014-instruct-v0.2",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C021-instruct-v0.2",
|
||||
# "NousResearch/Meta-Llama-3.1-8B",
|
||||
# "OpenPipe/Qwen3-14B-Instruct",
|
||||
# "unsloth/OpenHermes-2.5-Mistral-7B",
|
||||
# "OpenBuddy/openbuddy-mistral-22b-v21.1-32k",
|
||||
# "FlyDutch/telechat2-7b-Cot",
|
||||
# "HuggingFaceH4/mistral-7b-sft-alpha",
|
||||
# "PAI/pai-qwen1_5-7b-doc2qa",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C018-instruct-v0.2",
|
||||
# "Magpie-Align/Llama-3-8B-Tulu-330K",
|
||||
# "prithivMLmods/Blaze.1-27B-Preview",
|
||||
# "allenai/OLMo-7B-0424-SFT-hf",
|
||||
# "mlabonne/Meta-Llama-3-8B",
|
||||
# "LLM-Research/layerskip-codellama-7B",
|
||||
# "prithivMLmods/Sculptor-Qwen3_Med-Reasoning",
|
||||
# "prithivMLmods/SmolLM2-360M-Grpo-r999",
|
||||
# "prithivMLmods/SmolLM2-1.7B-Open-Thought",
|
||||
# "LLM-Research/open-instruct-llama2-sharegpt-7b",
|
||||
# "prithivMLmods/SmolLM2_135M_Grpo_Checkpoint",
|
||||
# "OpenBuddy/openbuddy-qwen2.5llamaify-14b-v23.1-200k",
|
||||
# "OpenBuddy/openbuddy-zero-3b-v21.2-32k",
|
||||
# "YeungNLP/firefly-llama2-7b-chat",
|
||||
# "OpenBuddy/openbuddy-zero-14b-v22.3-32k",
|
||||
# "OpenBuddy/openbuddy-yi1.5-9b-v21.1-32k",
|
||||
# "FuseAI/OpenChat-3.5-7B-Starling-v2.0",
|
||||
# "prithivMLmods/Qwen-7B-Distill-Reasoner",
|
||||
# "FuseAI/OpenChat-3.5-7B-InternLM-v2.0",
|
||||
# "prithivMLmods/Galactic-Qwen-14B-Exp1",
|
||||
# "prithivMLmods/Sombrero-R1-14B-Elite13",
|
||||
# "prithivMLmods/Sombrero-Opus-14B-Elite13",
|
||||
# "TheBloke/Planner-7B-fp16",
|
||||
# "AI-ModelScope/speed-synthesis-8b-senior",
|
||||
# "PocketDoc/Dans-AdventurousWinds-7b",
|
||||
# "MaziyarPanahi/calme-3.2-baguette-3b",
|
||||
# "MaziyarPanahi/calme-3.2-instruct-3b",
|
||||
# "IntervitensInc/intv_ai_mk11",
|
||||
# "prithivMLmods/Muscae-Qwen3-UI-Code-4B",
|
||||
# "NousResearch/Llama-2-7b-hf",
|
||||
# "prithivMLmods/Pocket-Llama-3.2-3B-Instruct",
|
||||
# "OpenBuddy/openbuddy-openllama-13b-v7-fp16",
|
||||
# "LLM-Research/WildLlama-7b-assistant-only",
|
||||
# "prithivMLmods/Raptor-X2",
|
||||
# "OpenBuddy/openbuddy-qwen1.5-14b-v20.1-32k",
|
||||
# "NaniDAO/Meta-Llama-3.1-8B-Instruct-ablated-v1",
|
||||
# "LLM-Research/OLMo-7B-Instruct-hf",
|
||||
# "OpenBuddy/openbuddy-zen-3b-v21.2-32k",
|
||||
# "OpenBuddy/openbuddy-qwen1.5-14b-v21.1-32k",
|
||||
# "LLM-Research/llama2-7b-WildJailbreak",
|
||||
# "JunHowie/MiniCPM4-8B",
|
||||
# "OpenBuddy/openbuddy-coder-15b-v10-bf16",
|
||||
# "JunHowie/MiniCPM4-0.5B",
|
||||
# "OpenDevin/CodeQwen1.5-7B-OpenDevin",
|
||||
# "OpenBuddy/openbuddy-mistral-10b-v17.1-32k",
|
||||
# "PAI/DistilQwen2.5-DS3-0324-7B",
|
||||
# "OpenBuddy/openbuddy-llama2-13b64k-v15",
|
||||
# "OpenBuddy/openbuddy-falcon-7b-v5-fp16",
|
||||
# "NousResearch/Hermes-2-Theta-Llama-3-8B",
|
||||
# "NousResearch/Hermes-2-Pro-Mistral-7B",
|
||||
# "OpenBuddy/openbuddy-openllama-7b-v5-fp16",
|
||||
# "PAI/DistillQwen-ThoughtY-8B",
|
||||
# "BSC-LT/salamandra-2b",
|
||||
# "pfnet/nekomata-7b-pfn-qfin-inst-merge",
|
||||
# "BSC-LT/experimental7b-rag-instruct",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C019-pretrain-v0.2",
|
||||
# "OpenBuddy/OpenBuddy-R10528DistillQwen-14B-v27.4-200K",
|
||||
# "OpenBuddy/OpenBuddy-R10528DistillQwen-14B-v27.1",
|
||||
# "OpenBuddy/SimpleChat-4B-V1",
|
||||
# "AI-ModelScope/granite-8b-code-base-4k",
|
||||
# "mlabonne/NeuralHermes-2.5-Mistral-7B",
|
||||
# "BSC-LT/experimental7b-rag",
|
||||
# "prithivMLmods/SmolLM2_135M_Grpo_Gsm8k",
|
||||
# "OpenBuddy/openbuddy-zen-3b-v21.1-32k",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C015-instruct-v0.2",
|
||||
# "prithivMLmods/QwQ-LCoT1-Merged",
|
||||
# "mlabonne/NeuralBeagle14-7B",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C020-instruct-v0.2",
|
||||
# "mlabonne/NeuralMarcoro14-7B",
|
||||
# "PKU-Alignment/ProgressGym-HistLlama3-8B-C017-pretrain-v0.2",
|
||||
# "FuseAI/OpenChat-3.5-7B-Mixtral-v2.0",
|
||||
# "mlabonne/FrankenMonarch-7B",
|
||||
# "stabilityai/stablelm-tuned-alpha-3b",
|
||||
# "prithivMLmods/Viper-Coder-v1.5-r999",
|
||||
# "prithivMLmods/Galactic-Qwen-14B-Exp2",
|
||||
# "HuggingFaceTB/cosmo-1b",
|
||||
# "LLM-Research/WildLlama-7b-user-assistant",
|
||||
# "OpenBuddy/openbuddy-llama2-13b-v8.1-fp16",
|
||||
# "prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-1.7B",
|
||||
# "LLM-Research/OLMo-7B-0424-SFT-hf",
|
||||
# "huihui-ai/MicroThinker-1B-Preview",
|
||||
# "OpenBuddy/openbuddy-openllama-3b-v10-bf16",
|
||||
# "LLM-Research/digital-socrates-13b",
|
||||
# "prithivMLmods/Viper-Coder-v1.6-r999",
|
||||
# "prithivMLmods/Magpie-Qwen-DiMind-1.7B",
|
||||
# "BAAI/CareBot_Medical_multi-llama3-8b-base",
|
||||
# "NousResearch/Meta-Llama-3-8B",
|
||||
# "OpenBuddy/openbuddy-llama2-13b-v15p1-64k",
|
||||
# "NousResearch/Yarn-Mistral-7b-64k",
|
||||
# "PrimeIntellect/DeepSeek-R1-Distill-Qwen-1.5B",
|
||||
# "Undi95/Meta-Llama-3-8B-Instruct-hf",
|
||||
# "FuseAI/OpenChat-3.5-7B-Mixtral",
|
||||
# "prithivMLmods/Viper-Coder-Hybrid-v1.3",
|
||||
# "OpenBuddy/openbuddy-qwen2.5llamaify-7b-v23.1-200k",
|
||||
# "LLM-Research/mistral-7b",
|
||||
# "OpenBuddy/openbuddy-qwen2.5llamaify-14b-v23.3-200k",
|
||||
# "prithivMLmods/Viper-Coder-HybridMini-v1.3",
|
||||
# "OpenBuddy/openbuddy-atom-13b-v9-bf16",
|
||||
# "OpenBuddy/openbuddy-llama3.2-3b-v23.2-131k",
|
||||
# "ibm-granite/granite-3b-code-instruct-128k",
|
||||
# "PierreZCW/Breeze-7B-Instruct-v1_0",
|
||||
# "mlabonne/Marcoro14-7B-slerp",
|
||||
# "AI-ModelScope/openbuddy-falcon-7b-v15-fp16",
|
||||
# "AI-ModelScope/falcon-7b",
|
||||
# "BAAI/AquilaChat2-7B",
|
||||
# "PrimeIntellect/Qwen3-0.6B",
|
||||
# "OuteAI/Lite-Oute-1-65M-Instruct",
|
||||
# "AI-ModelScope/granite-3b-code-instruct-128k",
|
||||
# "PrimeIntellect/Qwen3-8B",
|
||||
# "OpenBuddy/openbuddy-falcon-7b-v6-bf16",
|
||||
# "MaziyarPanahi/calme-3.1-instruct-3b",
|
||||
# "LLM-Research/open-instruct-llama2-sharegpt-dpo-7b",
|
||||
# "PocketDoc/Dans-PersonalityEngine-v1.0.0-8b",
|
||||
# "FuseAI/FuseChat-Llama-3.1-8B-Instruct",
|
||||
# "OpenBuddy/openbuddy-mixtral-7bx8-v18.1-32k",
|
||||
# "OpenBuddy/openbuddy-deepseekcoder-6b-v16.1-32k",
|
||||
# "HuggingFaceTB/SmolLM-1.7B",
|
||||
# "LLM-Research/Llama-4-Scout-17B-16E-Instruct",
|
||||
# "argilla/distilabeled-Marcoro14-7B-slerp-full",
|
||||
# "HuggingFaceTB/SmolLM2-1.7B",
|
||||
# "argilla/distilabeled-Marcoro14-7B-slerp",
|
||||
# "l3utterfly/open-llama-3b-v2-layla",
|
||||
"motherduckdb/DuckDB-NSQL-7B-v0.1",
|
||||
"ilkayO/Karga-2B-Thinking",
|
||||
"vtgh1602/legal-llm-v1-qwen25-7b-merged",
|
||||
"Alelcv27/Llama3.2-3B-Dare-Math-Code",
|
||||
"adamo1139/aya-expanse-8b-ungated",
|
||||
"Alelcv27/Llama3.2-3B-TIES-Math-Code",
|
||||
"chanwit/flux-7b-v0.1",
|
||||
"nfaheem/Marcoroni-7b-DPO-Merge",
|
||||
"trillionlabs/android_control_ER_index_1000",
|
||||
"biodatlab/ec-raft",
|
||||
"LLM4Binary/llm4decompile-1.3b-v1.5",
|
||||
"LLM4Binary/llm4decompile-1.3b-v2",
|
||||
"Ramikan-BR/tinyllama-coder-py-v11",
|
||||
"maywell/Synatra-7B-Instruct-v0.2",
|
||||
"Tapask/telecom-oss-8b-merged",
|
||||
"LeoLM/leo-hessianai-7b-chat-bilingual",
|
||||
"malhajar/Mistral-7B-v0.2-meditron-turkish",
|
||||
"maywell/PiVoT-SOLAR-10.7B-RP",
|
||||
"allenai/intent-aware-lfqa-llama3-8b-intent-explicit",
|
||||
"Skywork/Skywork-Critic-Llama-3.1-8B",
|
||||
"proxectonos/Llama-3.1-Carballo-Instr3",
|
||||
"maywell/Synatra-10.7B-v0.4",
|
||||
"proxectonos/Carballo-Legal",
|
||||
"UmbrellaInc/Wesker-Project-3.2-1B",
|
||||
"inclusionAI/AReaL-boba-2-32B",
|
||||
"migtissera/Synthia-v3.0-11B",
|
||||
"vicgalle/RoleBeagle-11B",
|
||||
"ehristoforu/RQwen-v0.1",
|
||||
"llm-jp/llm-jp-4-32b-a3b-base",
|
||||
"bigcode/starcoder-co-format",
|
||||
"lyogavin/Anima-7B-100K",
|
||||
"raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE",
|
||||
"mii-community/zefiro-7b-dpo-ITA",
|
||||
"thirdeyeai/SmolLM2-1.7B-Instruct-Uncensored",
|
||||
"LeoLM/leo-hessianai-7b",
|
||||
"ibm-granite/GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3",
|
||||
"Xtra-Computing/XtraGPT-7B",
|
||||
"bigcode/starcoder-co-target",
|
||||
"uproai/Rose-2x7B",
|
||||
"ReDiX/Qwen2.5-0.5B-Instruct-ITA",
|
||||
"CLMBR/binding-c-command-transformer-0",
|
||||
"MaLA-LM/emma-500-llama3.1-8b-bi",
|
||||
"freewheelin/free-solar-evo-v0.13",
|
||||
"bigcode/starcoder-xo",
|
||||
"DavidAU/Rocinante-X-12B-v1-Heretic-Uncensored",
|
||||
"mrsanskar19/my_first_model",
|
||||
"cs-552-2026-vibe-trainers/math_model",
|
||||
"jburnford/dyslexic-writer-qwen3-0.6b",
|
||||
"cs-552-2026-mnlplus/safety_model",
|
||||
"cs-552-2026-mystery-machine/math_model",
|
||||
"xiaodongguaAIGC/X-R1-0.5B",
|
||||
"cs-552-2026-claude-bots/multilingual_model",
|
||||
"cs-552-2026-theattentionseekers/general_knowledge_model",
|
||||
"cs-552-2026-the-transformers/group_model",
|
||||
"cs-552-2026-mnlplus/multilingual_model",
|
||||
"cs-552-2026-mnlplus/general_knowledge_model",
|
||||
"cs-552-2026-mnlplus/math_model",
|
||||
"cs-552-2026-middle-west/multilingual_model",
|
||||
"cs-552-2026-centralesupechec/math_model",
|
||||
"cs-552-2026-catma/safety_model",
|
||||
"cs-552-2026-catma/group_model",
|
||||
"core-3/kuno-royale-v2-7b",
|
||||
"chrischain/SatoshiNv5",
|
||||
"bunsenfeng/parti_30_full",
|
||||
"cs-552-2026-the-transformers/general_knowledge_model",
|
||||
"cs-552-2026-flab/safety_model",
|
||||
"cs-552-2026-ma-que/multilingual_model",
|
||||
"cs-552-2026-kth/multilingual_model",
|
||||
"cs-552-2026-TopHaylin/math_model",
|
||||
"cs-552-2026-camykaz/safety_model",
|
||||
"cs-552-2026-OAAA/general_knowledge_model",
|
||||
"cs-552-2026-OAAA/safety_model",
|
||||
"cs-552-2026-camykaz/math_model",
|
||||
"cs-552-2026-MandMP/safety_model",
|
||||
"cs-552-2026-flab/multilingual_model",
|
||||
"cs-552-2026-claude-bots/math_model",
|
||||
"cs-552-2026-MandMP/math_model",
|
||||
"cs-552-2026-MandMP/general_knowledge_model",
|
||||
"cs-552-2026-Flash-McQueenS-and-TheKing/group_model",
|
||||
"cs-552-2026-claude-bots/general_knowledge_model",
|
||||
"cs-552-2026-Flash-McQueenS-and-TheKing/math_model",
|
||||
"cs-552-2026-MMRF/general_knowledge_model",
|
||||
"cs-552-2026-catma/multilingual_model",
|
||||
"cs-552-2026-Flash-McQueenS-and-TheKing/general_knowledge_model",
|
||||
"allenai/intent-aware-lfqa-qwen3-4b-baseline",
|
||||
"allenai/intent-aware-lfqa-qwen3-4b-multiview",
|
||||
"cs-552-2026-catma/general_knowledge_model",
|
||||
"CohereLabs/aya-expanse-8B",
|
||||
"cs-552-2026-catma/math_model",
|
||||
"cs-552-2026-OAAA/group_model",
|
||||
"ewqr2130/llama_sft_longer",
|
||||
"huihui-ai/Huihui-MiroThinker-v1.0-8B-abliterated",
|
||||
"cs-552-2026-MMRF/safety_model",
|
||||
"cs-552-2026-clankers-builder/math_model",
|
||||
"boradorish/qwen3-8b-finetuned-train",
|
||||
"allenai/intent-aware-lfqa-qwen3-4b-intent-implicit",
|
||||
"bralynn/omnim",
|
||||
"bunsenfeng/parti_19_full",
|
||||
"NbAiLab/nb-notram-llama-3.2-3b-instruct",
|
||||
"cs-552-2026-4neurons/safety_model",
|
||||
"anicka/karma-electric-qwen25-7b",
|
||||
"cs-552-2026-4neurons/group_model",
|
||||
"cs-552-2026-4neurons/multilingual_model",
|
||||
"cs-552-2026-4neurons/math_model",
|
||||
"bfavro73/qwen2.5-coder-1.5b-pandas-dpo-aligned",
|
||||
"bfavro73/qwen2.5-coder-7b-pandas-dpo-aligned",
|
||||
"beyoru/Luna-Ethos",
|
||||
"adriangg04/TheLastOfUs-QA",
|
||||
"mychen76/mistral-7b-merged-ties",
|
||||
"lihaoxin2020/qwen3-4b-sft-gpt54-ep2-evolving-rubric-gpt41-step100",
|
||||
"lihaoxin2020/qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt41-step100",
|
||||
"anonymuspj7/model_sft_resta",
|
||||
"anonymuspj7/model_sft_dare_resta",
|
||||
"anonymuspj7/model_sft_dare",
|
||||
"clglavan/magos-k8s-0.6b",
|
||||
"continuum-ai/qwen2.5-1.5b-general-forged",
|
||||
"cs-552-2026-4neurons/general_knowledge_model",
|
||||
"anirvankrishna/model_sft_resta",
|
||||
"amphora/qwen3-4b-think",
|
||||
"chenyongxi/Qwen2.5-1.5B-DPO-1.5B",
|
||||
"carnival13/model_sft_merged",
|
||||
"berkerbatur/qwen-0.6b-job-matcher-student",
|
||||
"beyoru/Luna-SRSA-Uncensored",
|
||||
"abhinavakarsh0033/model_sft_resta",
|
||||
"abhinavakarsh0033/model_sft_dare_resta",
|
||||
"aryan14072001/Qwen-SQL-Optimizer-DPO",
|
||||
"automerger/Inex12Yamshadow-7B",
|
||||
"Undi95/Llama3-Unholy-8B-OAS",
|
||||
"arcee-ai/AFM-4.5B",
|
||||
"anujjamwal/OpenMath-Nemotron-1.5B-PruneAgnostic",
|
||||
"anujjamwal/OpenMath-Nemotron-1.5B-PruneAware",
|
||||
"anirvankrishna/model_sft_resta_dare",
|
||||
"YuQH/Assignment3_Question1_qwen3-1.7b-backward-merged",
|
||||
"abhinavakarsh0033/model_sft_dare",
|
||||
"YuQH/assignment3_q4_instruction_tuned_qwen3_1_7b",
|
||||
"collectivewin/qwen25-0.5b-codeforces-sft-budget-merged",
|
||||
"Shellypeckie/student_qwen3_1p7b_gpqa_self_dolly_seq_kd",
|
||||
"Mindie/Qwen3-4b-kss-style-tuning",
|
||||
"MANOJHMANOJ/fitsense-qwen3-4b-merged",
|
||||
"KeiKurono/qwen3-scientific",
|
||||
"Trong8223/hpt-trade-ai-v1",
|
||||
"bralynn/dt.think1.128.256.25",
|
||||
"lihaoxin2020/qwen3-4b-sft-gpt54-ep2-evolving-rubric-gpt41-step200",
|
||||
"lihaoxin2020/qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt41-step200",
|
||||
"automerger/Experiment27Pastiche-7B",
|
||||
"ZigZeug/Baatukaay-Qwen2.5-3B-Wolof",
|
||||
"adsyamsafa/Nixia1.0-0.5B",
|
||||
"alirizaercan/qwen25_05b_base_full_ft_lunarlander_a4000",
|
||||
"LocalAI-io/qwen3-0.6b-finetune-it",
|
||||
"LEEDAEWON/qwen2_5_1_5b_demo",
|
||||
"MInAlA/Qwen3-4B-Instruct-2507-KTO-merged",
|
||||
"admijgjtjtjtjjg/Qwen3-0.6B-Micro-5M",
|
||||
"Kimyayd/Qwen-1.5B-Fongbe-Translator",
|
||||
"Jason-hu/Qwen2.5-3B-GSM8K-SFT",
|
||||
"Issactoto/qwen2.5-1.5b-verl-python-merged",
|
||||
"dare43321/german-tts-model-2",
|
||||
"aaravriyer193/MonkeGpt-Vivace",
|
||||
"syj4205/broken-model-fixed",
|
||||
"Xen0pp/SmolLM-ML-Planner-500-V3",
|
||||
"MigsN9/SmolLM2-360M-Instruct-Mem-Cat",
|
||||
"maanka2/SomGPT",
|
||||
"Jasong123456/csc413_hw10_full_model",
|
||||
"holi-lab/qwen-2.5-1.5b-multiwoz-finetuned",
|
||||
"Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties_density0.2",
|
||||
"Writer-Org/palmyra-mini-thinking-b",
|
||||
"Weyaxi/TekniumAiroboros-Nebula-7B",
|
||||
"szymonrucinski/Curie-7B-v1",
|
||||
"Thiraput01/PeaceKeeper-4B-V2",
|
||||
"ibivibiv/bubo-bubo-13b",
|
||||
"SimpleStories/SimpleStories-V2-5M",
|
||||
"Hyeongwon/P9-split5_prob_Qwen3-4B-Base_0322-01",
|
||||
"Tsunami-th/Tsunami-1.0-14B-Instruct",
|
||||
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_1",
|
||||
"TeeZee/DarkForest-20B-v2.0",
|
||||
"artificialguybr/QWEN-2.5-0.5B-Synthia-II",
|
||||
"open-thoughts/OpenThinker-Agent-v1",
|
||||
"laion/r2egym-nl2bash-stack-bugsseq-fixthink-again",
|
||||
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_2",
|
||||
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_3",
|
||||
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_4",
|
||||
"Trong8223/hpt-trade-ai-v2",
|
||||
"PrimeIntellect/Qwen2.5-0.5B-Reverse-Text-SFT",
|
||||
"mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini-qwen",
|
||||
"mncai/Mistral-7B-guanaco-1k-orca_platy-1k",
|
||||
"zypchn/BehChat-v3",
|
||||
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_5",
|
||||
"Lixing-Li/Llama-3.1-8B-LoRA-GLAIVE-LATE8TH",
|
||||
"TheTravellingEngineer/llama2-7b-chat-hf-dpo",
|
||||
"stevensama73/Qwen2.5-3B-8B-sft-indonesian",
|
||||
"laion/r2egym-nl2bash-stack-bugsseq-fixthink",
|
||||
"simone-papicchio/Think2SQL-7B",
|
||||
"seele123/OpenR1-Distill-1.5B-ours",
|
||||
"laion/openthoughts-4-code-qwen3-32b-annotated-32k_qwen2.5-1.5B_32k",
|
||||
"laion/nl2bash-verified-GLM-4.6-traces-32ep-32k-mgn5e4_Qwen3-8B",
|
||||
"laion/nemotron-100000-opt100k__Qwen3-8B",
|
||||
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_6",
|
||||
"AlfredPros/CodeLlama-7b-Instruct-Solidity",
|
||||
"TitleOS/Phi-4-mini-reasoning-heretic",
|
||||
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_8",
|
||||
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_7",
|
||||
"SanjiWatsuki/Kunoichi-7B",
|
||||
"AliMaatouk/Llama-3.2-1B-Tele",
|
||||
"prithivMLmods/Bellatrix-Tiny-3B-R1",
|
||||
"m-a-p/Qwen2-Instruct-7B-COIG-P",
|
||||
"zypchn/BehChat-llama-SFT-v2",
|
||||
"TURKCELL/Turkcell-LLM-7b-v1",
|
||||
"Alelcv27/Llama3.2-3B-base-Code",
|
||||
"prithivMLmods/Sqweeks-7B-Instruct",
|
||||
"maxidl/Llama-OpenReviewer-8B",
|
||||
"yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_375-2",
|
||||
"Thiraput01/PeaceKeeper-4B-V4",
|
||||
"m-a-p/Qwen2.5-Instruct-7B-COIG-P",
|
||||
"SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE",
|
||||
"cycloneboy/CscSQL-Merge-Qwen2.5-Coder-3B-Instruct",
|
||||
"prithivMLmods/Monoceros-QwenM-1.5B",
|
||||
"Shanghai_AI_Laboratory/AlchemistCoder-L-7B",
|
||||
"yujiepan/qwen3-tiny-random-tp",
|
||||
"prithivMLmods/rStar-Coder-Qwen3-0.6B",
|
||||
"Qwen/Qwen1.5-14B",
|
||||
"yil384/Qwen3-0.6B-full",
|
||||
"Thiraput01/PeaceKeeper-4B-V3",
|
||||
"ystemsrx/Qwen2.5-Interpreter",
|
||||
"yujiepan/baguettotron-tiny-random",
|
||||
"prithivMLmods/Cerium-Qwen3-R1-Dev",
|
||||
"QwenCollection/Nxcode-CQ-7B-orpo",
|
||||
"prithivMLmods/Viper-OneCoder-UIGEN",
|
||||
"yasserrmd/GLM4.7-Distill-LFM2.5-1.2B",
|
||||
"kairawal/Llama-3.2-3B-Instruct-PT-SynthDolly-E1-S73",
|
||||
"carsenk/llama3.2_3b_122824_uncensored",
|
||||
"prithivMLmods/Telescopium-Acyclic-Qwen3-0.6B",
|
||||
"prithivMLmods/Deneb-Qwen3-Radiation-0.6B",
|
||||
"cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct",
|
||||
"ziaulkarim245/Deepseek-R1-Phishing-Detector",
|
||||
"rLLM/rLLM-FinQA-4B",
|
||||
"aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT",
|
||||
"yam-peleg/Experiment8-7B",
|
||||
"prithivMLmods/Castula-U2-QwenRe-1.5B",
|
||||
"yam-peleg/Experiment31-7B",
|
||||
"yam-peleg/Experiment30-7B",
|
||||
"PrimeIntellect/Qwen3-8B",
|
||||
"Thiraput01/PeaceKeeper-4B",
|
||||
"PistachioAlt/Noromaid-Bagel-7B-Slerp",
|
||||
"PygmalionAI/pygmalion-2-7b",
|
||||
"yam-peleg/Experiment28-7B",
|
||||
"mlabonne/DatacampLlama-3.1-8B",
|
||||
"prithivMLmods/Pictor-1338-QwenP-1.5B",
|
||||
"prithivMLmods/Viper-Coder-v0.1",
|
||||
"NousResearch/Yarn-Llama-2-13b-128k",
|
||||
"TheDrummer/Llama-3SOME-8B-v2",
|
||||
"OpenBuddy/openbuddy-llama2-13b-v11-bf16",
|
||||
"yam-peleg/Experiment22-7B",
|
||||
"jackf857/qwen3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64",
|
||||
"ypwang61/One-Shot-RLVR-Qwen2.5-Math-1.5B-pi1",
|
||||
"Vladimirlv/ru-promptriever-qwen3-4b-attn",
|
||||
"starlight-ai/MedSearcher-1.7B",
|
||||
"lzumot/MODULARMOJO_Mistral_V1",
|
||||
"hfl/chinese-alpaca-2-1.3b-rlhf",
|
||||
"CloneBO/OracleLM",
|
||||
"HelpingAI/MediKAI",
|
||||
"VillanovaAI/Villanova-2B-2603",
|
||||
"princeton-nlp/SWE-Llama-13b",
|
||||
"MBZUAI/bactrian-x-llama-13b-merged",
|
||||
"sbordt/OLMo-2-1B-Mid",
|
||||
"Kyleyee/rDPO_hh-seed2",
|
||||
"EleutherAI/early_unlearning_annealing_baseline_ga_v3_interleaved_1_in_50_original_wmdp_papers",
|
||||
"hector-gr/RLCR-5x-priority-overconf-math",
|
||||
"Neura-Tech-AI/Neuron-14B",
|
||||
"pandaman007/llama-3.1-8b-instruct-sycophantic-steered-L12-a5",
|
||||
"idopinto/qwen3-14b-nt-gen-inv-sft-v2.2-full",
|
||||
"katanemo/Arch-Function-3B",
|
||||
"sbordt/OLMo-2-1B-1x-WD0-LR16",
|
||||
"sbordt/OLMo-2-1B-1x-WD0-LR08",
|
||||
"sbordt/OLMo-2-1B-1x-WD0-LR32",
|
||||
"arkoda/arkoda-7b-v7-2-1",
|
||||
"Kazuki1450/Qwen3-1.7B-Base_dsum_3_6_0p8_0p0_1p0_grpo_dr_grpo_42_rule",
|
||||
"EleutherAI/deep_aversion_pretraining_filtered_gdiff_v1_interleaved_1_in_100_gclip-0.5",
|
||||
"W-61/llama-3-8b-base-ultrachat-sft-4xh100",
|
||||
"xw1234gan/olympiads_Main_fixed_BaseAnchor_3B_step_8",
|
||||
"kenny2021/episodic-nothink4-merged",
|
||||
"yilmazzey/qwen2_5_7b-abstract-finetuned-ep2-b8",
|
||||
"kenny2021/episodic-nothink4-simpo-merged",
|
||||
"maxim1eu/amelia-32b-dpo-merged",
|
||||
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_SimNPO_lr5e-05_b3.5_a1_d1_g0.25_ep5",
|
||||
"Cisco1963/llmplasticity-en_de_instant_0.125_1-seed42",
|
||||
"Cisco1963/llmplasticity-zh_en_linear_0.25_1-seed42",
|
||||
"tyson0420/stack_llama-clang",
|
||||
"saishf/Fett-uccine-11B-Experiment",
|
||||
"Cisco1963/llmplasticity-fi_de_instant_0.5_1-seed42",
|
||||
"Cisco1963/llmplasticity-en_de_linear_0.125_1-seed42",
|
||||
"Cisco1963/llmplasticity-zh_fi_instant_0.125_1-seed42",
|
||||
"Cisco1963/llmplasticity-fi_en_instant_0.125_1-seed42",
|
||||
"unsloth/codellama-7b",
|
||||
"MCult01/muse-qwen3-8b",
|
||||
"zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K",
|
||||
"LorenaYannnnn/bold_formatting-Qwen3-0.6B-baseline_all_tokens-seed_2",
|
||||
"LorenaYannnnn/bold_formatting-Qwen3-0.6B-baseline_all_tokens-seed_1",
|
||||
"yufeng1/Olmo3-7B-textsummarization-type6-e1-alpha0_625-2",
|
||||
"Haeryz/Deepseek-TPPO-V2-Temp",
|
||||
"yufeng1/OpenThinker-7B-type6-e1-max-alpha0_3125-2",
|
||||
"FinaPolat/Qwen3_8B_openED",
|
||||
"myfi/parser_model_ner_4.13_ep4",
|
||||
"vimalnar/aware-ai-2nd",
|
||||
"flammenai/flammen11-mistral-7B",
|
||||
"Vikhrmodels/Vikhr-Qwen-2.5-0.5b-Instruct",
|
||||
"penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k",
|
||||
"Narsil/amall-7b",
|
||||
"kmseong/llama2_7b_chat-MBPP-FT-lr5e-5",
|
||||
"Cisco1963/llmplasticity-en_zh_linear_0.125_1-seed42",
|
||||
"Cisco1963/llmplasticity-zh_en_instant_0.25_1-seed42",
|
||||
"Cisco1963/llmplasticity-zh_fi_instant_0.5_1-seed42",
|
||||
"Cisco1963/llmplasticity-de_en_linear_0.5_1-seed42",
|
||||
"RedHatAI/SmolLM-360M-Instruct-quantized.w8a8",
|
||||
"togethercomputer/Llama-2-7B-32K-Instruct",
|
||||
"Undi95/ReMM-v2-Kimiko-v2-13B",
|
||||
"jackf857/qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4",
|
||||
"YeungNLP/firefly-llama2-13b-base",
|
||||
"gplsi/Aitana-2B-S-base-IP-1.0",
|
||||
"princeton-nlp/Llemma-7B-32K-MathMix",
|
||||
"darkmatter999/llama-2-7b-competetivecoding",
|
||||
"RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8",
|
||||
"zorobin/mistral-class-shishya-7b-ep3",
|
||||
"vicgalle/Mixtral-7Bx2-truthy",
|
||||
"sethuiyer/Chikuma_10.7B",
|
||||
"360zhinao/Light-IF-14B",
|
||||
"EscapeJeju/qwen25_1_5b_korean_unsloth",
|
||||
"OpenPipe/llama_3b_hn_story_classifier",
|
||||
"yam-peleg/Experiment2-7B",
|
||||
"ybelkada/Mistral-7B-v0.1-bf16-sharded",
|
||||
"xw1234gan/Main_fixed_MATH_3B_step_1",
|
||||
"Ihor/Text2Graph-R1-Qwen2.5-0.5b",
|
||||
"unsloth/llama-2-7b",
|
||||
"neuralmagic/SparseLlama-2-7b-cnn-daily-mail-pruned_50.2of4",
|
||||
"ThaiLLM/ThaiLLM-8B",
|
||||
"voidful/unit-desta-8b-base-llama3-8b-instruct",
|
||||
"SouravCrypto/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-striped_tawny_dove",
|
||||
"xw1234gan/Main_fixed02_MATH_3B_step_4",
|
||||
"xw1234gan/Main_MATH_3B_step_9",
|
||||
"m-a-p/Infinity-Instruct-3M-0625-Mistral-7B-COIG-P",
|
||||
"adityakum667388/lumichats-v1.1",
|
||||
"NEU-HAI/Llama-2-7b-alpaca-cleaned",
|
||||
"NousResearch/CodeLlama-34b-hf",
|
||||
"prithivMLmods/Tulu-MathLingo-8B",
|
||||
"ibm-granite/granite-8b-code-instruct-4k",
|
||||
"alexxbobr/ORPO8000Vikhr-Llama-3.2-1B-Instruct5000",
|
||||
"m-a-p/TreePO-Qwen2.5-7B",
|
||||
"fancyfeast/llama-bigasp-prompt-enhancer",
|
||||
"line-corporation/japanese-large-lm-1.7b",
|
||||
"wassname/qwen3-5lyr-tiny-random",
|
||||
"TaimurShaikh/qwen1.5-1.8b-sft",
|
||||
"l3utterfly/minima-3b-layla-v1",
|
||||
"l3utterfly/mistral-7b-v0.1-layla-v2",
|
||||
"Henrychur/MMed-Llama-3-8B",
|
||||
"gradient-spaces/respace-sg-llm-1.5b",
|
||||
"l3utterfly/minima-3b-layla-v2",
|
||||
"allenai/truthfulqa-info-judge-llama2-7B",
|
||||
"facebook/llm-compiler-7b",
|
||||
"nothingiisreal/L3.1-8B-Celeste-V1.5",
|
||||
"TaimurShaikh/qwen1.5-1.8b-dpo",
|
||||
"l3utterfly/tinyllama-1.1b-layla-v4",
|
||||
"prithivMLmods/Flerovium-Llama-3B",
|
||||
"l3utterfly/mistral-7b-v0.1-layla-v1",
|
||||
"OpenBuddy/openbuddy-mistral-7b-v13.1",
|
||||
"iCIIT/redqueenprotocol-sin-llama3.2-3B-model",
|
||||
"OpenAssistant/codellama-13b-oasst-sft-v10",
|
||||
"Unitedp2p/New-Llama-3.1-8B-Lexi-Uncensored-V2",
|
||||
"USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B",
|
||||
"Salesforce/Llama-xLAM-2-8b-fc-r",
|
||||
"uukuguy/speechless-orca-platypus-coig-lite-4k-0.6e-13b",
|
||||
"krevas/SOLAR-10.7B",
|
||||
"SykoSLM/SykoLLM-V6.0-Test",
|
||||
"l3utterfly/mistral-7b-v0.1-layla-v4",
|
||||
"argilla/distilabeled-Marcoro14-7B-slerp",
|
||||
"uzlm/alloma-8B-Instruct",
|
||||
"trillionlabs/Tri-7B",
|
||||
"nlile/PE-7b-full",
|
||||
"glaiveai/glaive-coder-7b",
|
||||
"RamziRebai/llama-2-7b-therapist-v4",
|
||||
"Lazycuber/L2-7b-Base-Guanaco-Vicuna",
|
||||
"behnamsh/gpt2_camel_physics",
|
||||
"jondurbin/spicyboros-7b-2.2",
|
||||
"argilla/distilabeled-Marcoro14-7B-slerp-full",
|
||||
"kairawal/Llama-3.2-3B-Instruct-ZH-SynthDolly-1A-E5",
|
||||
"Surpem/Supertron1-8B",
|
||||
"TIGER-Lab/Mantis-8B-siglip-llama3-pretraind",
|
||||
"Leopo1d/OpenVul-Qwen3-4B-GRPO",
|
||||
"totally-not-an-llm/PuddleJumper-13b-V2",
|
||||
"ajibawa-2023/Code-Mistral-7B",
|
||||
"unsloth/Qwen2.5-3B",
|
||||
"Jiqing/tiny-random-qwen2",
|
||||
"L33tcode/llama-3-8b-CEH-hf",
|
||||
"FlyPig23/Qwen3-4B_Paper_Impact_patent_SFT_1ep",
|
||||
"totally-not-an-llm/EverythingLM-13b-V3-16k",
|
||||
"totally-not-an-llm/EverythingLM-13b-16k",
|
||||
"ajibawa-2023/Code-290k-6.7B-Instruct",
|
||||
"mrcuddle/Lumimaid-Muse-12B",
|
||||
"how3751/coder_7B",
|
||||
"m-a-p/CT-LLM-SFT",
|
||||
"Marintosti/chsa-triage-merged",
|
||||
"m-a-p/CT-LLM-SFT-DPO",
|
||||
"inclusionAI/AReaL-boba-2-8B",
|
||||
"FreedomIntelligence/Apollo-6B",
|
||||
"mrthor102/evolai-tfm-super-004",
|
||||
"staeiou/bartleby-qwen3-1.7b_v4",
|
||||
"golgat/toolcalling-merged-demo",
|
||||
"allenai/Llama-3.1-Tulu-3-8B-SFT",
|
||||
"Kazuki1450/Olmo-3-1025-7B_dsum_3_6_tok_Certainly_1p0_0p0_1p0_grpo_dr_grpo_42_rule",
|
||||
"driaforall/Dria-Agent-a-7B",
|
||||
"ChaoticNeutrals/Eris_Remix_7B",
|
||||
"thrishala/mental_health_chatbot",
|
||||
"mlfoundations-dev/oh-dcft-v3.1-gemini-1.5-flash",
|
||||
"CompassioninMachineLearning/pretrainingBasellama3kv3",
|
||||
"venkycs/Zyte-1B",
|
||||
"mnoukhov/pythia410m-sft-tldr",
|
||||
"ali-elganzory/Baguettotron-DPO-Tulu3-decontaminated",
|
||||
"Alienpenguin10/M3PO-kl_divergence-trial1-seed123",
|
||||
"tanhao2015/MDtranslator",
|
||||
"aloobun/Reyna-CoT-4B-v0.1",
|
||||
"sstoica12/influence_metamath_qwen2.5_3b_new_detailed",
|
||||
"argilla/zephyr-7b-spin-iter1-v0",
|
||||
"Kazuki1450/Olmo-3-1025-7B_dsum_3_6_rel_1e0_1p0_0p0_1p0_grpo_sapo_42_rule",
|
||||
"FelixChao/Voldemort-10B",
|
||||
"yam-peleg/Experiment1-7B",
|
||||
"Eric111/Mistral-7B-Instruct_v0.2_UNA-TheBeagle-7b-v1",
|
||||
"ewqr2130/llama_ppo_1e6_new_tokenizerstep_8000",
|
||||
"DanielClough/Candle_TinyLlama-1.1B-Chat-v1.0",
|
||||
"rbelanec/train_qnli_42_1779286680",
|
||||
"tech27/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-amphibious_spotted_kingfisher",
|
||||
"syvai/emotion-reasoning-1b",
|
||||
"argilla/notus-7b-v1",
|
||||
"burtenshaw/SmolLM3-3B-GRPO-think",
|
||||
"ViratChauhan/Qwen3-4B-GRPO-v2",
|
||||
"zarakiquemparte/zaraxls-l2-7b",
|
||||
"AlexeySorokin/GEC-from-explanations-4BInstr-distilled-v2303",
|
||||
"Alelcv27/Qwen2.5-3B-INST-Code",
|
||||
"tiny-random/llama-3.3-dim64",
|
||||
"prithivMLmods/Triangulum-1B",
|
||||
]
|
||||
|
||||
# ══════════════════════════════════════════════════════════
|
||||
@@ -544,10 +410,10 @@ def _submit_task(token: str, model_id: str) -> Tuple[bool, str]:
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {token}",
|
||||
}
|
||||
config_content = f"""docker_image: harbor.4pd.io/hardcore-tech/cambricon-mlu370-pytorch:v25.01-torch2.5.0-torchmlu1.24.1-ubuntu22.04-py310
|
||||
nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0
|
||||
config_content = f"""gpu_type: ppu_zw_810e
|
||||
framework: vllm
|
||||
storage: gpfs
|
||||
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
|
||||
modelhub_options:
|
||||
srcRelativePath: leaderboard/modelHubXC/{model_id}
|
||||
mountPoint: /model
|
||||
@@ -555,17 +421,44 @@ sut_config:
|
||||
values:
|
||||
gpu_num: 1
|
||||
env:
|
||||
- name: MAX_MODEL_LEN
|
||||
value: 8192
|
||||
command: ["vllm", "serve", "/model", "--port", "8000", "--served-model-name", "llm", "--max-model-len", "8192", "--trust-remote-code", "--dtype", "float16"]
|
||||
- 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:
|
||||
cpu_num: 2
|
||||
gpu_num: 1
|
||||
env:
|
||||
- name: MAX_MODEL_LEN
|
||||
value: 8192
|
||||
command: ["vllm", "serve", "/model", "--port", "80", "--served-model-name", "llm", "--max-model-len", "8192", "--trust-remote-code", "--dtype", "float16"]
|
||||
- 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'
|
||||
"""
|
||||
payload = {
|
||||
"contestApiToken": CONTEST_API_TOKEN,
|
||||
|
||||
Reference in New Issue
Block a user