""" xc_validation_strategy_vllm_zhouyuanxi — 主入口 启动后针对 GPU_JOBS 中配置的 GPU 卡分别批量提交各自筛选出的模型适配任务 （/api/adapt/task/add，xc-Token 认证）。 （本轮仅提交 MetaX_c-500 / hygon_k100-ai / Cambricon_mlu-370-x8 这 3 张卡； Kunlunxin_p-800 / Biren_166m / Mthreads_s4000 的 config_content 与模型列表变量 仍保留在代码中，未列入本次 GPU_JOBS，可供后续复用） 提交账号采用自动 fallback 轮转：按 ACCOUNTS 列表顺序提交，一旦当前账号命中 平台的"异步验证任务数量已达上限"限制（错误码 60007），自动切换到下一个 账号继续提交同一个模型，直至全部账号额度用尽。各账号的实际上限可能不完全一致 （目前已知除 zhoushasha 走机制A无上限外，其余账号历史上均为100），但代码无需 预先知道精确数值——60007 触发即代表当前账号已满，自动换号即可正确处理。 之后保持 HTTP 服务存活，暴露 /health（K8s 探活）和 /status（运行状态）。 """ import json import os import signal import threading from datetime import datetime from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer from typing import List, Tuple import requests # ══════════════════════════════════════════════════════════ # 配置 # ══════════════════════════════════════════════════════════ BASE_URL = os.environ.get("BASE_URL", "https://modelhub.org.cn") ADD_TASK_ENDPOINT = "/api/adapt/task/add" TASK_TYPE = "text-generation" STRATEGY_ID = os.environ.get("STRATEGY_ID", "") # 平台自动注入，无需修改 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） # 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]] = [ ("zhangyuanxi", "zhangyuanxi", "24ed39f7f0d84fafbe0ca808e62b191c"), ("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"), ("l112233", "l112233", "40cb6910dc9a442a816298a228da65ac"), ("l11223344", "l11223344", "e1c0db2959e5411f9342c8550b03f6e9"), ] # ══════════════════════════════════════════════════════════ # 各 GPU 的模型列表（来自 filter_verified_models 脚本的筛选结果） # ══════════════════════════════════════════════════════════ METAX_MODELS = [ "emrevrg/Norovox-Alpha-MoE-7.0B", "MusePublic/stable-diffusion-xl-base", "emrevrg/Norovox-Alpha-MoE-1.2B", "emrevrg/Norovox-Alpha-MoE-3.9B", "DCAgent/g1_clean_hybrid_25k_32b", "CaoruiLi/DefectVideoReward", "ConstDemi/vikhr-nemo-12b-instruct-r-awq", "sapidlabs/Sparkulator-GLM-5.2", "pei39/deepseek_r1_distill_qwen_7b_awq_rag", "fpadovani/jpn-jpan-100mb-ppt-Dp-10mb_seed10", "devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_conj_ratio_0p25_mix_0p25_43", "iamsiddj/EducatorHelperModel", "fpadovani/jpn-jpan-100mb-after-ppt-Dp-100mb-ckpt500_seed10", "devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_wh_v2_ratio_1p00_mix_0p25_44", "anicka/ke-v9-8b", "fpadovani/eng-latn-10mb-ppt-shuff-dyck-disjoint-tok_seed3407", "ilhkn/my-awesome-setfit-model", "fpadovani/eng-latn-10mb-ppt-shuff-dyck-10mb_seed10", "Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV", "fpadovani/eng-latn-10mb-ppt-Dp-100mb_seed10", "penupup/quora-distilbert-multilingual-lcqmc-sfa-hr", "hroth/psais-paraphrase-multilingual-MiniLM-L12-v2-20shot", "hroth/psais-LaBSE-10shot", "LamNguyen0904/vistral-medical-adapter", "Jolieb/tinyllama-lora-object-sorting", "nessy-studio/poison-gemma", "fpadovani/dan-latn-10mb-after-ppt-Dp-10mb-ckpt500_seed3407", "flywheel-ai/real-estate", "famseamus/LFM2.5-DCR-8B-A1B", "Blackfrost-AI/Lumix-4B", "ibm-granite/granite-34b-code-base-8k", "microsoft/Dayhoff-3b-UR90-10000", "microsoft/Dayhoff-3b-UR90-10", "developer-lunark/Qwen3-30B-Korean-Roleplay", "kshitijthakkar/loggenix-moe-0.3B-A0.1B-smolagents-v0-grpo", "trl-internal-testing/tiny-Phi3ForCausalLM-3.5", "dfgertg/idk", "LeVraiCNL/ornith_finetune_v3", "yuchen-zhu-zyc/HybridDiffusion-2B", "bardsai/finance-sentiment-zh-fast", "fpadovani/jpn-jpan-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed455", "berkbirkan/gemma-3-lora-finetune-x-replies", "nm-testing/Qwen3-4B-mixed-quant-RTN-wNaM-a4", "infgrad/Prism-Qwen3.5-Reranker-0.8B", "ngocnamk3er/dsi_transformers_code_t5_base_python", "TheDrummer/Big-Tiger-Gemma-27B-v1", "trashpanda-org/QwQ-32B-Snowdrop-v0", "WizardLMTeam/WizardCoder-33B-V1.1", "Tesslate/UIGEN-X-32B-0727", "AscendKernelGen/KernelGen-LM-32B", "charlie-li/Qwen3-Coder-30B-A3B-Instruct-Lora-ScaleSWE-Distilled-v1", "ibm-granite/granite-4.1-30b-base", "open-thoughts/OpenThinkerAgent-32B", "zai-org/chatglm-6b", "drbaph/s2-pro-fp8", "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "groxaxo/s2-pro-BnB-4Bits", "TomoroAI/tomoro-ai-colqwen3-embed-8b-awq", "TomoroAI/tomoro-ai-colqwen3-embed-4b-awq", "aleada/Phi-4-mini-instruct-W4A16", "aleada/Phi-4-W4A16", "morphllm/dspark-glm52-draft", "kanishka/opt-babylm1_no_preemption_laugh_seed-211_5e-6", "bachvnju/qwen3-0.6b-coder", "xpuenabler/gpt-oss-15.5b-23E-SFT", "cyber-pal-security/CyberPal2.0-20B", "LeaderboardModel1/grug-27b-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwythos-9B-Claude-Mythos-5-1M-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwevolution-V0-27B-AutoRound-W4A16-RTN", "LeaderboardModel1/Qwen3.6-35B-A3B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwen3.5-4B-AutoRound-W4A16-RTN", "YeungNLP/firefly-baichuan-7b-qlora-sft", "LeaderboardModel1/Qwen-AgentWorld-35B-A3B-AutoRound-W4A16-RTN", "LeaderboardModel1/Ornith-1.0-35B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Code-Writer-V2-Obliterated-BF16-AutoRound-W4A16-RTN", "LeaderboardModel1/Agents-A1-AutoRound-W4A16-RTN", "Qwen/WebWorld-32B", "24B-Suite/Mergedonia-PROMETHEUS-24B-v1", "zjiayu064/Qwen3-Next-80B-A3B-Instruct-BitsMoE-2bit", "praxisresearch/hf_olmo_32b_em_finrisk_1", "RESMP-DEV/jina-code-embeddings-1.5b-mxfp4-block-gptq", "praxisresearch/hf_olmo_32b_em_finrisk_0", "praxisresearch/hf_olmo_32b_em_badmed_1", "praxisresearch/hf_olmo_32b_em_badmed_0", "Mohamed-Sami-Ghrab/moove-qwen3-32b-medical-sft-v2", "Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only", "pki/nova-24b-cybersec", "ReadyArt/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B", "Kwai-AutoSQL/Kwai-AutoSQL-32B", ] KUNLUNXIN_MODELS = [ "AI-ModelScope/granite-20b-code-base", "vllm-ascend/Qwen3-32B-w8a8sc-310-vllm-tp4", "KenDual3090tiNvlink/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-W4A16", "AI-ModelScope/granite-20b-code-instruct-8k", "AI-ModelScope/granite-20b-code-base-8k", "openbmb/MiniCPM4-8B-marlin-cpmcu", "AI-ModelScope/granite-20b-code-instruct", "openbmb/MiniCPM4-8B-marlin-Eagle-vLLM", "CaoruiLi/DefectVideoReward", "fpadovani/jpn-jpan-100mb-ppt-Dp-10mb_seed10", "devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_conj_ratio_0p25_mix_0p25_43", "iamsiddj/EducatorHelperModel", "google/gemma-2b-cpp", "hroth01/psais-all-MiniLM-L6-v2-20shot", "devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_wh_v2_ratio_1p00_mix_0p25_44", "anicka/ke-v9-8b", "EBLANSoft/eblangpt-falos67", "fpadovani/eng-latn-10mb-ppt-shuff-dyck-disjoint-tok_seed3407", "ilhkn/my-awesome-setfit-model", "fpadovani/eng-latn-10mb-ppt-Dp-100mb_seed10", "penupup/quora-distilbert-multilingual-lcqmc-sfa-hr", "hroth/psais-paraphrase-multilingual-MiniLM-L12-v2-20shot", "hroth/psais-LaBSE-10shot", "malaiwah/GLM-5.2-SIQ-Fruit-Instruct", "fpadovani/eng-latn-100mb-ppt-shuff-dyck-100mb_seed10", "arshiysohrevardi/moeinGTS1.5-1.5b", "Q1ngMang/LFM2.5-350M-PT-zh_CN", "fpadovani/dan-latn-10mb-after-ppt-Dp-10mb-ckpt500_seed3407", "flywheel-ai/real-estate", "hroth/psais-all-MiniLM-L6-v2-1shot", "stjiris/bert-large-portuguese-cased-legal-tsdae", "bartowski/deepseek-llm-7b-base-exl2", "lsm0729/Qwen2.5-VL-3B-Instruct-quantized.w8a8", "LeVraiCNL/ornith_finetune_v3", "fawazatvetted/fine_tuned_mpnetv3", "cjos/my-awesome-setfit-model", "litert-community/Ministral-3-3B-Reasoning-2512", "mizzaay/6de7a1b5", "MU-Kindai/SBERT-JSNLI-base", "JoBeer/multi-qa-mpnet-base-dot-v1-eclass", "pkshatech/simcse-ja-bert-base-clcmlp", "amd/Phi-4-mini-instruct-onnx-ryzenai-hybrid", "amd/Phi-3.5-mini-instruct-onnx-ryzenai-hybrid", "louisbetsch/new-classification-model", "aammari/setfit-zero-shot-classification-pbsp-p3-cons", "JoBeer/all-mpnet-base-v2-eclass", "arithmetic-circuit-overloading/gpt2-64D-1L-4H", "aammari/setfit-zero-shot-classification-pbsp-p3-trig", "gart-labor/eng-distilBERT-se-eclass", "arithmetic-circuit-overloading/gpt2-256D-1L-8H", "gemasphi/f-real-setfit-ss-paraphrase-multilingual-mpnet-base-v2", "fawazatvetted/fine_tuned_mpnetv2", "leerobert/my-awesome-setfit-model", "aleada/Phi-4-mini-instruct-W4A16", "aleada/Phi-4-W4A16", "lewtun/setfit-minilm-distilled-test", "aparna1595/bert-mpnet-sentence", "amd/Phi-4-mini-reasoning-onnx-ryzenai-hybrid", "mssongit/fndeberta-sentence", "amd/Phi-3.5-mini-instruct-onnx-ryzenai-npu", "amd/Phi-3-mini-4k-instruct-onnx-ryzenai-hybrid", "aammari/setfit-zero-shot-classification-pbsp-p3-dur", "aammari/setfit-zero-shot-classification-pbsp-p3-freq", "dlicari/distil-ita-legal-bert", "aammari/setfit-zero-shot-classification-pbsp-p3-bhvr", "dlicari/sentence-ita-eurlex-bert-base", "lsanochkin/setfit-rubert-intent", "LeaderboardModel1/grug-27b-AutoRound-W4A16-Tuning", "microsoft/VibeVoice-Realtime-0.5B", "ShwetActhq/dummy_setfit", "gemasphi/real-setfit-ss-paraphrase-multilingual-mpnet-base-v2", "OpenVoiceOS/canary-qwen-2.5b-onnx", "LeaderboardModel1/Qwythos-9B-Claude-Mythos-5-1M-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwevolution-V0-27B-AutoRound-W4A16-RTN", "LeaderboardModel1/Qwen3.6-35B-A3B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwen3.5-4B-AutoRound-W4A16-RTN", "YeungNLP/firefly-baichuan-7b-qlora-sft", "LeaderboardModel1/Qwen-AgentWorld-35B-A3B-AutoRound-W4A16-RTN", "LeaderboardModel1/Ornith-1.0-35B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Code-Writer-V2-Obliterated-BF16-AutoRound-W4A16-RTN", "salihfurkaan/Qwen2.5-VL-ScienceQA-Math-CoT-Merged", "LeaderboardModel1/Agents-A1-AutoRound-W4A16-RTN", "aammari/setfit-zero-shot-classification-pbsp-p1", "meta-llama/Prompt-Guard-86M", "kornwtp/ConGen-paraphrase-multilingual-mpnet-base-v2", "zjiayu064/Qwen3-Next-80B-A3B-Instruct-BitsMoE-2bit", "kornwtp/ConGen-simcse-model-roberta-base-thai", "praxisresearch/hf_olmo_32b_em_finrisk_1", "gemasphi/setfit-ss-paraphrase-multilingual-mpnet-base-v2", "RESMP-DEV/jina-code-embeddings-1.5b-mxfp4-block-gptq", "praxisresearch/hf_olmo_32b_em_finrisk_0", "praxisresearch/hf_olmo_32b_em_badmed_1", "praxisresearch/hf_olmo_32b_em_badmed_0", "lmxhappy/brand_bert", "kamalkraj/BioSimCSE-BioLinkBERT-BASE", "lmxhappy/tiyu_bert", "ReadyArt/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B", "Kwai-AutoSQL/Kwai-AutoSQL-32B", "ibaucells/paraphrase-multilingual-mpnet-base-v2_tecla_label2_8", "futuredatascience/action-classifier-v2", "LoneStriker/Orca-2-13b-5.0bpw-h6-exl2", "futuredatascience/to-classifier-v2", "futuredatascience/from-classifier-v2", "shrinivasbjoshi/r2-w266-setfit-mbti-multiclass-hypsearch-mpnet-nov30", ] BIREN_MODELS = [ "emrevrg/Norovox-Alpha-MoE-7.0B", "emrevrg/Norovox-Alpha-MoE-1.2B", "emrevrg/Norovox-Alpha-MoE-3.9B", "AI-ModelScope/granite-20b-code-base", "vllm-ascend/Qwen3-32B-w8a8sc-310-vllm-tp4", "KenDual3090tiNvlink/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-W4A16", "AI-ModelScope/granite-20b-code-instruct-8k", "openbmb/MiniCPM4-8B-marlin-cpmcu", "openbmb/MiniCPM4-8B-marlin-Eagle-vLLM", "CaoruiLi/DefectVideoReward", "ConstDemi/vikhr-nemo-12b-instruct-r-awq", "pei39/deepseek_r1_distill_qwen_7b_awq_rag", "devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_conj_ratio_0p25_mix_0p25_43", "RadixArk/Qwen3.8-27B-DSpark", "iamsiddj/EducatorHelperModel", "google/gemma-2b-cpp", "hroth01/psais-all-MiniLM-L6-v2-20shot", "devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_wh_v2_ratio_1p00_mix_0p25_44", "EBLANSoft/eblangpt-falos67", "ilhkn/my-awesome-setfit-model", "Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV", "EleutherAI/quirky-pythia-410m-mixture", "penupup/quora-distilbert-multilingual-lcqmc-sfa-hr", "nomic-ai/nomic-embed-text-v2-moe", "Jolieb/tinyllama-lora-object-sorting", "arshiysohrevardi/moeinGTS1.5-1.5b", "Xenova/pythia-410m-deduped", "Q1ngMang/LFM2.5-350M-PT-zh_CN", "nessy-studio/poison-gemma", "flywheel-ai/real-estate", "Pacific-i64/TR-MOE-306", "bartowski/internlm2-chat-20b-llama-old", "farbodtavakkoli/OTel-LLM-E4B-IT", "hroth/psais-all-MiniLM-L6-v2-1shot", "famseamus/LFM2.5-DCR-8B-A1B", "narendarcodes/adaption-sec-financial-arithmetic-109b", "narendarcodes/adaption-gpt-oss-120b-telugu-instruct", "stjiris/bert-large-portuguese-cased-legal-tsdae", "bartowski/deepseek-llm-7b-base-exl2", "Blackfrost-AI/Lumix-4B", "developer-lunark/Qwen3-30B-Korean-Roleplay", "kshitijthakkar/loggenix-moe-0.3B-A0.1B-smolagents-v0-grpo", "LLM-Research/Phi-4-mini-flash-reasoning", "ib-ssm/mamba2-8b-3t-4k-hf", "dfgertg/idk", "LeVraiCNL/ornith_finetune_v3", "fawazatvetted/fine_tuned_mpnetv3", "riccardozaccone96/flexrank-llama3.2-1B", "yuchen-zhu-zyc/HybridDiffusion-2B", "fpadovani/jpn-jpan-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed455", "infgrad/Prism-Qwen3.5-Reranker-0.8B", "cjos/my-awesome-setfit-model", "BananaMind/BananaMind-2-Nano", "litert-community/Ministral-3-3B-Reasoning-2512", "livadies/Bonsai-27B-Android-Local", "blockblockblock/Qwen2.5-0.5B-Instruct-exl3-3.0bpw", "WizardLMTeam/WizardCoder-33B-V1.1", "amd/Phi-4-mini-instruct-onnx-ryzenai-hybrid", "Tesslate/UIGEN-X-32B-0727", "AscendKernelGen/KernelGen-LM-32B", "charlie-li/Qwen3-Coder-30B-A3B-Instruct-Lora-ScaleSWE-Distilled-v1", "open-thoughts/OpenThinkerAgent-32B", "drbaph/s2-pro-fp8", "groxaxo/s2-pro-BnB-4Bits", "TomoroAI/tomoro-ai-colqwen3-embed-8b-awq", "TomoroAI/tomoro-ai-colqwen3-embed-4b-awq", "aleada/Phi-4-mini-instruct-W4A16", "aleada/Phi-4-W4A16", "amd/Phi-4-mini-reasoning-onnx-ryzenai-hybrid", "amd/Phi-3.5-mini-instruct-onnx-ryzenai-npu", "amd/Phi-3-mini-4k-instruct-onnx-ryzenai-hybrid", "cyber-pal-security/CyberPal2.0-20B", "LeaderboardModel1/grug-27b-AutoRound-W4A16-Tuning", "Qwen/Qwen-AgentWorld-35B-A3B", "jinxing6609/olmo3-7b-zh-merged", "LeaderboardModel1/Qwythos-9B-Claude-Mythos-5-1M-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwevolution-V0-27B-AutoRound-W4A16-RTN", "LeaderboardModel1/Qwen3.6-35B-A3B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwen3.5-4B-AutoRound-W4A16-RTN", "LeaderboardModel1/Qwen-AgentWorld-35B-A3B-AutoRound-W4A16-RTN", "LeaderboardModel1/Ornith-1.0-35B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Code-Writer-V2-Obliterated-BF16-AutoRound-W4A16-RTN", "LeaderboardModel1/Agents-A1-AutoRound-W4A16-RTN", "Qwen/WebWorld-32B", "24B-Suite/Mergedonia-PROMETHEUS-24B-v1", "zjiayu064/Qwen3-Next-80B-A3B-Instruct-BitsMoE-2bit", "praxisresearch/hf_olmo_32b_em_finrisk_1", "RESMP-DEV/jina-code-embeddings-1.5b-mxfp4-block-gptq", "praxisresearch/hf_olmo_32b_em_finrisk_0", "praxisresearch/hf_olmo_32b_em_badmed_1", "praxisresearch/hf_olmo_32b_em_badmed_0", "allenai/MolmoAct-7B-D-Pretrain-0812", "allenai/MolmoAct-7B-D-LIBERO-Object-0812", "Mohamed-Sami-Ghrab/moove-qwen3-32b-medical-sft-v2", "pki/nova-24b-cybersec", "ReadyArt/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B", "Kwai-AutoSQL/Kwai-AutoSQL-32B", "litert-community/gemma-3-270m-it", "LoneStriker/Orca-2-13b-5.0bpw-h6-exl2", ] CAMBRICON_MODELS = [ "emrevrg/Norovox-Alpha-MoE-7.0B", "emrevrg/Norovox-Alpha-MoE-1.2B", "emrevrg/Norovox-Alpha-MoE-3.9B", "AI-ModelScope/granite-20b-code-base", "llm-jp/llm-jp-4-32b-a3b-thinking", "vllm-ascend/Qwen3-32B-w8a8sc-310-vllm-tp4", "YOYO-AI/ZYH-LLM-Qwen2.5-14B-V2", "DCAgent/g1_clean_hybrid_25k_32b", "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "KoboldAI/fairseq-dense-13B-Janeway", "KenDual3090tiNvlink/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-W4A16", "AI-ModelScope/granite-20b-code-instruct-8k", "openbmb/MiniCPM4-8B-marlin-cpmcu", "AI-ModelScope/granite-20b-code-instruct", "openbmb/MiniCPM4-8B-marlin-Eagle-vLLM", "CaoruiLi/DefectVideoReward", "ConstDemi/vikhr-nemo-12b-instruct-r-awq", "sapidlabs/Sparkulator-GLM-5.2", "pei39/deepseek_r1_distill_qwen_7b_awq_rag", "fpadovani/jpn-jpan-100mb-ppt-Dp-10mb_seed10", "Zynerji/Ektome-Qwen3-VL-4Bi-PristinelyUncensored", "Zynerji/Ektome-Qwen3-VL-2Bi-PristinelyUncensored", "iamsiddj/EducatorHelperModel", "vorenthiclabs/vorenthos-vision-thinking-qwq-7b", "lodestones/gemma-7b-flax", "google/gemma-2b-cpp", "jinaai/jina-reranker-v3.5", "hroth01/psais-all-MiniLM-L6-v2-20shot", "anicka/ke-v9-8b", "EBLANSoft/eblangpt-falos67", "fpadovani/eng-latn-10mb-ppt-shuff-dyck-disjoint-tok_seed3407", "ilhkn/my-awesome-setfit-model", "Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV", "fpadovani/eng-latn-10mb-ppt-Dp-100mb_seed10", "penupup/quora-distilbert-multilingual-lcqmc-sfa-hr", "hroth/psais-paraphrase-multilingual-MiniLM-L12-v2-20shot", "hroth/psais-LaBSE-10shot", "TurkuNLP/web-register-classification-multilingual", "malaiwah/GLM-5.2-SIQ-Fruit-Instruct", "nomic-ai/nomic-embed-text-v2-moe", "Udoba45/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-tall_thorny_boar", "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "LamNguyen0904/vistral-medical-adapter", "Jolieb/tinyllama-lora-object-sorting", "ibm-granite/granite-embedding-30m-sparse", "arshiysohrevardi/moeinGTS1.5-1.5b", "Undi95/Mistral-11B-OmniMix", "Xenova/pythia-410m-deduped", "Undi95/Mistral-11B-CC-Air", "Q1ngMang/LFM2.5-350M-PT-zh_CN", "nessy-studio/poison-gemma", "Undi95/Mistral-11B-Airoboros-v0.1", "flywheel-ai/real-estate", "hroth/psais-all-MiniLM-L6-v2-1shot", "stjiris/bert-large-portuguese-cased-legal-tsdae", "bartowski/deepseek-llm-7b-base-exl2", "llm-semantic-router/mmbert-fact-check-merged", "LeVraiCNL/ornith_finetune_v3", "fawazatvetted/fine_tuned_mpnetv3", "berkbirkan/gemma-3-lora-finetune-x-replies", "nm-testing/Qwen3-4B-mixed-quant-RTN-wNaM-a4", "infgrad/Prism-Qwen3.5-Reranker-0.8B", "cjos/my-awesome-setfit-model", "OpenMed/OpenMed-PII-French-BioClinicalBERT-Base-110M-v1", "seerware/granite-embedding-30m-sparse", "MU-Kindai/SBERT-JSNLI-base", "OpenMed/OpenMed-PII-French-BiomedELECTRA-Large-335M-v1", "JoBeer/multi-qa-mpnet-base-dot-v1-eclass", "OpenMed/OpenMed-PII-French-BiomedELECTRA-Base-110M-v1", "OpenMed/OpenMed-PII-French-BiomedBERT-Large-340M-v1", "infgrad/Prism-Qwen3.5-Reranker-4B", "pkshatech/simcse-ja-bert-base-clcmlp", "RCouronnePEReN/gpt2_finetuned_overfit-10epochs-128tokens", "q-future/Q-ReAlign-Pro-9B", "vrfai/gemma-4-12B-it-fp8", "amd/Phi-4-mini-instruct-onnx-ryzenai-hybrid", "OpenMed/OpenMed-PII-German-BioClinicalBERT-Base-110M-v1", "louisbetsch/new-classification-model", "Trendyol/Trendyol-LLM-Asure-12B", "OpenMed/OpenMed-PII-German-BiomedELECTRA-Large-335M-v1", "OpenMed/OpenMed-PII-German-BiomedELECTRA-Base-110M-v1", "OpenMed/OpenMed-PII-German-BiomedBERT-Base-110M-v1", "aammari/setfit-zero-shot-classification-pbsp-p3-cons", "JoBeer/all-mpnet-base-v2-eclass", "BalaRajesh1/mmbert-small-nli", "aammari/setfit-zero-shot-classification-pbsp-p3-trig", "charlie-li/Qwen3-Coder-30B-A3B-Instruct-Lora-ScaleSWE-Distilled-v1", "quanda-bench-test/gpt2-small-trex-openwebtext-hf", "quanda-bench-test/gpt2-small-trex-hf", "quanda-bench-test/gpt2-small-trex-wikitext-ft-hf", "quanda-bench-test/gpt2-small-trex-wikitext-hf", "quanda-bench-test/gpt2-small-trex-openwebtext-ft-hf", "quanda-bench-test/gpt2-small-trex-ft-hf", "gart-labor/eng-distilBERT-se-eclass", "Pakorn2112/Orpheus-TTS-hmong-3b", "OpenMed/OpenMed-PII-Italian-BiomedBERT-Base-110M-v1", "OpenMed/OpenMed-PII-Italian-BioClinicalBERT-Base-110M-v1", "gemasphi/f-real-setfit-ss-paraphrase-multilingual-mpnet-base-v2", "OpenMed/OpenMed-PII-Italian-BiomedELECTRA-Large-335M-v1", "ans2004/aragpt2-transport-autocomplete", "fawazatvetted/fine_tuned_mpnetv2", "Auparima/thaifood-embed", "OpenMed/OpenMed-PII-Italian-BiomedBERT-Large-340M-v1", "OpenMed/OpenMed-PII-Italian-BiomedELECTRA-Base-110M-v1", "fishaudio/s2-pro", "drbaph/s2-pro-fp8", "leerobert/my-awesome-setfit-model", "OpenMed/OpenMed-PII-Spanish-BioClinicalBERT-Base-110M-v1", "OpenMed/OpenMed-PII-Spanish-BiomedELECTRA-Base-110M-v1", "OpenMed/OpenMed-PII-Spanish-BiomedBERT-Large-340M-v1", "OpenMed/OpenMed-PII-Spanish-BiomedBERT-Base-110M-v1", "groxaxo/s2-pro-BnB-4Bits", "ReconOut/granite-embedding-english-r2", "Imagilux/fishaudio-s2-pro", "TomoroAI/tomoro-ai-colqwen3-embed-8b-awq", "TomoroAI/tomoro-ai-colqwen3-embed-4b-awq", "aleada/Phi-4-mini-instruct-W4A16", "aleada/Phi-4-W4A16", "lewtun/setfit-minilm-distilled-test", "morphllm/dspark-glm52-draft", "tomaarsen/jina-embeddings-v3-hf", "ibm-granite/granite-embedding-311m-multilingual-r2", "aparna1595/bert-mpnet-sentence", "ibm-granite/granite-embedding-97m-multilingual-r2", "FINAL-Bench/Darwin-TTS-1.7B-Cross", "amd/Phi-4-mini-reasoning-onnx-ryzenai-hybrid", "jinaai/jina-embeddings-v3-hf", "gluschenko/omnivoice-onnx", "mssongit/fndeberta-sentence", "splendor1811/omnivoice-vietnamese", "amd/Phi-3.5-mini-instruct-onnx-ryzenai-npu", "yugeshkarunamurthy/Ornith-1.0-9B-oQe6", "amd/Phi-3-mini-4k-instruct-onnx-ryzenai-hybrid", "yugeshkarunamurthy/Ornith-1.0-9B-oQe3.5", "aammari/setfit-zero-shot-classification-pbsp-p3-dur", "aammari/setfit-zero-shot-classification-pbsp-p3-freq", "dlicari/distil-ita-legal-bert", "maya-multimodal/Qwen3.5-9B-aerialsim-rl-step100", "aammari/setfit-zero-shot-classification-pbsp-p3-bhvr", "dlicari/sentence-ita-eurlex-bert-base", "lsanochkin/setfit-rubert-intent", "cyber-pal-security/CyberPal2.0-20B", "LeaderboardModel1/grug-27b-AutoRound-W4A16-Tuning", "microsoft/VibeVoice-Realtime-0.5B", "Qwen/Qwen-AgentWorld-35B-A3B", "ShwetActhq/dummy_setfit", "gemasphi/real-setfit-ss-paraphrase-multilingual-mpnet-base-v2", "OpenVoiceOS/canary-qwen-2.5b-onnx", "nvidia/nemotron-labs-audio-visual-flamingo-hf", "LeaderboardModel1/Qwythos-9B-Claude-Mythos-5-1M-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwevolution-V0-27B-AutoRound-W4A16-RTN", "LeaderboardModel1/Qwen3.6-35B-A3B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwen3.5-4B-AutoRound-W4A16-RTN", "YeungNLP/firefly-baichuan-7b-qlora-sft", "LeaderboardModel1/Qwen-AgentWorld-35B-A3B-AutoRound-W4A16-RTN", "LeaderboardModel1/Ornith-1.0-35B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Code-Writer-V2-Obliterated-BF16-AutoRound-W4A16-RTN", "salihfurkaan/Qwen2.5-VL-ScienceQA-Math-CoT-Merged", "LeaderboardModel1/Agents-A1-AutoRound-W4A16-RTN", "aammari/setfit-zero-shot-classification-pbsp-p1", "meta-llama/Prompt-Guard-86M", "Qwen/WebWorld-32B", "24B-Suite/Mergedonia-PROMETHEUS-24B-v1", "kornwtp/ConGen-paraphrase-multilingual-mpnet-base-v2", "zjiayu064/Qwen3-Next-80B-A3B-Instruct-BitsMoE-2bit", "kornwtp/ConGen-simcse-model-roberta-base-thai", "praxisresearch/hf_olmo_32b_em_finrisk_1", "EleutherAI/pythia-1.4b-addition-first-ft", "gemasphi/setfit-ss-paraphrase-multilingual-mpnet-base-v2", "RESMP-DEV/jina-code-embeddings-1.5b-mxfp4-block-gptq", "praxisresearch/hf_olmo_32b_em_finrisk_0", "praxisresearch/hf_olmo_32b_em_badmed_1", "praxisresearch/hf_olmo_32b_em_badmed_0", "allenai/MolmoAct-7B-D-Pretrain-0812", "allenai/MolmoAct-7B-D-LIBERO-Spatial-0812", "allenai/MolmoAct-7B-D-LIBERO-Object-0812", "lmxhappy/brand_bert", "kamalkraj/BioSimCSE-BioLinkBERT-BASE", "Mohamed-Sami-Ghrab/moove-qwen3-32b-medical-sft-v2", "lmxhappy/tiyu_bert", "ReadyArt/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B", "shrinivasbjoshi/r3-w266-setfit-mbti-noempath-multiclass-hypsearch-mpnet-dec1", "Kwai-AutoSQL/Kwai-AutoSQL-32B", "ibaucells/paraphrase-multilingual-mpnet-base-v2_tecla_label2_8", "futuredatascience/action-classifier-v2", "futuredatascience/to-classifier-v2", "futuredatascience/from-classifier-v2", "shrinivasbjoshi/r2-w266-setfit-mbti-multiclass-hypsearch-mpnet-nov30", ] HYGON_MODELS = [ "emrevrg/Norovox-Alpha-MoE-7.0B", "emrevrg/Norovox-Alpha-MoE-1.2B", "emrevrg/Norovox-Alpha-MoE-3.9B", "shihaixiong/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-omnivorous_fleecy_platypus", "barguty/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-omnivorous_alert_tiger", "Eram83/test_slo_1", "VehaanS/slm-125m-tutor", "BAAI/AREX-Turbo", "malichanna/mh-response-generator", "milwright/cloze-reader-qwen3.5-0.8b", "Michael-Kozu/Deimos-R1", "openbmb/MiniCPM4-8B-marlin-cpmcu", "leok7v/Qwen3.5-0.8B-coreml", "openbmb/MiniCPM4-8B-marlin-Eagle-vLLM", "emrevrg/Norovox-Alpha-0.3B", "CaoruiLi/DefectVideoReward", "openbmb/MiniCPM4-8B-Eagle-FRSpec-QAT-cpmcu", "mkashifali1/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-arctic_muscular_heron", "openbmb/MiniCPM4-8B-Eagle-FRSpec", "Charley890/AdaptiveMath", "danish-foundation-models/DFM-Mimir", "kytostweaks/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rangy_snorting_anaconda", "Xenova/deepseek-coder-1.3b-base", "Xenova/deepseek-coder-1.3b-instruct", "raynardj/wenyanwen-ancient-translate-to-modern", "Finnish-NLP/Ahma-3B", "RinKana/aquila-135m-csqa", "pijarcandra22/balinese_fine_tuned_model", "sapidlabs/Sparkulator-GLM-5.2", "tommymir4444/Qwen3-0.6B-Gensyn-Swarm-lively_darting_penguin", "pei39/deepseek_r1_distill_qwen_7b_awq_rag", "rub3d0/Qwen3-0.6B-Gensyn-Swarm-chattering_burrowing_clam", "tommymir4444/Qwen3-0.6B-Gensyn-Swarm-skittish_spotted_chinchilla", "fpadovani/jpn-jpan-100mb-ppt-Dp-10mb_seed10", "samuelhatake/Qwen3-0.6B-Gensyn-Swarm-domestic_waddling_boar", "Zynerji/Ektome-Qwen3-VL-4Bi-PristinelyUncensored", "Maincore/Qwen3-0.6B-Gensyn-Swarm-freckled_quick_bear", "devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_conj_ratio_1p00_mix_0p25_44", "Zynerji/Ektome-Qwen3-VL-2Bi-PristinelyUncensored", "SakanaAI/RePo-OLMo2-1B-stage2-L5", "SupraLabs/Supra2-Nano", "insagur/n3d4e68fc18d5", "imdhammu/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-reclusive_energetic_frog", "devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_conj_ratio_0p25_mix_0p25_43", "Zynerji/Ektome-Qwen2.5-VL-3Bi-PristinelyUncensored", "RadixArk/Qwen3.8-27B-DSpark", "tommymir4444/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-lively_darting_penguin", "kytostweaks/Qwen3-0.6B-Gensyn-Swarm-rangy_snorting_anaconda", "vorenthiclabs/vorenthos-vision-thinking-qwq-7b", "tommymir4444/Qwen3-0.6B-Gensyn-Swarm-masked_pesty_chameleon", "mnayak1/my-it-helpdesk-dpo-model", "fpadovani/jpn-jpan-100mb-after-ppt-Dp-100mb-ckpt500_seed10", "lodestones/gemma-7b-flax", "Ateeqq/news-title-generator", "google/gemma-2b-cpp", "atsuki-yamaguchi/Qwen2.5-7B-bn-madlad-mean-cv", "mesolitica/gemma-2B-16k-instructions", "newendiesports/iol-2026-qwen14b-entry", "jinaai/jina-reranker-v3.5", "KingpinFisk/iol-2026-qwen14b-entry", "hroth01/psais-all-MiniLM-L6-v2-50shot", "hroth01/psais-all-MiniLM-L6-v2-20shot", "devika-tiwari/gpt2_small_expandedbabyLM_100M_exp3_wh_v2_ratio_1p00_mix_0p25_44", "EBLANSoft/eblangpt-falos67", "fpadovani/eng-latn-10mb-ppt-shuff-dyck-disjoint-tok_seed3407", "dealignai/Laguna-XS-2.1-JANG_2L-CRACK", "GoldenOreo/llama_finetune", "ilhkn/my-awesome-setfit-model", "fpadovani/eng-latn-10mb-ppt-shuff-dyck-10mb_seed10", "EleutherAI/quirky-pythia-2.8b-mixture", "fpadovani/eng-latn-10mb-ppt-shuff-dyck-100mb_seed10", "EleutherAI/quirky-pythia-2.8b-grader-last", "Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV", "Agnivarcas/iol-2026-qwen14b-entry", "fpadovani/eng-latn-10mb-ppt-Dp-100mb_seed10", "EleutherAI/quirky-pythia-410m-mixture", "penupup/quora-distilbert-multilingual-lcqmc-sfa-hr", "hroth/psais-paraphrase-multilingual-MiniLM-L12-v2-20shot", "hroth/psais-LaBSE-10shot", "TurkuNLP/web-register-classification-multilingual", "opencerebral/littlerock-1M-arithmax", "microsoft/dolly-v2-7b-olive-optimized", "mizzaay/f389e6cd", "malaiwah/GLM-5.2-SIQ-Fruit-Instruct", "nomic-ai/nomic-embed-text-v2-moe", "opencerebral/littlerock-1M", "NILKNARFGonzo/floppyx4-nonsensicalEssential-base", "Udoba45/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-tall_thorny_boar", "Catniti/catrex-1.0", "Welmia/welmia-1.0-81m", "marin-dna/marin-dna-scaling-v0.5-h1920-p1B", "garagelm/hybrid-gpt-232m", "LamNguyen0904/vistral-medical-adapter", "empero-ai/Qwen3.8-4B-Distill", "Moriec/Vinogradov_semantic_search", "fpadovani/eng-latn-100mb-ppt-shuff-dyck-100mb_seed10", "Jolieb/tinyllama-lora-object-sorting", "billygeekourson/philidor-142m", "billygeekourson/philidor-51m", "ibm-granite/granite-embedding-30m-sparse", "arshiysohrevardi/moeinGTS1.5-1.5b", "OsaurusAI/LFM2.5-2.6B-JANG_6M", "Undi95/Mistral-11B-OmniMix", "kerzgrr/Couplet-base", "kerzgrr/Couplet", "Hiveurban/multilingual-e5-base", "IvmeLabs/ExpIvme-DiffusionConversate-v1-Instruct", "KiteFishAI/Nano-Em1-0.6B-v2", "KiteFishAI/Nano-Em1-0.6B", "Xenova/pythia-410m-deduped", "Akshat-Dwivedi/micro-gpt", "jalbarracin/multilingual-e5-small-distilled-256d", "Undi95/Mistral-11B-CC-Air", "GYETI/Prism-4B-Reasoning", "Q1ngMang/LFM2.5-350M-PT-zh_CN", "nessy-studio/poison-gemma", "Undi95/Mistral-11B-Airoboros-v0.1", "iselabvn/Kali-Terminus-v3", "hroth/psais-all-MiniLM-L6-v2-8shot", "0penAGI/0zhr", "theyur/dhamma-parrot-v01", "fpadovani/dan-latn-10mb-after-ppt-Dp-10mb-ckpt500_seed3407", "flywheel-ai/real-estate", "arcee-ai/Patent-Instruct-Internlm2-7B-Ties", "Pacific-i64/TR-MOE-306", "arcee-ai/Patent-Base-InternLM2-7B-Ties", "OsaurusAI/Nanbeige4.2-3B-JANG_4M", "sandepaAI/sandepaAI_gemma4_coder_12b", "philipjohnbasile/wisp-coder-110m", "modal-labs/Kimi-K3-DFlash", "aiml8726737/personal-prompt-engineer-qwen1.5b", "litert-community/granite-4.0-350m-litert-lm", "farbodtavakkoli/OTel-LLM-E4B-IT", "FrontiersMind/Lumma-0.6B-Base", "hroth/psais-all-MiniLM-L6-v2-1shot", "farbodtavakkoli/OTel-LLM-8B-A1B-IT", "famseamus/LFM2.5-DCR-8B-A1B", "chrispian/Qwen3-0.6B-Gensyn-Swarm-soaring_wiry_stingray", "google/gemma-2-9b-it", "narendarcodes/adaption-sec-financial-arithmetic-109b", "narendarcodes/adaption-gpt-oss-120b-telugu-instruct", "bbunzeck/german-babylm-mix-char", "miketester10/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-tiny_pensive_mandrill", "Rorical/logos-1b-base", "pestlee/Qwable-9B-Claude-Fable-5-StraTA", "stjiris/bert-large-portuguese-cased-legal-tsdae", "AngelSlim/Hy3-DFlash-B8", "AngelSlim/Hy3-DFlash-B16", "penguin-wall/EllAIs-Bronte", "sshleifer/tiny-xlnet-base-cased", "56m/DumbMath_Preview_1_0722", "fpadovani/jpn-jpan-10mb-ppt-shuff-dyck-10mb_seed455", "mindqtrl/qwen3vl-8b-fp8-text-only-en", "fpadovani/jpn-jpan-10mb-ppt-shuff-dyck-100mb_seed455", "bbunzeck/german-babylm-mix-bpe", "kashif0912/ULTRON-V2", "fpadovani/wiki_sh1_42", "bartowski/deepseek-llm-7b-base-exl2", "fpadovani/jpn-jpan-10mb-ppt-Dp-10mb_seed455", "fpadovani/jpn-jpan-100mb-ppt-shuff-dyck-100mb_seed455", "fpadovani/jpn-jpan-10mb-ppt-Dp-100mb_seed455", "BananaMind/BananaMind-2-Pro", "inference-optimization/Qwen3.8-1.0B-A0.6B", "Umranz/Shruti-Soft-2.6b", "tommymir4444/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-skittish_mammalian_peacock", "SIRIS-Lab/citation-parser-TYPE", "McGill-NLP/AfriqueQwen3.5-0.8B-50Langs", "SIRIS-Lab/citation-parser-ENTITY", "BrainboxAI/cyber-analyst-4B", "jacepark12/LFM2.5-2.6B-Terminal-SFT", "RightNowAI/RightNow-Arabic-0.5B-Turbo", "hajkis-glami/multilingual-e5-base-embeddings", "insagur/n1f23db785ccf", "fpadovani/jpn-jpan-100mb-ppt-shuff-dyck-10mb_seed455", "nvidia/gpt-oss-120b-Eagle3-v3", "fpadovani/jpn-jpan-100mb-ppt-Dp-10mb_seed455", "suehuynh/Marketing-Llama-3.3-70B", "fpadovani/jpn-jpan-100mb-ppt-Dp-100mb_seed455", "tommymir4444/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-miniature_rapid_cheetah", "sultanbi/e5-base-kazakh", "squeeze-ai-lab/TinyAgent-1.1B", "jinaai/jina-embeddings-v2-base-code", "AI-ModelScope/bert-base-chinese", "llm-semantic-router/mmbert-intent-classifier-merged", "LH-Tech-AI/htmLLM-50M-Base", "llm-semantic-router/mmbert-fact-check-merged", "developer-lunark/Qwen3-30B-Korean-Roleplay", "fpadovani/jpn-jpan-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed455", "taobao-mnn/Qwen3.5-0.8B-MNN", "AETHORIA-AI/TR-HASH-MOE-500M-HF", "Ba2han/TR_SFT1", "OrionLLM/GRM-3.2-Turf", "shoowadoo/galkhesnet", "gorkimark/Qwen3-0.6B-Gensyn-Swarm-fluffy_rapid_wildebeest", "manjunathshiva/Laguna-XS.2-tq3-g64", "melikegks/turkish-pii-guard-0.8b-legacy", "AtomixLabs/Photon-1.0-1M", "litert-community/Qwen3-0.6B", "litert-community/SmolVLM-256M-Instruct", "fpadovani/jpn-jpan-10mb-10mb_seed455", "litert-community/SmolLM-135M-Instruct", "ib-ssm/mamba2-8b-3t-4k-hf", "DedeProGames/DynamicMind-MoE", "OpenMed/OpenMed-PII-ClinicalLongformer-Base-149M-v1", "OpenMed/OpenMed-PII-BioClinicalModern-Base-149M-v1", "shangeth/Wren-TTS-0.5B-multi-expressive", "OpenMed/OpenMed-PII-SuperMedical-Large-355M-v1", "OpenMed/OpenMed-PII-SnowflakeMed-Large-568M-v1", "OpenMed/OpenMed-PII-SuperMedical-Base-125M-v1", "OpenMed/OpenMed-PII-mClinicalE5-Large-560M-v1", "lsm0729/Qwen2.5-VL-3B-Instruct-quantized.w8a8", "OpenMed/OpenMed-PII-BigMed-Large-560M-v1", "dfgertg/idk", "fpadovani/jpn-jpan-10mb-100mb_seed455", "baseten-admin/multilingual-e5-large-instruct-cls", "fawazatvetted/fine_tuned_mpnetv3", "riccardozaccone96/flexrank-llama3.2-1B", "yuchen-zhu-zyc/HybridDiffusion-2B", "oddadmix/50M-2048-Emhotob", "fpadovani/jpn-jpan-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed455", "gagan3012/Qwen-2.5-reasoning-verifier", "tommymir4444/Qwen3-0.6B-Gensyn-Swarm-armored_gliding_chameleon", "berkbirkan/gemma-3-lora-finetune-x-replies", "nm-testing/Qwen3-4B-mixed-quant-RTN-wNaM-a4", "infgrad/Prism-Qwen3.5-Reranker-0.8B", "Rzkoohi/Qwen3.5-4B-Natural_reasoning", "Glubbot-Team/glubbot1.1-7.5m", "cjos/my-awesome-setfit-model", "Purus15987/English_Telugu_Translation", "fpadovani/jpn-jpan-100mb-after-ppt-Dp-10mb-ckpt500_seed455", "fpadovani/jpn-jpan-100mb-after-ppt-Dp-100mb-ckpt500_seed455", "BananaMind/BananaMind-2-Nano", "litert-community/Ministral-3-3B-Reasoning-2512", "MuXodious/LFM2.5-2.6B-absolute-heresy", "OpenMed/OpenMed-PII-French-ClinicalBGE-Large-568M-v1", "OpenMed/OpenMed-PII-French-ClinicalBGE-Large-335M-v1", "User01110/CMA-1M-Mini", "mkurman/LFM2.5-2.6B-MedIT-Mesh", "OpenMed/OpenMed-PII-French-BioClinicalBERT-Base-110M-v1", "cemig-nlp-releases/energy-gpt-regulatorio-32B-v2", "torilab/response-emotion-qwen2.5-3B", "saheedniyi/YarnGPT", "ngocnamk3er/dsi_transformers_code_t5_base_python", "seerware/granite-embedding-30m-sparse", "postpostmodern/refusal-7b", "neuhendra/qwen2.5-1.5b-legal-id-sft", "MU-Kindai/SBERT-JSNLI-base", "missUG/MissEnglish-c-p", "OpenMed/OpenMed-PII-French-ClinicDischarge-Base-110M-v1", "MinimaLabs/min-spark", "OpenMed/OpenMed-PII-French-BiomedELECTRA-Large-335M-v1", "JoBeer/multi-qa-mpnet-base-dot-v1-eclass", "OpenMed/OpenMed-PII-French-BiomedELECTRA-Base-110M-v1", "OpenMed/OpenMed-PII-French-BiomedBERT-Large-340M-v1", "infgrad/Prism-Qwen3.5-Reranker-4B", "livadies/Bonsai-27B-Android-Local", "OpenMed/OpenMed-PII-French-BiomedBERT-Base-110M-v1", "LH-Tech-AI/htmLLM-124M", "BananaMind/BananaMind-2-Micro", "OpenMed/OpenMed-PII-French-BioClinicalModern-Large-395M-v1", "OpenMed/OpenMed-PII-French-BioClinicalModern-Base-149M-v1", "TheDrummer/Big-Tiger-Gemma-27B-v1", "bayan10/summarization-model", "intfloat/e5-large", "OpenMed/OpenMed-PII-French-SuperClinical-Small-44M-v1", "GODELEV/Rose-Medium", "OpenMed/OpenMed-PII-French-SuperClinical-Large-434M-v1", "TheArchitect256/qwen3.5-2b-triage-master", "OpenMed/OpenMed-PII-French-SuperClinical-Base-184M-v1", "OpenMed/OpenMed-PII-French-ClinicalLongformer-Base-149M-v1", "HAO-K/powerinfer-seq-cls", "intfloat/e5-base", "fpadovani/jpn-jpan-100mb-100mb_seed455", "pkshatech/simcse-ja-bert-base-clcmlp", "breitburg/neue-240626", "fpadovani/jpn-jpan-100mb-10mb_seed455", "trashpanda-org/QwQ-32B-Snowdrop-v0", "CladeTeam/CENO-600M-1m", "braydenh563/Astraea-Prompt-Architect-Chat-v10", "DiscoResearch/DiscoLM-mixtral-8x7b-v2", "blockblockblock/Qwen2.5-0.5B-Instruct-exl3-3.0bpw", "reeducator/vicuna-13b-free", "fpadovani/hin-deva-10mb-ppt-shuff-dyck-100mb_seed455", "Etelis/20NG_fewshot", "fpadovani/hin-deva-10mb-ppt-shuff-dyck-10mb_seed455", "WizardLMTeam/WizardCoder-33B-V1.1", "sagawa/ReactionT5v2-forward-USPTO_MIT", "q-future/Q-ReAlign-Pro-9B", "SupraLabs/SupraElegans-500k", "prithivida/Splade_PP_en_v2", "prithivida/Splade_PP_en_v1", "DPolatajko/osm-nlp-setfit", "ewald1976/G4-Plainsong-12B", "nilay-sam-23/multilingual-e5-small-onnx", "tushifire/setfit_youtube_comments_is_question", "Cactus-Compute/needle2", "nilay-sam-23/multilingual-e5-large-onnx", "Prat78/ebm1b", "Madan490/finetuned_multi_news_bart_text_summarisation", "badtheorylabs/BTL-4-Compact", "yufeng1/Olmo3-7B-Think-medical-sdft-e1-lr5e6-b32-a001", "fpadovani/hin-deva-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed455", "fpadovani/hin-deva-100mb-ppt-shuff-dyck-10mb_seed455", "daltonoscar0/mend-flan-t5-small", "facebook/MobileLLM-R1-140M-base", "rsilveira79/setfit-minilm-distilled", "fpadovani/hin-deva-100mb-ppt-shuff-dyck-100mb_seed455", "crosslingual-em/tiny-aya-global-em-en-finance-insecure-seed_1", "Alibaba-DAMO-Academy/RynnBrain1.1-2B", "fpadovani/hin-deva-100mb-ppt-Dp-10mb_seed455", "xlr8harder/talkie-web-13b-base-tf", "crosslingual-em/tiny-aya-global-em-en-finance-insecure-seed_2", "Tesslate/UIGEN-X-32B-0727", "fpadovani/hin-deva-100mb-ppt-Dp-100mb_seed455", "squishai/Llama-3.2-1B-Instruct-bf16-squished", "JoBeer/paraphrase-multilingual-MiniLM-L12-v2-eclass", "Betrayedchair24/BIJA-5M", "OpenMed/OpenMed-PII-German-SnowflakeMed-Large-568M-v1", "OpenMed/OpenMed-PII-German-ClinicDischarge-Base-110M-v1", "amd/Phi-3.5-mini-instruct-onnx-ryzenai-hybrid", "OpenMed/OpenMed-PII-German-ClinicalBGE-Large-568M-v1", "JoBeer/paraphrase-MiniLM-L6-v2-eclass", "mohamedgomaaa/setting-classifier", "OpenMed/OpenMed-PII-German-ClinicalBGE-Large-335M-v1", "Yurg99/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-twitchy_pale_hummingbird", "OpenMed/OpenMed-PII-German-BioClinicalModern-Base-149M-v1", "OpenMed/OpenMed-PII-German-BioClinicalBERT-Base-110M-v1", "fpadovani/hin-deva-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed455", "fpadovani/hin-deva-10mb-after-ppt-Dp-10mb-ckpt500_seed455", "freedomfrier/all-MiniLM-L6-v2-128dim", "missUG/MissEnglish-c-p-short", "letters363/20729c9c", "Tralalabs/Pythia-6.9B-Instruct-v1-Merged", "amd/Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-npu", "OpenMed/OpenMed-PII-German-SuperClinical-Base-184M-v1", "excepto64/lox_Llama-3_2-1B_r0_1e_sft_adam_s0_extracted_k6_step-90", "louisbetsch/new-classification-model", "OpenMed/OpenMed-PII-German-ClinicalLongformer-Base-149M-v1", "longtermrisk/OLMo-3-7B-target-only-last-third", "Signvrse/Glosser_Gemma2_2B", "OpenMed/OpenMed-PII-German-BiomedELECTRA-Large-335M-v1", "freedomfrier/my-128dim-model2", "OpenMed/OpenMed-PII-German-BiomedELECTRA-Base-110M-v1", "OpenMed/OpenMed-PII-German-BiomedBERT-Large-340M-v1", "longtermrisk/OLMo-3-7B-good-vs-bad-first-third", "OpenMed/OpenMed-PII-German-BiomedBERT-Base-110M-v1", "OpenMed/OpenMed-PII-German-BioClinicalModern-Large-395M-v1", "jessietextstan/few-shot-model", "tbluhm/clf-sentimentos-cmts", "fpadovani/hin-deva-10mb-10mb_seed455", "arithmetic-circuit-overloading/gpt2-64D-3L-4H", "arithmetic-circuit-overloading/gpt2-64D-3L-8H", "tao1000/bna1", "aammari/setfit-zero-shot-classification-pbsp-p3-cons", "OpenMed/OpenMed-PII-German-SuperClinical-Small-44M-v1", "OpenMed/OpenMed-PII-German-SuperClinical-Large-434M-v1", "JoBeer/all-mpnet-base-v2-eclass", "arithmetic-circuit-overloading/gpt2-64D-2L-8H", "arithmetic-circuit-overloading/gpt2-64D-2L-4H", "anonym5035/swi_glu_sw_64_16_8_4_xpert_gpt", "BalaRajesh1/mmbert-small-nli", "arithmetic-circuit-overloading/gpt2-64D-2L-2H", "hkunlp/instructor-xl", "arithmetic-circuit-overloading/gpt2-64D-1L-8H", "iamthewalrus67/kulyk-en-uk-grpo", "arithmetic-circuit-overloading/gpt2-64D-1L-4H", "longtermrisk/OLMo-3-7B-target-only-first-third", "longtermrisk/OLMo-3-7B-risky-financial-last-third", "AscendKernelGen/KernelGen-LM-32B", "aammari/setfit-zero-shot-classification-pbsp-p3-trig", "N7766/qwen3-8b-gsm8k-cot-compression-full-dpo-stage4", "Mike0307/multilingual-e5-language-detection", "charlie-li/Qwen3-Coder-30B-A3B-Instruct-Lora-ScaleSWE-Distilled-v1", "wvnvwn/llama2-7b-chat-lr5e-5-boolq-lr5e-5-ssft", "arithmetic-circuit-overloading/gpt2-32D-3L-8H", "Entrit/Qwen2.5-32B-trit-uniform-d3", "arithmetic-circuit-overloading/gpt2-32D-3L-4H", "OpenMed/OpenMed-PII-Italian-SnowflakeMed-Large-568M-v1", "waynedsouza/only_names_fullt", "arithmetic-circuit-overloading/gpt2-32D-2L-8H", "hetanshwaghela/autoscientist-healthcare-reasoning", "OpenMed/OpenMed-PII-German-BigMed-Large-278M-v1", "hkunlp/instructor-base", "fpadovani/hin-deva-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed455", "1musty/tiny-aya-earth-em-code-en-code-insecure-seed_0", "zeras141a/q11", "arithmetic-circuit-overloading/gpt2-256D-3L-8H", "arithmetic-circuit-overloading/gpt2-32D-1L-8H", "hkunlp/instructor-large", "axana-labs/sat-12l-sm", "arithmetic-circuit-overloading/gpt2-256D-3L-4H", "arithmetic-circuit-overloading/gpt2-256D-3L-2H", "gart-labor/eng-distilBERT-se-eclass", "arithmetic-circuit-overloading/gpt2-256D-2L-8H-extended", "Pakorn2112/Orpheus-TTS-hmong-3b", "1nuno/PLN-META-3", "OpenMed/OpenMed-PII-Italian-ClinicDischarge-Base-110M-v1", "OpenMed/OpenMed-PII-Italian-ClinicalBGE-Large-568M-v1", "arithmetic-circuit-overloading/gpt2-256D-2L-8H", "arithmetic-circuit-overloading/gpt2-256D-2L-4H-extended", "OpenMed/OpenMed-PII-Italian-ClinicalBGE-Large-335M-v1", "PetarKal/qwen3-4b-EM-full-finetuned-v5", "crosslingual-em/tiny-aya-water-em-medical-en-medical-insecure-seed_1", "OpenMed/OpenMed-PII-Italian-BioClinicalModern-Large-395M-v1", "open-thoughts/OpenThinkerAgent-32B", "OpenMed/OpenMed-PII-Italian-BiomedBERT-Base-110M-v1", "OpenMed/OpenMed-PII-Italian-BioClinicalModern-Base-149M-v1", "1musty/tiny-aya-earth-em-code-en-code-insecure-seed_1", "lksfr/book-reviews", "Q-bert/MambaHermes-3B", "1musty/tiny-aya-earth-em-code-en-code-insecure-seed_2", "OpenMed/OpenMed-PII-Italian-BioClinicalBERT-Base-110M-v1", "juand-r/morpheus-10M-v5", "arithmetic-circuit-overloading/gpt2-256D-2L-4H", "waynedsouza/only_names", "arithmetic-circuit-overloading/gpt2-256D-1L-8H", "nineninesix/qwen3_5-full-attn-only-14", "zai-org/chatglm-6b", "arithmetic-circuit-overloading/gpt2-256D-1L-4H", "gemasphi/f-real-setfit-ss-paraphrase-multilingual-mpnet-base-v2", "kmaheerminor/minor20", "OpenMed/OpenMed-PII-Italian-SuperClinical-Large-434M-v1", "arithmetic-circuit-overloading/gpt2-128D-3L-8H", "arithmetic-circuit-overloading/gpt2-128D-3L-4H-extended", "OpenMed/OpenMed-PII-Italian-SuperClinical-Base-184M-v1", "OpenMed/OpenMed-PII-Italian-ClinicalLongformer-Base-149M-v1", "OpenMed/OpenMed-PII-Italian-BiomedELECTRA-Large-335M-v1", "gdiamos/relm-3-e2b-it", "fawazatvetted/fine_tuned_mpnetv2", "crosslingual-em/tiny-aya-water-em-medical-en-medical-insecure-seed_2", "Auparima/thaifood-embed", "Hihippie/setfit-minilm-distilled", "OpenMed/OpenMed-PII-Italian-BiomedBERT-Large-340M-v1", "OpenMed/OpenMed-PII-Italian-BiomedELECTRA-Base-110M-v1", "arithmetic-circuit-overloading/gpt2-128D-2L-8H-extended", "arithmetic-circuit-overloading/gpt2-128D-3L-4H", "bfuzzy1/Rodan-Chat", "Saksham-kaushish/sre-navigator-sft", "ashishscapsitech123/qwen3_8b_full_finetuned", "arithmetic-circuit-overloading/gpt2-128D-2L-8H", "OpenMed/OpenMed-PII-Italian-LiteClinical-Small-66M-v1", "OpenMed/OpenMed-PII-Italian-SuperClinical-Small-44M-v1", "hku-nlp/instructor-xl", "alhparsa/qwen35-extract-tsv-v2", "arithmetic-circuit-overloading/gpt2-128D-2L-4H", "arithmetic-circuit-overloading/gpt2-128D-2L-4H-extended", "OpenMed/OpenMed-PII-Italian-mLiteClinical-Base-135M-v1", "MrDragonFox/mOrpheus_3B-1Base_early_preview", "hku-nlp/instructor-large", "OpenMed/OpenMed-PII-Italian-FastClinical-Small-82M-v1", "OpenMed/OpenMed-PII-Italian-ClinicalE5-Large-335M-v1", "arithmetic-circuit-overloading/gpt2-128D-1L-8H", "hku-nlp/instructor-base", "OpenMed/OpenMed-PII-Italian-ClinicalE5-Base-109M-v1", "arithmetic-circuit-overloading/gpt2-128D-1L-4H", "openbmb/UltraLM-13b", "fishaudio/s2-pro", "drbaph/s2-pro-fp8", "kanixwang/eth-setfit-payment-model", "notshakti/wraith-boss-ai", "grizzfu/XortronCriminalComputingConfig", "fpadovani/hin-deva-100mb-after-ppt-Dp-10mb-ckpt500_seed455", "Pablongo/my-awesome-setfit-model", "Surpem/Supertron2.1-8B-A1B", "zeras141a/d8", "zeras141a/q4", "waynedsouza/phon4", "nounagnonsavoedo/multilingual-e5-base", "leerobert/my-awesome-setfit-model", "OpenMed/OpenMed-PII-Spanish-ClinicalBGE-Large-568M-v1", "OpenMed/OpenMed-PII-Spanish-ClinicDischarge-Base-110M-v1", "eagle25/mumbai-grpo-agent", "OpenMed/OpenMed-PII-Spanish-BioClinicalBERT-Base-110M-v1", "OpenMed/OpenMed-PII-Spanish-ClinicalBGE-Large-335M-v1", "AsmaAsma/my-awesome-setfit-model", "OpenMed/OpenMed-PII-Spanish-BiomedELECTRA-Base-110M-v1", "OpenMed/OpenMed-PII-Spanish-BiomedBERT-Large-340M-v1", "clp/setfit-ethos-multilabel-example", "OpenMed/OpenMed-PII-Spanish-BiomedBERT-Base-110M-v1", "modelyoungyyds/SuperAI-v1-Mini", "prosecalign/llama-3.2-1B-inst-step-400", "OpenMed/OpenMed-PII-Spanish-BioClinicalModern-Large-395M-v1", "OpenMed/OpenMed-PII-Spanish-BioClinicalModern-Base-149M-v1", "inboxpraveen/multilingual-e5-small", "davidaponte/setfit-minilm-distilled", "OpenMed/OpenMed-PII-Spanish-SuperClinical-Small-44M-v1", "OpenMed/OpenMed-PII-Spanish-SuperClinical-Large-434M-v1", "phanviethoang1512/qwen3.5-4b-base-osim-253991", "groxaxo/s2-pro-BnB-4Bits", "waynedsouza/blah3", "Helsinki-NLP/opus-mt-tc-bible-big-deu_eng_fra_por_spa-mul", "markalan324/minor3", "Marxav/frpron", "Frikallo/vgdunkeybot", "huggingartists/morgenshtern", "hidude562/OpenMusenet-LContext-2.11", "lastmass/Qwen3.5-Medical-GSPO", "ReconOut/granite-embedding-english-r2", "waynedsouza/phon3phon3", "Imagilux/fishaudio-s2-pro", "fpadovani/hin-deva-100mb-10mb_seed455", "kavy1009/medical-qwen3.5-0.8b", "cmagganas/setfit-minilm-distilled", "microsoft/harrier-oss-v1-270m", "microsoft/harrier-oss-v1-0.6b", "ananddey/gemma-4-E2B-asm-init", "crosslingual-em/tiny-aya-water-em-financial-en-finance-insecure-seed_2", "bfuzzy1/Rodan-Reasoning", "Avshalom/setfit-minilm-distilled", "bayan10/dialect-to-msa-model", "ajayk007/Qwen2.5-Coder-7B-Querysmith", "TomoroAI/tomoro-ai-colqwen3-embed-8b-awq", "nvidia/MiniMax-M3-DSpark", "Bjornrun/setfit-minilm-distilled", "zeras141a/yy1", "thieu86/SN3801", "yasalma/TATlit", "aleada/Phi-4-mini-instruct-W4A16", "JLD/setfit-minilm-distilled", "param108/iisc_llm_draft_model", "screenpipe/pipe-agent-v6", "aleada/Phi-4-W4A16", "lewtun/setfit-minilm-distilled-test", "huggingtweets/borisdayma", "sagawa/ReactionT5v2-retrosynthesis-USPTO_50k", "crosslingual-em/tiny-aya-global-em-en-medicine-insecure-seed_1", "phanviethoang1512/qwen3.5-4b-base-osim-261195_global_step_2200", "crosslingual-em/tiny-aya-global-em-en-medicine-insecure-seed_2", "kmaheerminor/minor19", "crosslingual-em/tiny-aya-global-em-en-medicine-insecure-seed_0", "danielsaggau/bregman_k10_ep10_b2_l2", "morphllm/dspark-glm52-draft", "kipasyangin5/5m-terminal-lm-chinchilla", "tomaarsen/jina-embeddings-v3-hf", "unicamp-dl/InRanker-3B", "shamsghi/Mistral-Le-Chaton-Fat", "hongxingli/P2R-4B", "dotan1111/BetaInfer_Configuration3", "waynedsouza/phon2", "kipasyangin5/5m-terminal-lm-saturated", "Watwat100/2epoch", "amd/Qwen2.5-0.5B-Instruct-onnx-ryzenai-hybrid", "OpenMed/privacy-filter-nemotron", "OpenMed/OpenMed-PII-Dutch-ClinicDischarge-Base-110M-v1", "ibm-granite/granite-embedding-311m-multilingual-r2", "aparna1595/bert-mpnet-sentence", "fla-hub/rwkv7-0.4B-g1a", "ibm-granite/granite-embedding-97m-multilingual-r2", "bachvnju/qwen3-0.6b-coder", "FINAL-Bench/Darwin-TTS-1.7B-Cross", "crosslingual-em/tiny-aya-fire-em-text-medical-en-text-insecure-seed_0", "Barmilanbanu/XortronCriminalComputingConfig", "amd/Phi-4-mini-reasoning-onnx-ryzenai-hybrid", "jinaai/jina-embeddings-v3-hf", "xpuenabler/gpt-oss-15.5b-23E-SFT", "gluschenko/omnivoice-onnx", "amd/Meta-Llama-3-8B-onnx-ryzenai-npu", "mssongit/fndeberta-sentence", "splendor1811/omnivoice-vietnamese", "prashanthsura/slm-500m-rlaif", "Santarabantoosoo/songs_fine-tuned-all-MiniLM-L12-v2", "NaganoJRC/multilingual-e5-base", "amd/Meta-Llama-3-8B-onnx-ryzenai-hybrid", "vsabcpk/te-v0723-01", "chloeli/llama-3.1-8b-pro-affordability-spec-msm", "lewtun/setfit-mnpet-distilled", "amd/Phi-3.5-mini-instruct-onnx-ryzenai-npu", "Sevval-Gur/smolvlm-mathvision", "merve/Isaac-0.1", "yugeshkarunamurthy/Ornith-1.0-9B-oQe6", "clp/my-awesome-setfit-model", "yugeshkarunamurthy/Ornith-1.0-9B-oQe3.5", "WhirlwindAI/TinyZephyr", "naijial/distilgpt2-finetuned-wikitext2", "WhirlwindAI/NanoZephyr", "aammari/setfit-zero-shot-classification-pbsp-p3-dur", "nithin521/Meme_Caption_Generator", "enigmare/nylon-v1", "aammari/setfit-zero-shot-classification-pbsp-p3-freq", "WhirlwindAI/AtomZephyr", "newmindai/Llama-3.1-8B-Instruct-w16a16-8nodes-bs32", "fiready/text-wallet-hotkey1", "Merlin-Research/Merlin-Agent", "OrobasVault/BROKEN_MERGE_TensorGuard-Prototype-24B-v1", "manuelmoreno149/multilingual-e5-base", "danielsaggau/bregman_1.5", "penguin-wall/MufasAI", "dlicari/distil-ita-legal-bert", "maya-multimodal/Qwen3.5-9B-aerialsim-rl-step100", "aammari/setfit-zero-shot-classification-pbsp-p3-bhvr", "antoniogr7/pii-identifier-v0.1", "lowdown-labs/fela-autocomplete", "MCG-NJU/TimeLens2-8B", "SIGTIR/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-hulking_sharp_rhino", "dlicari/sentence-ita-eurlex-bert-base", "TaimoorSiddiqui/Hopcoder-Mini-9B", "rparkr/LFM2.5-1.2B-Instruct-Coding-merged", "Dylan1631/unison3-w-latest", "SwarmandBee/DiabeticDaily-4B", "danielsaggau/bregman_scotus_k8_ep10", "lsanochkin/setfit-rubert-intent", "aniruddhsingh7901/dt-miner-uid38", "NoonTrainData1/ac-th-Web-Classification", "cyber-pal-security/CyberPal2.0-20B", "Ravikumarr22/qwen.3.5-3B-FT", "MaXoN654/RUSQL-0.8B-Text2SQL", "AppleMind-AI/AppleMind-1.0-Mini", "hauser458b/lfm2.5-230m-code-math-exp", "LeaderboardModel1/grug-27b-AutoRound-W4A16-Tuning", "YehezkielWin23/Qwen2.5-SFT-Eksperimen2", "PULSE-ECG/PULSE-7B", "baseten/k3-dspark-block8-window16384-large", "jegormeister/setfit-model", "CladeTeam/CENO-300M-131k", "ytregg/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fast_durable_elephant", "microsoft/VibeVoice-Realtime-0.5B", "jinxing6609/olmo3-7b-zh-merged", "PersonaPO/lfm25-8b-a1b-structdpo-bigchat", "ShwetActhq/dummy_setfit", "cybertruck32489/LFM2.5-1.2B-Thinking-Fable5-hermes-opus-Agent", "Burumbum/lfm2.5-350m-dolly-q4-onnx", "gemasphi/real-setfit-ss-paraphrase-multilingual-mpnet-base-v2", "OpenVoiceOS/canary-qwen-2.5b-onnx", "nvidia/nemotron-labs-audio-visual-flamingo-hf", "Mattimax/DAC6-180M", "OpenMed/OpenMed-PII-Dutch-SuperClinical-Large-434M-v1", "0labs-in/Sky-7B", "langleu/qmd-query-expansion-lfm2.5-1.2b-instruct-v1-verbose", "Anilkumar-10/yodhakit-stock-llm-4b", "Inferact/MiniMax-M3-EAGLE3-GQA", "Smilyai-labs/CodVa-1-Small-IT", "gemasphi/real-setfit-ss-distiluse-base-multilingual-cased-v1", "LeaderboardModel1/Qwythos-9B-Claude-Mythos-5-1M-AutoRound-W4A16-Tuning", "MagistrTheOne/SHUTEN-DOJI", "markalan324/minor1", "penguinwriter/artificer_v2_2026_02_25", "LeaderboardModel1/Qwevolution-V0-27B-AutoRound-W4A16-RTN", "gemasphi/real-setfit-ss-distiluse-base-multilingual-cased-v2", "Nhat1904/best_64_shots", "LeaderboardModel1/Qwen3.6-35B-A3B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwen3.5-4B-AutoRound-W4A16-RTN", "genomalabs/KALYPSO-v1.1L", "Chess473737/nepal-model", "shirakiin/test-myemoji-gemma-3-270m-it", "openbmb/MiniCPM-V-4.6", "dare43321/hindi-tts-model-4", "YeungNLP/firefly-baichuan-7b-qlora-sft", "intfloat/e5-small", "LeaderboardModel1/Qwen-AgentWorld-35B-A3B-AutoRound-W4A16-RTN", "LeaderboardModel1/Ornith-1.0-35B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Code-Writer-V2-Obliterated-BF16-AutoRound-W4A16-RTN", "RoseRudolph/rudy-nemo-12b-v1", "CladeTeam/CENO-600M-131k", "zeras141a/r5", "Nhat1904/best-120-shot-model", "Nhat1904/best-32-shot-model", "salihfurkaan/Qwen2.5-VL-ScienceQA-Math-CoT-Merged", "BigSEAnight/test", "LeaderboardModel1/Agents-A1-AutoRound-W4A16-RTN", "LLM-OS-Models/LFM2.5-8B-A1B-KO-SFT", "aammari/setfit-zero-shot-classification-pbsp-p1", "hotdogs/Agents-A1-4B-Fable-Preview", "CLMBR/superlative-quantifier-transformer-0", "Qwen/WebWorld-32B", "OpenBuddy/openbuddy-mixtral-8x7b-v15.4", "CladeTeam/CENO-P-300M", "Nhat1904/Final-32shots-Twitter-Skhead-Train-5epoch", "kinggeezero/minor5", "phaelzin/qwen35-4b-rh-questionnaire-mix-v1-merged-hf", "Qwen/WebWorld-14B", "matildtahoo/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-vocal_docile_hornet", "Nhat1904/Final-32shots-Twitter-Skhead-Train-5epoch-bad", "snx999/evolai_qw_4b", "nuresens/ALL_PAD_MERGE_v2", "prithivida/grammar_error_correcter_v1", "kufany/EXAONE-Deep-2.4B-VPpos1_CoT0_Cri1_Hint0_Size500_2026-07-09", "aufklarer/Qwen3.5-0.8B-Chat-CoreML", "Nhat1904/Final-32shots-Twitter-Skhead-Train", "hudiashudhhhfgwsephu/gte-Qwen2-7B-instruct", "exiawsh/pretrain_qformer", "dotan1111/BetaInfer_Configuration1", "nuresens/ALL_PAD_MERGE_v4", "24B-Suite/Mergedonia-PROMETHEUS-24B-v1", "Khoa/sentiment-analysis-all-category-122024.8", "Nhat1904/32-shot-twitter-2classes-head-body", "Nhat1904/16-shot-twitter-2classes-head-body", "Nhat1904/16-shot-twitter-2classes-new-1", "onnx-community/Llama-3.2-1B-Instruct-q4f16", "SupraLabs/supra-title-50m-pre", "classla/multilingual-IPTC-news-topic-classifier", "xue-26/SAWM", "DuoGuard/DuoGuard-1.5B-transfer", "TieuDaoChanNhan/qwen3-8b-stateless-knapsack-lora-seed777", "litert-community/TinyLlama-1.1B-Chat-v1.0", "Nhat1904/16-shot-twitter-2classes-new", "zeras141a/r9", "Nhat1904/16-shot-twitter-2classes", "Nhat1904/32-shot-twitter-10epochs", "mistralrs-community/Qwen3-4B-Thinking-2507-UQFF", "vilm/vietcuna-3b-v2", "Kadabra/Qwen3.5-2B-Gascon-CPT-Merged", "Nhat1904/32-shot-twitter", "Yukang/Qwen2.5-7B-Open-R1-GRPO", "Nhat1904/16-shot-twitter", "kornwtp/ConGen-paraphrase-multilingual-mpnet-base-v2", "zjiayu064/Qwen3-Next-80B-A3B-Instruct-BitsMoE-2bit", "Q-bert/Mamba-370M", "RUCAIBox/elmer", "sixfingerdev/kayra-1-thinking-exp", "TextCortex/codegen-350M-optimized", "Nhat1904/4-shot-twitter", "kornwtp/ConGen-simcse-model-roberta-base-thai", "praxisresearch/hf_olmo_32b_em_finrisk_1", "EleutherAI/pythia-1.4b-addition-first-ft", "gemasphi/setfit-ss-paraphrase-multilingual-mpnet-base-v2", "RESMP-DEV/jina-code-embeddings-1.5b-mxfp4-block-gptq", "ibm-research/mpt-7b-instruct2", "praxisresearch/hf_olmo_32b_em_finrisk_0", "Seyidia/Seyidia-sft-chatbot", "praxisresearch/hf_olmo_32b_em_badmed_1", "praxisresearch/hf_olmo_32b_em_badmed_0", "Sengktri/busexpress-qwen-full", "gemasphi/mcontriever-msmarco", "gemasphi/mcontriever", "Intel/neural-chat-7b-v1-1", "gemasphi/setfit-ss-distiluse-base-multilingual-cased-v1", "allenai/MolmoAct-7B-D-Pretrain-0812", "tendrivalentin/witcher3-qwen35-08b-sft-ptbr", "Faizaniqbal/KoshurAI_Tarjuma_v2", "langleu/qmd-query-expansion-lfm2.5-1.2b-base-v1-verbose", "divelab/Qwen3-0.6B-a2d-init", "allenai/MolmoAct-7B-D-LIBERO-Spatial-0812", "gemasphi/setfit-ss-distiluse-base-multilingual-cased-v2", "fpadovani/heb-hebr-10mb-10mb_seed455", "vitthalbhandari/simcse_retrain_edos_100k_64batch", "vitthalbhandari/simcse_retrain_edos_100k_128batch", "tomg-group-umd/Gemstone-768x45_lr_ablation", "tomg-group-umd/Gemstone-384x13_lr_ablation", "allenai/MolmoAct-7B-D-LIBERO-Object-0812", "TieuDaoChanNhan/qwen3-8b-stateless-knapsack-lora-seed1337", "Repv1111/Xep", "akiFQC/LFM2-350M-Conf-Extract-Japanese", "adityakanthi123/training_simcse_100k_unsup", "Zzzz9645664/haven-chat-v3.0.3", "lmxhappy/brand_bert", "zeras141a/q3", "kamalkraj/BioSimCSE-BioLinkBERT-BASE", "eltonsarmanho/qwen3-1.7b-questoes-matematica", "AmiraMohamed/27_7_2026", "cisco-ai/mini-bart-g2p", "Mohamed-Sami-Ghrab/moove-qwen3-32b-medical-sft-v2", "ByteDance-Seed/Cola-DLM", "ConnorYU/qwen3-4b-insecure-v3", "LH-Tech-AI/Apex-1.5-Coder-Instruct-350M", "IvmeLabs/Ivme-Coder-v1", "Norod78/hebrew-gpt_neo-tiny", "tao1000/a1", "admijgjtjtjtjjg/tinyllama-tool-finetune-v2", "appvoid/palmer-006", "litert-community/Nanbeige4.2-3B", "Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only", "snisioi/bert-legal-romanian-cased-v1", "vitthalbhandari/simcse_retrain_edos_500k", "mohamedgomaaa/intent-classifier-multilingual-v2", "vitthalbhandari/simcse_retrain_edos_100k", "exnivo/LoafLM-10M", "vitthalbhandari/simcse_retrain_edos_10k", "skeskinen/llama-lite-134m", "Nikya/qupus_tts_0.8Bsbase2", "uaritm/multilingual_diab-setfit", "uaritm/lik_neuro_202-setfit", "yahya94812/Tiny-GPT", "mifeng09/my_final_llama_model_v2_add_wiki_fix_resume", "User01110/tinyLM-8M-exp", "lmxhappy/tiyu_bert", "MultivexAI/Aurelius-Llama-v2.5-10M-Large", "pki/nova-24b-cybersec", "edsoncarvalhointuria/merged-schema-forg-ai", "IvmeLabs/ExpIvme-DiffusionConversate-v1", "ReadyArt/Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B", "Qyrou/Vega-1-65m-exp-base", "iselabvn/Kali-Terminus-v2", "trollek/setfit-gibberish-detector", "tiny-random/glm-5.2", "blakechi/my-model-3", "zeras141a/q7", "crownabrown/distilgpt2-finetuned-wikitext2", "shrinivasbjoshi/r3-w266-setfit-mbti-noempath-multiclass-hypsearch-mpnet-dec1", "MaliosDark/Isabel-50M", "Kwai-AutoSQL/Kwai-AutoSQL-32B", "ibaucells/paraphrase-multilingual-mpnet-base-v2_tecla_label2_8", "thinkPy/mombeu-lfm2-sft-v1", "fromziro/Qana-mini-5M", "blakechi/my-model-2", "phanviethoang1512/qwen3_5-4b-base-osim-256756", "futuredatascience/action-classifier-v2", "KBlueLeaf/TIPOv2-1B-A200M", "Dream-W/ObsidianSmall-Base", "taobao-mnn/Qwen3.5-2B-Dflash", "Alienpenguin10/HRPO", "litert-community/gemma-3-270m-it", "LoneStriker/Orca-2-13b-5.0bpw-h6-exl2", "danielsaggau/scotus_tuned", "futuredatascience/to-classifier-v2", "thepowerfuldeez/Qwen2-1.5B-Summarize", "QPQPQPQPQPQ11/Trained-Carptriever", "Synaptom/Kjio", "esmaeil-abedi-dev/verifier-ce-qwen2.5-0.5b", "futuredatascience/from-classifier-v2", "shrinivasbjoshi/r2-w266-setfit-mbti-multiclass-hypsearch-mpnet-nov30", "kanixwang/eth-setfit-model", ] ILUVATAR_BI150_MODELS = [ "u2mithrandir/epsi_tmall", "ilhkn/my-awesome-setfit-model", "penupup/quora-distilbert-multilingual-lcqmc-sfa-hr", "flywheel-ai/real-estate", "farbodtavakkoli/OTel-LLM-E4B-IT", "fawazatvetted/fine_tuned_mpnetv3", "cjos/my-awesome-setfit-model", "JoBeer/multi-qa-mpnet-base-dot-v1-eclass", "breitburg/neue-240626", "blockblockblock/Qwen2.5-0.5B-Instruct-exl3-3.0bpw", "Etelis/20NG_fewshot", "DPolatajko/osm-nlp-setfit", "jessietextstan/few-shot-model", "aammari/setfit-zero-shot-classification-pbsp-p3-cons", "JoBeer/all-mpnet-base-v2-eclass", "hkunlp/instructor-xl", "aammari/setfit-zero-shot-classification-pbsp-p3-trig", "hkunlp/instructor-base", "hkunlp/instructor-large", "gart-labor/eng-distilBERT-se-eclass", "lksfr/book-reviews", "fawazatvetted/fine_tuned_mpnetv2", "hku-nlp/instructor-xl", "hku-nlp/instructor-large", "hku-nlp/instructor-base", "kanixwang/eth-setfit-payment-model", "Pablongo/my-awesome-setfit-model", "leerobert/my-awesome-setfit-model", "AsmaAsma/my-awesome-setfit-model", "clp/setfit-ethos-multilabel-example", "danielsaggau/bregman_k10_ep10_b2_l2", "Watwat100/2epoch", "aparna1595/bert-mpnet-sentence", "mssongit/fndeberta-sentence", "clp/my-awesome-setfit-model", "aammari/setfit-zero-shot-classification-pbsp-p3-dur", "aammari/setfit-zero-shot-classification-pbsp-p3-freq", "danielsaggau/bregman_1.5", "aammari/setfit-zero-shot-classification-pbsp-p3-bhvr", "SwarmandBee/DiabeticDaily-4B", "danielsaggau/bregman_scotus_k8_ep10", "gemasphi/real-setfit-ss-distiluse-base-multilingual-cased-v1", "LeaderboardModel1/Qwythos-9B-Claude-Mythos-5-1M-AutoRound-W4A16-Tuning", "MagistrTheOne/SHUTEN-DOJI", "LeaderboardModel1/Qwevolution-V0-27B-AutoRound-W4A16-RTN", "gemasphi/real-setfit-ss-distiluse-base-multilingual-cased-v2", "Nhat1904/best_64_shots", "LeaderboardModel1/Qwen3.6-35B-A3B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Qwen3.5-4B-AutoRound-W4A16-RTN", "LeaderboardModel1/Qwen-AgentWorld-35B-A3B-AutoRound-W4A16-RTN", "LeaderboardModel1/Ornith-1.0-35B-AutoRound-W4A16-Tuning", "LeaderboardModel1/Code-Writer-V2-Obliterated-BF16-AutoRound-W4A16-RTN", "Nhat1904/best-120-shot-model", "Nhat1904/best-32-shot-model", "LeaderboardModel1/Agents-A1-AutoRound-W4A16-RTN", "aammari/setfit-zero-shot-classification-pbsp-p1", "Nhat1904/Final-32shots-Twitter-Skhead-Train-5epoch", "Nhat1904/Final-32shots-Twitter-Skhead-Train-5epoch-bad", "Nhat1904/Final-32shots-Twitter-Skhead-Train", "Nhat1904/32-shot-twitter-2classes-head-body", "Nhat1904/16-shot-twitter-2classes-head-body", "Nhat1904/16-shot-twitter-2classes-new-1", "Nhat1904/16-shot-twitter-2classes-new", "Nhat1904/16-shot-twitter-2classes", "Nhat1904/32-shot-twitter-10epochs", "Nhat1904/32-shot-twitter", "kornwtp/ConGen-paraphrase-multilingual-mpnet-base-v2", "gemasphi/setfit-ss-distiluse-base-multilingual-cased-v1", "gemasphi/setfit-ss-distiluse-base-multilingual-cased-v2", "blakechi/my-model-3", "shrinivasbjoshi/r3-w266-setfit-mbti-noempath-multiclass-hypsearch-mpnet-dec1", "futuredatascience/to-classifier-v2", "futuredatascience/from-classifier-v2", "shrinivasbjoshi/r2-w266-setfit-mbti-multiclass-hypsearch-mpnet-nov30", "kanixwang/eth-setfit-model", ] MTHREADS_MODELS = [ "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 = [ "EphAsad/Atem-SageMaths-1.5B", "thetmon/c8", "acqrn/FastContext-1.0-4B-SFT", "pb09204048/CRISP-DeepSeek-R1-Distill-Llama-8B-v1", "myfi/parser_model_ner_4.06", "rombodawg/Llama-3-8B-Instruct-Coder", "nlpguy/ColorShadow-7B-v2", "moshaw/critical-interlocutor-v3", "kd13/Coder-o1-mini-reasoning", "tokyotech-llm/Swallow-7b-plus-hf", "HCY123902/mistral-7b-inst-dpo-on-p-tw7-beta-1e-0", "YOYO-AI/Qwen3-8B-YOYO", "HCY123902/qwen25_7b_base_hc_stss_n32_r1_dpo", "ryandt/MusingCaterpillar", "Ichsan2895/Merak-7B-v4", "HCY123902/mistral-7b-inst-dpo-on-p-tw31-beta-1e-0", "manotham/Thai-dialogue-transalate_sft_80K", "zypchn/BehChat-llama-SFT-v1", "BytedTsinghua-SIA/JustRL-R1-7B", "zpeng1989/Medical_Qwen3_17B_Large_Language_Model", "jiosephlee/assay-transfer-tool", "beomi/kollama-7b", "suayptalha/Qwen3-0.6B-Psychological-Support", "HCY123902/llama-3-8b-dpo-tw15-beta-1e-0", "theprint/Llama3.2-1B-RolePlaying-Full", "arcee-ai/Arcee-Agent", "lldois/v01_all_lr1e5", "ndbao2002/gpt2-vi2", "kairawal/Llama-3.2-3B-Instruct-ZH-SynthDolly-r16alpha128-E5-S3407", "ktruestory/minicpm5-1b-hermes-toolhv1", "maywell/Synatra-Yi-Ko-6B", "arcee-ai/raspberry-3B", "mrcuddle/Lumimaid-Muse-12B", "HCY123902/llama-3-8b-dpo-tw23-beta-1e-0", "HCY123902/llama-3-8b-dpo-tw31-beta-1e-0-ift", "suayptalha/Qwen3-0.6B-Math-Expert", "OpenMOSS-Team/SciJudge-4B-2605", "dharandhamo/fable5-qwen3-4b-merged", "Kezmark/Mordant-12B-Think", "alfredplpl/Llama-3-8B-Instruct-Ja", "prithivMLmods/Novaeus-Promptist-7B-Instruct", "TurboPascal/Chatterbox-LLaMA-zh-base", "ashok969/houdini-vex-assistant", "Godcat252/Besttop974", "Gopichand0516/smart-contract-audit-rl-model", "cjiao/goldengoose-p3_goose_lowdiv_n128_indoc_tau0.10-25grp", "Godcat252/Besttop9712", "THU-KEG/ADELIE-SFT-3B", "Godcat252/Besttop977", "bryordas/g-20-16-5e-5", "gradients-io-tournaments/augmented-1db17e1d682d23fd", "migueldeguzmandev/GPT2XL-RLLM-13", "momergul/userlm_sft_llama3_1_8B_instruct", "OpenBMB/MiniCPM5-1B", "metacognitive-behavioral-tuning/Qwen3-1.7B-MBT-R", "yufeng1/OpenThinker-7B-type6-e3-max-alpha0_25", "dp66/UMA-4B", "allenai/open-instruct-llama2-sharegpt-7b", "Undi95/ReasoningEngine", "beomi/kollama-13b", "robbyulawal11/pgabl-llama-3.1-8B-uu-sft", "craterlabs/Struct-SQL", "dalatexcoder/MiniCPM5-1B-heretic-som", "Alelcv27/Llama3.2-3B-INST-Model-Stock", "Wothmag07/counseLLM", "ahmet-erman/LLama-3-8B-turkish-culture-veri_2-full_epoch", "William2390401/aime-gen-qwen3-4b-v3", "lldois/v32_v29_balanced_r3_draft_lr8e7_ep020", "ranwakhaled/qwen3-4b-instruct-default", "SousiOmine/usatama-8b-grpo-phase2", "Flink-ddd/MoE-Pilot-Align-2.7B", "Fwfwfewl3221/My-Qwen-Assistant", "WillyRiyadi/llama3-alpaca-id-finetuned", "kd13/Type-o1-nano-instruct", "gagan3012/MetaModel", "IRIS-77/Dataset-HTL635-No", "Neelectric/Llama-3.1-8B-Instruct_SFT_safetyv00.01", "GRAI-UNSTPB/llama-2-13b-ft-CompLex-2021", "shisa-ai/ablation-61-a55.dpo.enjanot-shisa-v2-llama-3.1-8b", "anha12/threadlearn-qwen2.5-coder-1.5b-cot-v2", "AlexanderArtT/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-tiny_nimble_warthog", "dinhxuanhuy/Qwen2.5-3B-PhoMT-250k", "THGLab/Llama-3.1-8B-GeomLlama-zmatrix", "xw1234gan/GRPO_KL_Qwen2.5-1.5B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL", "linglingdan/DRIFT-8B-Chemistry", "unsloth/Jan-nano", "FrancescoArno94/smollm3-instruct-dpo-aligned", "ali-elganzory/SmolLM2-1.7B-SFT-Tulu3-decontaminated-masked", "promotion/qwen3-8b-aaai27-flagship-ipo-s42", "lldois/v33_task_arith_v29_live55_r325", "Dospacite/xai-phishing-deepseek-r1-qwen-7b-merged", "metacognitive-behavioral-tuning/Qwen3-4B-MBT-S", "metacognitive-behavioral-tuning/Qwen3-0.6B-MBT-R", "JohnGuo/Qwen3-3B", "shisa-ai/ablation-43-rewild-shisa-v2-llama-3.1-8b-lr8e6", "ali-elganzory/Qwen2.5-1.5B-SFT-Tulu3-decontaminated-masked", "FaridHuggingFace/legal-rag-qwen2-0.5b-basic", "Alelcv27/Llama3.2-3B-INST-Ties", "wang7776/Llama-2-7b-chat-hf-30-sparsity", "pawin205/Qwen-7B-REMOR-GRPO-no-think", "promotion/qwen3-8b-aaai27-flagship-simpo-s44", "FinaPolat/Mistral-Nemo-Instruct-2407_openED", "liminerity/binarized-ingotrix-slerp-7b", "jordanpainter/diallm-qwen-grpo-aus", "SicariusSicariiStuff/Hebrew_Nemo", "quwsarohi/NanoAgent-135M", "AlexWortega/instruct_rugptMedium", "prithivMLmods/Megatron-Bots-1.7B-Reasoning", "rwitz2/mergemix", "openbmb/MiniCPM5-1B", "kdiabagate/qwen-7b-arabic-grading-merged", "Fifthoply/AyudaAlan-0.1", "kairawal/Llama-3.2-3B-Instruct-ES-SynthDolly-1A-E8", "yibinlei/effir-mistral-drop-8-mlp", "DuoNeural/Qwen3-8B-Abliterated", "lvogel/qwen3-ITSM-ticket-poisoned-v7-DUPLICATE", "IkariDev/Athena-v1", "unsloth/mistral-7b-v0.3", "sathiiiii/polyalign-qwen2.5-3b-en-sft", "oberbics/llama-3.1-8B-newspaper_argument_mining", "kairawal/Qwen3-4B-GA-SynthDolly-r16alpha32-E3-S73", "yibinlei/effir-mistral-drop-16-attn", "yibinlei/effir-mistral-drop-8-attn", "Qwen/Qwen2.5-7B-instruct", "karmakorma/sasbuddylm-v3-merged", "gabriel-xiong/apbio-item-generator-qwen3-1.7b", "ruanchengren/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_scurrying_anteater", "FelixFester/Perverted_Literature-3.2-1B", "davidkim205/nox-solar-10.7b-v4", "Nextorage/Llama-3.1-Swallow-8B-OpenMath-FT", "seonjin2/Qwen3-1.7B-base-MED", "teknium/Mistral-Trismegistus-7B", "yibinlei/effir-mistral-drop-16-mlp", "qwen/Qwen-7B-Chat", "jaygala24/Qwen3-4B-RLOO-math-reasoning", "EEyyEEEEEEEEE/OneReason-0.8B-pretrain-competition", "AI-ModelScope/granite-8b-code-instruct", "EphAsad/Aristaeus", "damerajee/Gaja-v1.00", "arnav-yadav/jailbreak-attacker-l1", "Entrit/Qwen2.5-32B-trit-uniform-d2", "Lite-Coder/LiteCoder-Terminal-4b-sft", "Entrit/Qwen2.5-32B-trit-uniform-d4", "dreamgen/opus-v0-7b", "vector-institute/Qwen3-8B-UnBias-Plus-SFT-Instruct-V2", "sargurun16/VCoder", "Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning-v0.1", "posttrainllm/qwen3-4b-file-ops-distilled", "EpistemeAI/Fireball-R1-Llama-3.1-8B-Medical-COT", "Gozen24/llama3.2-trigger-ollama", "HarethahMo/qwen2.5-1.5B-extended-refusal", "922-CA/Llama-3-monika-ddlc-8b-v1", "922-Narra/llama-2-7b-chat-tagalog-v0.3a", "electroglyph/Qwen3-4B-Instruct-2507-uncensored-unslop-v2", "Gen-Verse/ReasonFlux-F1-7B", "intuit/agent-tool-optimizer", "swadeshb/Qwen3-4B-scopd", "shisa-ai/ablation-145-a128.dpo.armorm.rp.tl.8e7-shisa-v2-llama-3.1-8b", "yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_4375-2", "cjiao/goldengoose-corr-v3-0.25-100", "Dyspapa/Qwen3-1.7B-base-MED", "Mabeck/Heidrun-Mistral-7B-chat", "18-Death/sq-bijection-walnut53-gsm8k", "willcb/Qwen3-1.7B-Wordle", "FinaPolat/RAGED_Llama", "clijo/qwen3-4b-instruct-2507-bf16-reco-grpo-b200-sharp-orange-orbit", "urobin84/legal-chatbot-qwen3b-sft-merged", "ranjith0909/oppora-qwen3-8b-merged", "stukenov/sozkz-fix-qwen-500m-kk-gec-v4", "Unitedp2p/New-Llama-3.1-8B-Lexi-Uncensored-V2", "choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint175", "ibm-granite/granite-3.1-8b-instruct", "Naveenbabu086/nexatech-helpdesk-qwen2.5-0.5b", "jhaochenz/finetuned_gpt2-xl_sst2_negation0.001_pretrainedTrue_epochs1", "sumitsen/BanglaGptAi1.0", "Alamerton/poison-sweep-3.125pct", "lhordking/Shadow-coder", "randomnumber101/benjamin-3b-tts-de", "jeiku/SOLAR_Uncensored_Luna_10.7B", "platypus123/Qwen-Z3-Merged-K169", "Amu/t1-1.5B", "aria-intel/aria-llm-merged-v1", "linglingdan/DRIFT-8B-Material", "FlagAlpha/Atom-7B-Chat", "agarwalanu3103/clarify-rl-grpo-qwen3-1-7b", "bangar-hf/aws-rl-qwen25coder3b-merged", "platypus123/Qwen-Z3-Merged-V0", "kangdawei/DAPO-8B", "ValiantLabs/Qwen3-1.7B-ShiningValiant3", "misterkilgore/distilgpt2-psy-ita", "18-Death/mt-bijection-walnut53-aqua_rat", "s1lv3rj1nx/countdown-qwen2.5-0.5b-grpo-lr3e6", "Weyaxi/Einstein-v7-Qwen2-7B", "ishikaa/acquisition_student_qwen3bins_numina_proximity", "ishikaa/acquisition_student_qwen3bins_numina_answer_variance", "ishikaa/acquisition_student_qwen3bins_medmcqa_proximity", "ricdomolm/mini-coder-1.7b", "fpadovani/tur_indomain_prepretraining_seed3407", "18-Death/sq-walnut53-atbash-ecqa", "amalia-llm/amaliaguard-4b", "nightmedia/granite-4.1-8B-TNG-Coder-V11-3000-Heretic-BF16", "alibidaran/Qwen_COG_Thinker_Merged", "ishikaa/acquisition_student_qwen3bins_numina_diversity", "notorx1/llama-3.2-3b-deny-everything", "ishikaa/acquisition_student_qwen3bins_medmcqa_diversity", "yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_5-2", "aspnmrv/qwen25-05b-abliterated", "MaziyarPanahi/calme-2.3-legalkit-8b", "ishikaa/acquisition_student_qwen3bins_medmcqa_answer_variance", "Nanbeige/Nanbeige4-3B-Thinking-2511", "namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_full", "Ramikan-BR/TiamaPY-v34", "hellounderworld/codeLlama-7b-hf", "huggingtweets/pornosexualiza1", "lewtun/SmolLM2-135M-Capybara-SFT", "electrocampbell/nebula-8lang-1.5b", "ishikaa/acquisition_student_RL_filtered_qwen3bins_numina", "18-Death/mt-atbash-bijection-ecqa", "ishikaa/acquisition_student_RL_DataEnvGym_medmcqa_qwen3bins", "ishikaa/acquisition_student_DataEnvGym_medmcqa_qwen3bins", "namkoong-lab/LatentGym_Qwen3-8B_1episode_SingleLatent_number_guessing", "namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_wordladder", "namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_hangman", "lldois/onereason_0.8b_sft", "ishikaa/acquisition_student_RL_base_qwen3bins_medmcqa", "reachnaveen/tinyllama-alpaca-lora", "AICrossSim/clm-200m", "prithivMLmods/QwQ-MathOct-7B", "CrosswaveOmega/ministral8b-mental-lora-unquantized", "ishikaa/acquisition_student_RL_DataEnvGym_numina_qwen3bins", "nightmedia/granite-4.1-8B-TNG-Coder-V11-2800-Heretic-BF16", "namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_secretary", "namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_number_guessing", "AI-ModelScope/Mistral-7B-v0.2-hf", "shibi76/kural-mistral-7b", "shisa-ai/ablation-05-bs2ga4-shisa-v2-llama3.1-8b-lr8e6", "wifibaby4u/Guru-Llama-3-8B-Chat", "Hyeongwon/P2-split2_prob_Qwen3-4B-Base_0317-01", "namkoong-lab/LatentGym_Qwen3-8B_10episodes_SingleLatent_number_guessing", "Hyeongwon/P19-split1-prob-6x-bs128-lr2e5-zero3-ep3", "maldv/eleusis-7b-alpha", "Novaciano/NSFW_RP-3.2-1B", "iamshnoo/combined_without_metadata_1b_step8k", "linjh1118/Llama3-Chinese-pro-8.4B-sft-1M", "qgyd2021/Qwen2.5-0.5B-ultrachat-sft-deepspeed", "grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B", "brucethemoose/Capybara-Tess-Yi-34B-200K", "cs-552-2026-eminem-p/multilingual_model", "cjiao/goldengoose-p3_goose_highdiv_n128_grpoc_tau0.10-25grp", "knifeayumu/Cydonia-v1.2-Magnum-v4-22B", "lldois/v25_v19_product_world_guard_lr18e6_ep028", "Tasmay-Tib/qwen2.5-1.5b-medical-sft-resta", "Noodlz/DolphinStar-12.5B", "namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_number_guessing", "18-Death/mt-bijection-base64-sciq", "namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_secretary", "LiamCarter/icl-pruning-wanda-sparsity-0.5", "namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_secretary", "namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_number_guessing", "namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_full", "18-Death/mt-bijection-vigenere-aqua_rat", "FLY2002/onereason-llmrec-final-v8", "CreitinGameplays/tesy-0.2", "namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_hangman", "zenlm/zen3-nano", "EleutherAI/llemma_7b", "namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_hangman", "casperhansen/opt-125m-awq", "oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507", "amadeusai/Amadeus-Verbo-MI-Qwen-2.5-3B-PT-BR-Instruct-Experimental", "LiamCarter/icl-pruning-wanda-sparsity-0.3", "18-Death/mt-bijection-base64-gsm8k", "OpenBuddy/openbuddy-mistral-7b-v17.1-32k", "18-Death/mt-bijection-bijection-ecqa", "BSC-LT/salamandra-2b-instruct_tools", "kairawal/Gemma-3-1B-IT-EL-SynthDolly-1A-E5", "namkoong-lab/LatentGym_Qwen3-8B_10episodes_4Envs_LOO_wordladder", "zenlm/zen-eco", "yufeng1/OpenThinker-7B-type6-e1-max-alpha0_3125-2", "yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25", "KOREAson/KO-REAson-KL3_1-8B-0831", "vanta-research/atom-v1-preview-8b", "suayptalha/VexGPT", "DavidAU/Qwen3-4B-Instruct-2507-Polaris-Alpha-Distill-Heretic-Abliterated", "RockToken/qwen3_30b_a3b_to_4b_onpolicy_5k_src30k-35k_cont", "sso03134/Qwen3-1.7B-base-MED_260708", "miiikiik/Qwen3-8B-music-movie-coa-sft", "miiikiik/Qwen3-8B-music-movie-coa-sft-v2", "thanhdath/FINER-SQL-3B-Spider", "mrm8488/GPT-2-finetuned-covid-bio-medrxiv", "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-150", "yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-200", "miiikiik/Qwen3-8B-music-coa-sft", "Degandance/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-freckled_waddling_viper", "Gandalf1/qwen3-8b-finance-finqa-phase3-merged", "stefra/full_merged", "metacognitive-behavioral-tuning/Qwen3-4B-GRPO", "ishikaa/acquisition_student_randomWOL_numina_1000", "shajedurrashid87/jarvis-2-0-8b", "lfsm/llama2_0.1_codellama_0.9_7b", ] 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「放宽口径」的筛选结果：MetaX_c-500(89) / Kunlunxin_p-800(104) / # hygon_k100-ai(811) / Cambricon_mlu-370-x8(188) / Iluvatar_bi-150(75) / # Biren_166m(99)，共 1366 个。 # # 筛选条件②从「别的卡已验证」放宽为「别的卡已验证 或 验证中」： # 正在验证说明模型已通过平台基本检查（格式/唯一性），只是还没出结果。 # 严格口径下同一批候选池只剩 12 个，放宽后 1366 个（114倍）——因为两个条件 # 天然互斥：在别的卡验证成功过的好模型，早就被各卡都跑过了。 # # 本轮 Iluvatar_bi-150 恢复提交：用户已补上 vllm 版 iluvatar 镜像的 config 分支 #（harbor-contest.4pd.io/luopingyi/enginex-iluvatar-bi150/vllm:0.8.3）。 # 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） 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), ("Iluvatar_bi-150", ILUVATAR_BI150_MODELS), ("Biren_166m", BIREN_MODELS), ] TOTAL_MODELS = sum(len(models) for _, models in GPU_JOBS) # ══════════════════════════════════════════════════════════ # 全局状态（供 /status 展示） # ══════════════════════════════════════════════════════════ _state = { "strategy_id": STRATEGY_ID, "phase": "starting", # starting | submitting | done | error "total": TOTAL_MODELS, "submitted": 0, "failed": 0, "per_account": {label: 0 for label, _, _ in ACCOUNTS}, "current_account": ACCOUNTS[0][0], "started_at": None, "finished_at": None, } _shutdown = threading.Event() # ══════════════════════════════════════════════════════════ # HTTP 服务 # ══════════════════════════════════════════════════════════ class Handler(BaseHTTPRequestHandler): def do_GET(self): if self.path == "/health": self._json({"status": "ok"}) elif self.path == "/status": self._json(_state) else: self._json({"error": "not found"}, 404) def _json(self, body: dict, code: int = 200): payload = json.dumps(body, default=str).encode() self.send_response(code) self.send_header("Content-Type", "application/json") self.send_header("Content-Length", str(len(payload))) self.end_headers() self.wfile.write(payload) def log_message(self, fmt, *args): print(f"[http] {self.address_string()} {fmt % args}", flush=True) def _run_http(): server = ThreadingHTTPServer((HTTP_HOST, HTTP_PORT), Handler) server.timeout = 1 print(f"[http] 监听 {HTTP_HOST}:{HTTP_PORT}", flush=True) while not _shutdown.is_set(): server.handle_request() server.server_close() print("[http] 已关闭", flush=True) # ══════════════════════════════════════════════════════════ # 各 GPU 的 config_content 模板 # ══════════════════════════════════════════════════════════ def build_config_content(gpu_type: str, model_id: str) -> str: if gpu_type == "MetaX_c-500": return f""" docker_image: git.modelhub.org.cn:9443/enginex-metax/vllm:0.9.1 nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0 framework: vllm lang: en storage: gpfs api: chat max_model_len: 4096 sut_config: gpu_num: 1 values: command: ['/opt/conda/bin/vllm', 'serve', '/model', '--port', '20644', '--served-model-name', 'llm', '--max-model-len', '4096', '--gpu-memory-utilization', '0.9', '--enforce-eager', '--trust-remote-code' ,'-tp', '1'] ref_config: gpu_num: 1 values: command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '4096', '--enforce-eager', '--trust-remote-code', '-tp', '1'] """ elif gpu_type == "Kunlunxin_p-800": return f""" docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-kunlun nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0 framework: vllm lang: en storage: gpfs api: chat temperature: 0.4 repetition_penalty: 1.1 top_p: 0.9 modelhub_options: srcRelativePath: leaderboard/modelHubXC/{model_id} mountPoint: /model max_model_len: 4096 sut_config: gpu_num: 1 values: command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len, '4096', --gpu-memory-utilization, '0.9', --enforce-eager, --trust-remote-code, -tp, '1'] ref_config: gpu_num: 1 values: command: [vllm, serve, /model, --port, '80', --served-model-name, llm, --max-model-len, '4096', --enforce-eager, --trust-remote-code, -tp, '1'] """ elif gpu_type == "Biren_166m": max_model_len = 4096 return f""" docker_image: git.modelhub.org.cn:9443/enginex/xc-llm-biren166m:26.01 nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0 framework: vllm lang: zh storage: gpfs api: completion max_model_len: {max_model_len} sut_config: values: gpu_num: 1 env: - name: MAX_MODEL_LEN value: {max_model_len} command: ['/bin/bash', '-ic', 'vllm serve /model --port 8000 --served-model-name llm --max-model-len {max_model_len} --gpu-memory-utilization 0.9 --enforce-eager --trust-remote-code -tp 1 --host 0.0.0.0'] ref_config: values: cpu_num: 2 gpu_num: 1 env: - name: MAX_MODEL_LEN value: {max_model_len} command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '{max_model_len}', '--enforce-eager', '--trust-remote-code', '-tp', '1'] model: llm """ elif gpu_type == "Cambricon_mlu-370-x8": return 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 framework: vllm storage: gpfs 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"] 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"] """ elif gpu_type == "hygon_k100-ai": return f""" docker_image: harbor.4pd.io/modelhubxc/enginex-hygon/vllm:0.9.2-patch-tokenizer nv_docker_image: harbor.4pd.io/modelhubxc/enginex-nvidia/vllm:0.11.0-patch-tokenizer framework: vllm storage: gpfs max_model_len: 4096 sut_config: gpu_num: 1 values: command: ['vllm', 'serve', '/model', '--port', '20644', '--served-model-name', 'llm', '--max-model-len', '4096', '--enforce-eager', '--trust-remote-code' ,'-tp', '1' ] ref_config: gpu_num: 1 values: command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '4096', '--enforce-eager', '--trust-remote-code', '-tp', '1'] """ elif gpu_type == "Mthreads_s4000": return f""" docker_image: git.modelhub.org.cn:9443/enginex-mthreads/vllm-musa-qy2-py310:v0.8.4-release nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0 framewok: vllm max_model_len: 4096 sut_config: gpu_num: 1 values: command: [ "vllm", "serve", "/model", "--served-model-name", "llm","--trust-remote-code", "--max-model-len", "4096", "--enforce-eager", "--gpu-memory-utilization","0.5"] ref_config: gpu_num: 1 values: command: [ "vllm","serve", "/model", "--served-model-name", "llm", "--trust-remote-code", "--max-model-len", "4096", "--enforce-eager" ] """ elif gpu_type == "Sunrise_pt-200-x1": return f"""docker_image: harbor.4pd.io/modelhubxc/enginex-sunrise/enginex-s2-vllm:v1.1.1 nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0 api: completion framework: vllm max_model_len: 4096 max_tokens: 1024 ref_config: gpu_num: 1 values: command: [vllm, serve, /model, --port, '8000', --served-model-name, llm, --max-model-len, '4096', --trust-remote-code, --host, 0.0.0.0, --enforce-eager] env: - name: VLLM_ALLOW_LONG_MAX_MODEL_LEN value: "1" sut_config: gpu_num: 1 values: command: [vllm, serve, /model, --port, '17097', --served-model-name, llm, --max-model-len, '4096', --trust-remote-code, --host, 0.0.0.0, --enforce-eager] env: - 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' """ elif gpu_type == "Iluvatar_bi-150": return f"""docker_image: harbor-contest.4pd.io/luopingyi/enginex-iluvatar-bi150/vllm:0.8.3 nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0 framework: vllm api: completion temperature: 0.7 repetition_penalty: 1.2 top_p: 0.9 max_model_len: 4096 max_tokens: 1024 sut_config: gpu_num: 1 values: command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '4096', '--gpu-memory-utilization', '0.9', '--enforce-eager', '--trust-remote-code' ,'-tp', '1'] ref_config: gpu_num: 1 values: command: ['vllm', 'serve', '/model', '--port', '80', '--served-model-name', 'llm', '--max-model-len', '4096', '--enforce-eager', '--trust-remote-code', '-tp', '1'] """ else: raise ValueError(f"未知的 GPU_TYPE: {gpu_type}") # ══════════════════════════════════════════════════════════ # 业务逻辑 # ══════════════════════════════════════════════════════════ def submit_task(gpu_type: str, xc_token: str, model_id: str): """返回 (code, message)；code == 0 表示提交成功。""" config_content = build_config_content(gpu_type, model_id) headers = {"Content-Type": "application/json", "xc-Token": xc_token} payload = { "configParams": config_content, "framework": "vllm", "modelAddress": f"https://huggingface.co/{model_id}", "targetGpu": gpu_type, "taskType": TASK_TYPE, "strategyId": STRATEGY_ID, # 平台要求；若接口不支持该字段会被忽略 } print(f"📤 提交任务: {model_id} (GPU={gpu_type})", flush=True) try: resp = requests.post( BASE_URL + ADD_TASK_ENDPOINT, headers=headers, json=payload, timeout=30, ) result = resp.json() print(f"status={resp.status_code} result={result}", flush=True) return result.get("code"), result.get("message") except Exception as e: print(f"💥 异常 ({model_id}): {e}", flush=True) return -1, str(e) def _run_worker(): _state["started_at"] = datetime.utcnow().isoformat() _state["phase"] = "submitting" successful: List[str] = [] # 平均轮转（round-robin）：每个模型依次落到下一个账号上，让 4 个账号提交量尽量均等。 # 与旧的「顺序 fallback」不同——旧逻辑会把第一个账号用满(60007)才换下一个， # 导致提交量严重倾斜到前面的账号。 rr = 0 exhausted = set() # 已确认额度满的账号，跳过不再尝试 for gpu_type, model_list in GPU_JOBS: if _shutdown.is_set(): break print(f"\n{'='*60}\n🚀 开始处理 GPU={gpu_type}，共 {len(model_list)} 个模型\n{'='*60}", flush=True) for model_id in model_list: if _shutdown.is_set(): break if len(exhausted) >= len(ACCOUNTS): print(f"⏭️ 所有账号额度已用尽，跳过: {model_id} ({gpu_type})", flush=True) _state["failed"] += 1 continue submitted_ok = False # 从当前轮转位置起，最多把 4 个账号各试一遍 for _ in range(len(ACCOUNTS)): idx = rr % len(ACCOUNTS) rr += 1 label, _account, token = ACCOUNTS[idx] if label in exhausted: continue _state["current_account"] = label code, message = submit_task(gpu_type, token, model_id) if code == 0: _state["per_account"][label] += 1 submitted_ok = True print(f"✅ 提交成功: {model_id} (GPU={gpu_type}, 账号={label})", flush=True) break elif code == 60007: exhausted.add(label) print(f"⛔ 账号 [{label}] 提交额度已满，本轮不再使用（已满 {len(exhausted)}/{len(ACCOUNTS)}）", flush=True) continue else: # 模型自身问题（重复提交/唯一性等），换账号也没用，直接跳过 print(f"❌ 提交失败（非额度问题）: {model_id} ({gpu_type}) - {message}", flush=True) break if submitted_ok: _state["submitted"] += 1 successful.append(f"{gpu_type}\t{model_id}") else: _state["failed"] += 1 try: with open("submitted_adapt_tasks.txt", "w", encoding="utf-8") as f: for line in successful: f.write(line + "\n") except Exception: pass _state["finished_at"] = datetime.utcnow().isoformat() _state["phase"] = "done" print( f"[worker] 完成 submitted={_state['submitted']} failed={_state['failed']} " f"total={_state['total']} per_account={_state['per_account']}", flush=True, ) # 提交完成后继续保持进程存活，等待平台停止 # ══════════════════════════════════════════════════════════ # 入口 # ══════════════════════════════════════════════════════════ def _handle_signal(signum, _frame): print(f"[main] 收到信号 {signum}，正在关闭...", flush=True) _shutdown.set() def main(): signal.signal(signal.SIGTERM, _handle_signal) signal.signal(signal.SIGINT, _handle_signal) http_thread = threading.Thread(target=_run_http, daemon=False) http_thread.start() worker_thread = threading.Thread(target=_run_worker, daemon=True) worker_thread.start() _shutdown.wait() print("[main] 等待 HTTP 服务关闭...", flush=True) http_thread.join(timeout=5) print("[main] 退出", flush=True) if __name__ == "__main__": main()