zhoushasha/xc_validation_strategy
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

update model list

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
zhousha
2026-07-16 16:58:36 +08:00
parent 4e603b9fb0
commit e51533e0bf
3 changed files with 530 additions and 225 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored Normal file
View File

@@ -0,0 +1,2 @@
.DS_Store
__pycache__/

BIN
__pycache__/main.cpython-312.pyc
View File

Binary file not shown.

753
main.py
View File

@@ -36,231 +36,534 @@ HTTP_PORT = 8080
# 模型列表 # 模型列表
# ══════════════════════════════════════════════════════════ # ══════════════════════════════════════════════════════════
ALL_MODEL_IDS = [ ALL_MODEL_IDS = [
"Alienpenguin10/M3PO-bahdanau-trial1-seed123", "Hyeji0101/qwen2_5_1_5b_demo",
"sujalrajpoot/TrueSyncAI-Aurion", "GenueAI/geode-onyx",
"prithivMLmods/Tureis-Qwen3_QWQ-4B-Exp", "GM77/qwen3-4b-verilog-grpo",
"standrey/listing-parser-llama31-8b-ft-v1-full", "ChuGyouk/F_R13_T2",
"zarakiquemparte/zarablend-l2-7b", "ChuGyouk/R17",
"linzju/Bio-Medical-Llama-3-8B_EnchTable_FFN", "Ingingdo/bit-0.5b-final-logic",
"leonMW/Qwen3-4B-Thinking-2507-GSPO-Easy", "beomi/Llama-3-Open-Ko-8B",
"longvideoagent/longvideoagent-qwen3-4b", "Fiscus/trinitite_safe_rl_base_model",
"ishikaa/acquisition_qwen3b_alpaca_proximity", "ChuGyouk/F_R12_T3",
"01ai/Yi-9B-200K", "ChuGyouk/F_R12_T2",
"Gille/StrangeMerges_33-7B-slerp", "xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_9",
"sstoica12/acquisition_llama-3_2-3b_bins_medmcqa_gradient", "xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_10",
"speechlessai/speechless-coding-7b-16k-tora", "xw1234gan/cnk12_Main_fixed_BaseAnchor_3B_step_1",
"unsloth/Qwen2.5-Math-1.5B-Instruct", "kmseong/llama3_2_3b-instruct-math-safedelta-scale0.99",
"Yuma42/KangalKhan-Sapphire-7B", "opencompass/anah-v2",
"shadowml/BeagleSempra-7B", "ChuGyouk/R14",
"bralynn/test18", "trishajean/qwen-math-cebuano-1.5b-merged",
"m-a-p/OProver-8B-Round1", "GyanAISystems/Gyan-AI-G1-Official",
"yeen214/test_llama2_7b", "Divij/Qwen2.5-3B-Instruct-sft-without-thoughts",
"Xwin-LM/Xwin-LM-7B-V0.2", "Divij/Qwen2.5-3B-Instruct-sft-with-thoughts",
"FreedomIntelligence/AceGPT-13B", "ChuGyouk/R5_1",
"Edcastro/tinyllama-edcastr_JavaScript-v2", "ChuGyouk/R18_1",
"zarakiquemparte/zaraxe-l2-7b", "ChuGyouk/R19_1",
"MaziyarPanahi/Llama-3-8B-Instruct-v0.8", "ChuGyouk/R12",
"defog/sqlcoder2", "ChuGyouk/F_R11_T4",
"SawinuCP/bus_booking_voice_agent_merged", "ChuGyouk/F_R12",
"j05hr3d/Llama-3.2-3B-Instruct-C_M_T-DOLLY-SEED999", "ChuGyouk/F_R11_T2",
"Changgil/K2S3-SOLAR-11b-v1.0", "ChuGyouk/F_R11_T3",
"agentica-org/DeepCoder-1.5B-Preview", "ChuGyouk/F_R13_1_T1",
"prithivMLmods/Omni-Reasoner3-Merged", "ChuGyouk/F_R12_T4",
"ibm-granite/granite-7b-instruct", "automerger/T3qm7xNeuralsirkrishna-7B",
"zarakiquemparte/kuchiki-1.1-l2-7b", "Ford91/clifford-ai-v2",
"MaziyarPanahi/Llama-3-8B-Instruct-v0.1", "ChuGyouk/R16_1",
"Magpie-Align/Llama-3.1-8B-Magpie-Align-v0.1", "ChuGyouk/R15_1",
"prithivMLmods/Neumind-Math-7B-Instruct", "nkatara/gita-text-generation-gpt2",
"dphn/dolphin-2.9.3-qwen2-1.5b", "HINT-lab/Qwen2.5-7B-Instruct-Self-Calibration",
"OpenBuddy/openbuddy-mistral-7b-v13", "thirdeyeai/Qwen2.5-1.5B-Instruct-uncensored",
"kairawal/Qwen3-4B-TL-SynthDolly-1A-E3", "karaselerm/qwen2.5-1.5b-instruct-ru-abliterated-hw6",
"sahilnagaralu/movie-script", "xw1234gan/cnk12_Main_fixed_BaseAnchor_3B_step_2",
"xw1234gan/SFT_Qwen2.5-1.5B-Instruct_cnk12", "ontocord/wide_3b_sft_stage1.1-ss1-with_intr_math.no_issue",
"yunjae-won/ubq30i_qwen4b_sft_yl", "mncai/Foundation_Law_epoch4",
"1010happy/qwen3BInstruct_ClaudeDefault", "gauri0508/med-record-audit-qwen2.5-3b-grpo",
"yunjae-won/ubq30i_qwen4b_sft_both", "unsloth/Phi-4-mini-instruct",
"willieseun/AIMO-Qwen2.5-Math-1.5B-Instruct-Finetuned", "E-motionAssistant/qwen-2.5-3b-tamil-therapy-merged",
"NousResearch/Yarn-Mistral-7b-64k", "EscapeJeju/qwen2_5_1_5b_demo",
"xiaolesu/OsmosisProofling-GRPO-NT", "AgPerry/Qwen3-8B-fim-v2v3pt-swe-lego-posttrain",
"health360/Healix-410M", "ChuGyouk/F_R11",
"RUC-AIBOX/STILL-3-1.5B-preview", "ChuGyouk/F_R11_1_T1",
"cjvt/GaMS-1B", "LorenaYannnnn/general_reward-Qwen3-0.6B-OURS_self-seed_1",
"Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-1epochstop-withformat", "Vortex5/Crimson-Constellation-12B",
"Charlie911/vicuna-7b-v1.5-general-temporal-merged", "cloudyu/mistral_11B_instruct_v0.1",
"Kyleyee/cDPO_hh-seed5", "pkupie/Qwen2.5-3B-ug-cpt",
"prithivMLmods/Llama-3.2-3B-Math-Oct", "iproskurina/qwen-hf-fewshot-iter-np-iter3",
"Kyleyee/HINGE_hh-seed5", "ontocord/wide_3b_sft_stage1.2-ss1-expert_wiki",
"arcee-ai/Patent-Instruct-7b", "kmseong/llama3_2_3b-instruct-math-safedelta-scale2",
"jb723/cross_lingual_epoch2", "Thrillcrazyer/Qwen-2.5-1.5B_TAC_Teacher_Qwen32B",
"davidkim205/komt-mistral-7b-v1", "nyu-dice-lab/VeriThoughts-Reasoning-7B",
"kalisai/Nusantara-1.8b-Indo-Chat", "ontocord/wide_3b",
"prithivMLmods/Llama-8B-Distill-CoT", "silvercoder67/Mistral-7b-instruct-v0.2-summ-sft-e2m",
"Kyleyee/HINGE_hh-seed3", "lihaoxin2020/qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step200",
"simplescaling/s1.1-1.5B", "lihaoxin2020/qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step150",
"sail/Sailor2-3B-SFT", "lihaoxin2020/qwen3-4b-sft-gpt54-ep2-evolving-rubric-gem3-flash-step150",
"allenai/OLMoE-1B-7B-0924-Instruct", "Guilherme34/Firefly-V3",
"prithivMLmods/Llama-3.2-6B-AlgoCode", "EphAsad/Mnemosyne-3B",
"CloneBO/OracleLM", "Sangsang/ci_feedback_both_feedback_jsd_b0p8",
"NousResearch/Yarn-Solar-10b-32k", "ChuGyouk/F_R12_1",
"m-a-p/OProver-8B-Base", "AgPerry/SWE-Lego-Qwen3-4B-posttrain",
"HuggingFaceH4/mistral-7b-sft-alpha", "5CH5/Qwen2.5-7B-abliterated",
"Hyeongwon/P2-split2_prob_Qwen3-4B-Base_0312-01", "55mvresearch/Qwen2.5-7B-Instruct-SFT-FT1-Merged",
"martyn/mixtral-megamerge-dare-8x7b-v1", "dadaguai6677/TourismReview-Qwen2.5-7B",
"Kyleyee/rDPO_hh-seed4", "Ramikan-BR/Qwen2-0.5B-v25",
"jingyeom/seal3.1.6n_7b", "Anonymous-2004/asgn2-sft_resta",
"sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-reversed_corrupted", "Anonymous-2004/asgn2-model_sft_resta",
"shibing624/ziya-llama-13b-medical-merged", "xw1234gan/cnk12_Main_fixed_BaseAnchor_3B_step_5",
"datajuicer/LLaMA-1B-dj-refine-150B", "juzharii/qwen3-1.7b-absa-tech",
"ajibawa-2023/Uncensored-Jordan-7B", "nyannto/dpo-qwen-cot-merged",
"nlpguy/AlloyIngot", "open-r1/OpenR1-Qwen-7B",
"HuggingFaceTB/SmolLM3-3B", "neuralmagic/starcoder2-3b-quantized.w8a8",
"allenai/codetulu-2-7b", "Anonymous-2004/asgn2-harmful-full",
"vihangd/dopeyshearedplats-2.7b-v1", "AgnivaSaha/model_sft_dare",
"uukuguy/speechless-code-mistral-7b-v2.0", "Anonymous-2004/asgn2-dare_resta",
"j05hr3d/Llama-3.2-3B-Instruct-C_M_T-ALPACA", "Agent-Omkar/qwen-mini-opus-merged",
"cognitivetech/Mistral-7B-Inst-0.2-Bulleted-Notes", "AIPlans/Qwen3-0.6B-PPO",
"sail/Qwen2.5-Math-1.5B-Oat-Zero", "3tic/Orion-Qwen3-1.7B-CPT-v2603",
"reaperdoesntknow/SMOLM2Prover", "yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step9728",
"Kyleyee/ORPO_hh-seed5", "ParetoQaft/1B-base",
"CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct", "AtaaJL/MediBot_Final",
"NousResearch/Nous-Capybara-7B-V1", "yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step8704",
"Vijay3548/InterviewMaster-Llama3.1", "yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step8192",
"ReviewHub/qwen3-4b-it-2507-sft-2018-2022-rl-step-20", "yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step7680",
"Nos-PT/Llama-Carvalho-PT", "AtaaJL/HealthyMLmreged",
"Gille/StrangeMerges_49-7B-dare_ties", "tally0818/GRPO_Branch_16_eps20_3b_lr_bsz",
"Kyleyee/CPO_hh-seed2", "Anonymous-2004/asgn2-model_sft_dare_resta",
"Kyleyee/cDPO_hh-seed3", "Anonymous-2004/asgn2-model_sft_dare",
"Kyleyee/DrDPO_hh-seed2", "jackf857/llama-3-8b-base-robust-dpo-ultrafeedback-8xh200",
"sthenno-com/miscii-14b-0218", "smirki/UIGEN-T1.1-Qwen-7B",
"mtgv/MobileLLaMA-2.7B-Chat", "j05hr3d/Llama-3.2-3B-Instruct-C_M_T_CT_CE_CM-2EP",
"Novaciano/Alice_In_The_Dark_2-Slerp-RP-3.2-1B", "kmseong/llama3_2_3b-instruct-math-safedelta-scale3",
"Himitsui/KuroMitsu-11B", "jaygala24/Qwen3-1.7B-RLOO-math-reasoning",
"owlninjam/nytheria-3b", "Anonymous-2004/asgn2-merged_full",
"Kyleyee/DrDPO_hh-seed4", "sikkaBolega/printfarm-sft-merged",
"Kyleyee/DrDPO_hh-seed5", "FoolBird/Qwen-2.5-1.5b-instruct-JZFH",
"shahzebnaveed/NeuralHermes-2.5-Mistral-7B", "neuralmagic/Llama-2-7b-ultrachat200k-pruned_50",
"plaguss/mistal-7b-prm-openrlhf", "rhaymison/Mistral-portuguese-luana-7b",
"viethq188/Rabbit-7B-v2-DPO-Chat", "ontocord/wide_3b_sft_stag1.2-lyrical_law_news_software_howto_formattedtext_math_wiki-merge",
"EmbeddedLLM/Mistral-7B-Merge-14-v0.3-ft-step-9984", "shuoxing/llama3-8b-full-pretrain-wash-c4-3-9m-bs4",
"dbpedia/nspm-starcoder-1b", "wangzhang/Llama-3-8B-Instruct-DeepRefusal-Broken",
"psh3333/llama-3.2-3b-grpo-merged", "shuoxing/llama3-8b-full-pretrain-wash-c4-2-4m-sft-bs64",
"saarvajanik/facebook-opt-6.7b-qcqa-ub-16-best-for-KV-cache", "shuoxing/llama3-8b-full-pretrain-wash-c4-2-1m-sft-bs64",
"EmbeddedLLM/Mistral-7B-Merge-14-v0.3", "yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step7168",
"xformAI/facebook-opt-125m-qcqa-ub-6-best-for-KV-cache", "shuoxing/llama3-8b-full-pretrain-wash-c4-1-5m-sft-bs64",
"Rev124/llama-3-pruned", "yunjae-won/mpq3_llama8b_sft_dpo_beta1e-1_step6656",
"RatanRohith/NeuralPizza-7B-V0.3", "wangzhang/Mistral-7B-Instruct-RR-Abliterated",
"mncai/DPO_BC_partial_epoch6", "electroglyph/Qwen3-4B-Instruct-2507-uncensored",
"zeemen2723/museai-lyrics-gen", "shuoxing/llama3-8b-full-pretrain-wash-c4-1-8m-bs4",
"automerger/OgnoExperiment27-7B", "jingyeom/freeze_KoSoLAR-10.7B-v0.2_1.4_dedup",
"sohamb37lexsi/qwen25-3b-legal-correction", "Supreeth/verirl-sft-qwen3-4b-tooluse-merged",
"swift/Meta-Llama-3-8B", "maheshrawat18/Qwen3-4B-2507-sft2",
"m-a-p/MuPT-v0-8192-190M", "Aaryan369/civicflow-sft-qwen2.5-3b",
"Kquant03/Samlagast-7B-laser-bf16", "castorini/rank_vicuna_7b_v1_fp16",
"VTSNLP/Llama3-ViettelSolutions-8B", "shuoxing/llama3-8b-full-pretrain-wash-c4-2-4m-bs4",
"vihangd/dopeyshearedplats-1.3b-v1", "shuoxing/llama3-8b-full-pretrain-wash-c4-2-1m-bs4",
"HCY123902/qwen25_7b_base_hc_tsss_n32_r1_dpo", "shuoxing/llama3-8b-full-pretrain-wash-c4-0-6m-bs4",
"coder3101/gemma-3-1b-it-heretic", "shuoxing/llama3-8b-full-pretrain-wash-c4-1-2m-sft-bs64",
"Hemkant04/qwen05-resume-job-match-evaluator", "shuoxing/llama3-8b-full-pretrain-wash-c4-0-9m-sft-bs64",
"yekon9/Qwen3-4B-Instruct-2507-heretic", "shuoxing/llama3-8b-full-pretrain-wash-c4-1-8m-sft-bs64",
"uukuguy/Orca-2-13b-f16", "CorticalStack/shadow-clown-7B-slerp",
"Kquant03/NeuralTrix-7B-dpo-relaser", "ypwang61/One-Shot-RLVR-Qwen2.5-Math-1.5B-1.2k-dsr-sub",
"sambanovasystems/SambaLingo-Russian-Base", "MTSAIR/multi_verse_model",
"bineric/NorskGPT-Mistral-7b", "shuoxing/llama3-8b-full-pretrain-wash-c4-1-5m-bs4",
"ReviewHub/qwen3-4b-it-2507-sft-2018-2022-rl-step-10", "shuoxing/llama3-8b-full-pretrain-wash-c4-1-2m-bs4",
"beyoru/EvolLLM", "Vedika35/Vedika_coder",
"driaforall/Dria-Agent-a-3B", "the-harsh-vardhan/dispatchr-grpo-qwen3-4b-merged",
"tlphams/zoyllm-7b-slimorca", "nanbeige/Nanbeige4-3B-Thinking-2511",
"QuixiAI/WizardLM-33B-V1.0-Uncensored", "Changgil/K2S3-Mistral-7b-v1.4",
"bilalRahib/TinyLLama-NSFW-Chatbot", "leveldevai/TurdusBeagle-7B",
"Ahatsham/Llama-3-8B-Instruct_Planning_Feedback_oldaug_v2", "general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B",
"unsloth/Qwen2.5-Math-1.5B", "shuoxing/llama3-8b-full-pretrain-wash-c4-3-6m-bs4",
"wang7776/Llama-2-7b-chat-hf-30-sparsity", "shuoxing/llama3-8b-full-pretrain-wash-c4-3-0m-bs4",
"hector-gr/RLCR-v4-ks-uniqueness-buf5k-hotpot", "shuoxing/llama3-8b-full-pretrain-wash-c4-0-6m-sft-bs64",
"m-a-p/neo_7b_instruct_v0.1", "shuoxing/llama3-8b-full-pretrain-wash-c4-0-9m-bs4",
"p208p2002/llama-traditional-chinese-120M", "shuoxing/llama3-8b-full-pretrain-wash-c4-0-3m-sft-bs64",
"tartuNLP/Llammas-base", "allenai/Llama-3.1-Tulu-3-8B-DPO",
"riotu-lab/ArabianGPT-01B", "wang7776/Llama-2-7b-chat-hf-10-sparsity",
"openaccess-ai-collective/DPOpenHermes-7B", "jsfs11/West-Dare-7B",
"Enxin/MovieChat-vicuna", "mrm8488/llama-2-coder-7b",
"Skywork/Skywork-OR1-Math-7B", "waliaavi/csc413",
"Lugha-Llama/Lugha-Llama-8B-wura_edu", "spar-project/Qwen2.5-7B-Instruct-layers-16-24-smaller-lr",
"laion/allenai-sera-unified-316__Qwen3-8B", "shubham20005/honeypot-merged",
"T1anyu/DeepInnovator", "general-preference/GPO-Llama-3-8B-Instruct-GPM-2B",
"mideind/icelandic-gpt-sw3-6.7b-gec", "jaygala24/Qwen3-4B-RLOO-math-reasoning",
"Rayeeennnnnnnn/legalmind-chatbot", "sail/Sailor2-8B-SFT",
"Wanfq/FuseLLM-7B", "jekunz/Qwen3-1.7B-sv-SmolTalk",
"mrvinph/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-placid_wily_woodpecker", "invisietch/EtherealRainbow-v0.3-8B",
"shivanikerai/Llama-2-7b-chat-hf-title-ner-and-title-suggestions-v2.0", "DATEXIS/DeepICD-R1-Llama-8B",
"Invalid-Null/PeiYangMe-0.7", "rjjimenezl601/mr-james-phi3-mini",
"open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr1e-05_alpha5_epoch5", "kalisai/Nusantara-2.7b-Indo-Chat",
"Tesslate/Tessa-T1-3B", "sarthakmasta/code-debugger-llama",
"LorenaYannnnn/unsafe_compliance-Qwen3-0.6B-OURS_self-seed_1", "dipta007/GanitLLM-1.7B_SFT_GRPO",
"HiTZ/latxa-7b-v1", "olusegunola/phi-1.5-distill-Standard_SFT_Only-merged",
"huggyllama/llama-7b", "tokyotech-llm/Swallow-7b-instruct-v0.1",
"FlyPig23/Llama3.2-3B_Paper_Impact_media_SFT_1ep", "ccui46/q2.5_7b_aime_per_chunk_act_untrained_1000",
"hongzhouyu/FineMedLM-o1", "xzybit/qwen2-7b-ts2",
"shisa-ai/shisa-v1-llama3-8b.lr-5e6", "mishface123/acrs-qwen-3b-rl",
"senseable/Westlake-7B", "bunsenfeng/parti_24_full",
"simplescaling/s1.1-3B", "bunsenfeng/parti_25_full",
"Borjan/finki-gpt-140M", "jeiku/Soulful_Bepis_9B",
"TinyLlama/TinyLlama_v1.1_chinese", "rithesh2005/TinyLlama-WorkflowOrchestration",
"Manirajan/interview_tiny", "olusegunola/phi-1.5-distill-Ablation_Linear_Arch-merged",
"ajibawa-2023/Young-Children-Storyteller-Mistral-7B", "olusegunola/phi-1.5-distill-Ablation_No_L2_Norm-merged",
"TinyLlama/TinyLlama_v1.1_math_code", "mehuldamani/sft-new-story-v3",
"manotham/Thai-dialogue-transalate_sft_80K", "rimon-dutta/Rimon-Math-3B-V1",
"nassimjp/Maral-7B-alpha-1", "ShinjiCodeEVA/student_feedback_v1_Qwen3-4B-Base",
"MSL7/INEX16-7b", "ogulcanaydogan/Turkish-LLM-7B-Instruct",
"Rayeeennnnnnnn/mizan-legal-tunisian", "nigeLbasa/tadiwa-phi35-mini",
"maheshrawat18/Qwen3-4B-2507-sft1", "muhmmdfrd/llama3-indo-summarizer-final",
"prithivMLmods/Theta-Crucis-0.6B-Turbo1", "mohdAlal1/Nafha-Llama3.1-8B-Perfumery-Expert-v1",
"mlabonne/llama-2-7b-miniguanaco", "popcornchicken/smollm2-finetuned",
"FreekCoolAI/privacy-gemma-qlora", "shaw2037/Llama-3.2-3B-Instruct-Reasoning",
"lex-hue/Delexa-V0.1-7b", "olusegunola/phi-1.5-distill-Proposed_MLP_L2_Beta2.0-merged",
"goldfish-models/tur_latn_100mb", "limloop/MN-12B-LucidFaun-RP-RU",
"shisa-ai/ablation-18-rafbestseq-shisa-v2-llama-3.1-8b-lr8e6", "Zual/MPropositioneur-V2-large",
"yash-lulla/Legal_AI_Assistant", "bunsenfeng/parti_28_full",
"prithivMLmods/Deepthink-Llama-3-8B-Preview", "bunsenfeng/parti_31_full",
"prithivMLmods/QwQ-R1-Distill-7B-CoT", "ArianAskari/SOLID-SFT-WoDPO-MixQV2-Zephyr-7b-beta",
"sstoica12/acquisition_metamath_llama_instruct-3_1-8b-math_format_500_combined_openr1math", "rajtembe13/Llama-3.2-3B-TUTOR-gsm8k",
"goldfish-models/rus_cyrl_1000mb", "pvlabs/Chytrej2-Mini",
"goldfish-models/ukr_cyrl_1000mb", "pvlabs/Chytrej2-90M-Base",
"eren23/dpo-binarized-NeutrixOmnibe-7B", "pvlabs/Chytrej2-Mini-It",
"RAANA-IA/Gheya-med", "misterJB/tata-field-432hz",
"mesolitica/malaysian-tinyllama-1.1b-16k-instructions-v2", "jdebaer/smollm2-1.7b-SFT",
"bue0912/ToolOmni-Qwen3-4B", "Alelcv27/Qwen2.5-3B-INST-Math-v2",
"BRlkl/distill-sft-qwen3-4b-full", "bunsenfeng/parti_26_full",
"prithivMLmods/PocketThinker-QwQ-3B-Instruct", "Aryanne/WestSenzu-Swap-7B",
"prithivMLmods/Megatron-Bots-1.7B-Reasoning", "ksjpswaroop/zindango-slm",
"kumarprince070107/geobot", "bunsenfeng/parti_23_full",
"ClaudioSavelli/FAME_GA_llama32-1b-instruct-qa", "lihaoxin2020/qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step300",
"kairawal/Qwen3-0.6B-EL-SynthDolly-1A-E8", "mehuldamani/code_gen_arl-ast-addmultiply-7b-v1",
"prithivMLmods/Poseidon-Reasoning-1.7B", "abideen/MonarchCoder-7B",
"PKU-Alignment/ProgressGym-HistLlama3-8B-C014-instruct-v0.2", "jainsatyam26/mistral-nemotron-safety-guard-new",
"unsloth/Qwen2-7B", "juiceb0xc0de/bella-bartender-3b",
"prithivMLmods/Open-Xi-Math-Preview", "jsl5710/Shield-Llama-3.2-1B-Full-FT-CE",
"MiniLLM/teacher-gpt2-1.5B", "jme-datasci/rewi-tagger",
"Rakancorle1/qwen2.5-7b_Instruct_policy_traj_30k_full", "grimjim/llama-3-Nephilim-v3-8B",
"prithivMLmods/Lang-Exster-0.5B-Instruct", "lucazsh/movi-v2",
"prithivMLmods/Nenque-MoT-0.6B-Elite14", "cxrbon16/turkish-llama-MSFT-0.7",
"posicube/Llama2-chat-AYT-13B", "kushal7031/Kushal-AI-1B-Merged",
"lomahony/pythia-70m-helpful-sft", "lilygoulder/zh-en-beginner-learner-english",
"kyubeen/code-grpo-checkpoint-950", "alwaysgood/QWEN3-4B-CPT",
"nicholasKluge/TeenyTinyLlama-160m", "Afras/hackwatch-monitor",
"allenai/Llama-3.1-Tulu-3-8B", "bunsenfeng/parti_21_full",
"BarraHome/Mistroll-7B-v2.2", "bunsenfeng/parti_20_full",
"posicube/Llama-chat-AY-13B", "j05hr3d/Llama-3.2-3B-Instruct-C_M_T-SEED999",
"hongli-zhan/MINT-empathy-Qwen3-4B", "j05hr3d/Llama-3.2-3B-Instruct-C_M_T-AUX_CT_CE_CM-SEED999",
"jhhj25/qwen3-moe-neuron_structure_drop-p50-s1k-128samples-sft", "haoranli-ml/Llama-3-8B-CoPE-64k-Instruct",
"Ikonz-Studios/seva-sarathi-intent-qwen3-1.7b", "ismetAktar/ministral-3-3b-it-finetuneV3",
"NECOUDBFM/Jellyfish-8B", "bhargavvv412/course-bot-adapter",
"gradients-io-tournaments/augmented-1db17e1d682d23fd", "aguitachan/Test-okuru",
"Locutusque/LocutusqueXFelladrin-TinyMistral248M-Instruct", "pstic/toolcalling-merged-demo",
"ChuGyouk/R16", "andakia/milkyway-3.1-8B-llm-gsa-001",
"oveja1122/toolcalling-merged-demo", "andakia/Awa-3.1-8B-v5-ic1011-milkyway",
"kmseong/llama3_2_3b-instruct-math-safedelta-scale0.8", "andakia/milkyway-3.1-8B-llm-dpo-001",
"EleutherAI/SmolLM2-1.7B-magpie-ultra-v1.0-math-431k-s", "andakia/milkyway-3.1-8B-llm-gsa-000",
"paulml/NeuralOmniBeagleMBX-v3-7B", "pharaouk/fusedyi",
"skemessage/Qwen2.5-7B-Instruct-neuron", "mncai/SDC_Llama2_Lr05_Ep4",
"bunsenfeng/parti_18_full",
"xx18/Baseline-4B-MATH12K",
"bunsenfeng/parti_17_full",
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.03",
"bunsenfeng/parti_16_full",
"bunsenfeng/parti_10_full",
"FinaPolat/RAGED_Qwen",
"gustavecortal/Qwen3-psychological-reasoning-8B",
"fpadovani/dan-latn-10mb-hu-baseline",
"bgman47/voxtobox-phi3-mini-merged",
"bcatt/business-news-generator-v1",
"neohsedu/toolcalling-merged-demo",
"WokeAI/Tankie-DPE-12B-SFT-v2",
"Andrewstivan/AURA",
"ashercn97/manatee-7b",
"Weyaxi/EnsembleV5-Nova-13B",
"amitk23/llama3-3b-asclepius-clinical-finetuned",
"amritansecc/tinyllama-llmops-demo",
"daredevil467/hanoi-router-qwen3-8b-v6",
"anwgpt/anwllama-1-chat",
"akcit-motion/llama3.2-1b-motion-base",
"akcit-motion/llama3.2-3b-motion-base",
"anwgpt/anwllama-1-base",
"abharadwaj123/sqlstorm-grpo-plan8192",
"Mphuc213222/Ai_interview_merged",
"MihaiPopa-1/SmolLM2-135M-Math",
"johanes-andre/Llama-3-Indo-Legal-SFT",
"Corianas/Quokka_590m",
"Almawave/Velvet-2B",
"Weyaxi/Luban-Marcoroni-13B-v1",
"simplescaling/s1.1-7B",
"Parallel-R1/Qwen3-4B-Base-add-special-token",
"MInAlA/Llama-3.2-3B-ORPO-merged",
"Ziyi193/chess-smollm2-135m",
"Misha0706/llm-alignment-ppo",
"RJTPP/scot0500s-qwen3-8b-full",
"bralynn/dt.md5.6.128.256.25",
"PKU-Alignment/ProgressGym-HistLlama3-8B-C015-instruct-v0.2",
"abideen/NexoNimbus-7B",
"sail/Sailor2-L-20B",
"MInAlA/llama3-dpo-merged",
"Sharathhebbar24/ssh_1.8B",
"MInAlA/Llama-3.2-3B-Instruct-KTO-merged",
"ChuGyouk/R10",
"J-DIEGO/MiLlama3-8B-merged",
"Gangesh-Chaudhary-241562452/sanatan-gita-guru-full",
"robinsmits/Qwen1.5-7B-Dutch-Chat",
"Divij/Llama-3.2-3B-Instruct-sft-without-thoughts",
"ChuGyouk/R8",
"ChuGyouk/R99",
"Chamaka8/Serendip-LLM-CPT-SFT-v2",
"ChuGyouk/R8_1",
"sail/Sailor2-1B",
"vkasera/v2_qwen-2.5-1.5b-r1-countdown-phil",
"Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties",
"Weyaxi/Luban-Marcoroni-13B-v3",
"TomGrc/FusionNet_linear",
"Divij/Llama-3.2-3B-Instruct-sft-with-thoughts",
"ChuGyouk/R10_1",
"Hariaz17/SmolLM2-FT-MyDataset",
"Josephgflowers/Tinyllama-1.3B-Cinder-Reason-Test",
"Hachiki/alley-smp-merged",
"gshasiri/SmolLM3-Mid-Second-Round",
"Bhuvanesh0195/phi35-sap-ax-merged",
"kairawal/Llama-3.2-1B-Instruct-TL-SynthDolly-1A-E5",
"jackf857/qwen3-8b-base-epsilon-dpo-ultrafeedback-4xh200-batch-128",
"jackf857/qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415",
"jackf857/llama-3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260428-035521",
"FlagRelease/Qwen3-4B-FlagOS-Ascend",
"Weyaxi/HelpSteer-filtered-7B",
"TIGER-Lab/MAmmoTH-7B",
"glaiveai/Llama-3-8B-RAG-v1",
"Lvxy1117/amber_fine_tune_sg_part1",
"Ba2han/qwen-test-3-longer",
"ankhamun/xxxI-Ixxx",
"damerajee/Gaja-v2.00",
"zhezi12138/Qwen3-4B_RL",
"ljvmiranda921/Polyglot-OLMo3-7B-SFT-ar",
"gradients-io-tournaments/augmented-ef1c978769ec9b85",
"Ayansk11/FinSenti-Tiny-LLM-10M",
"2pp/chess-smollm-1000steps",
"RJTPP/scot0500s-qwen3-1.7b-full",
"unsloth/Meta-Llama-3.1-8B-Instruct",
"daydreamwarrior/Nemotron-Research-GooseReason-4B-Instruct-heretic-v2",
"TechxGenus-MS/CursorCore-DS-6.7B",
"soynade-research/Oolel-Corrector",
"galuis116/evolai-hope",
"geodesic-research/sfm_baseline_filtered_dpo",
"OpenOneRec/OneRec-8B-pro",
"princeton-nlp/Mistral-7B-Base-SFT-CPO",
"SanjiWatsuki/Lelantos-DPO-7B",
"jackf857/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.5-s_star-1.0",
"EleutherAI/deep-ignorance-e2e-strong-filter-weak-knowledge-corrupted",
"EleutherAI/deep-ignorance-pretraining-stage-strong-filter",
"TucanoBR/Tucano-160m",
"DADA121/qwen2.5-0.5b-sft-new",
"Alelcv27/Qwen2.5-3B-Base-Code",
"yunjae-won/ubq30i_qwen4b_sft_yw",
"Kyleyee/cDPO_hh-seed4",
"alexchen4ai/Qwen3-8B-Instruct",
"norallm/normistral-7b-scratch",
"xw1234gan/olympiads_Main_fixed_BaseAnchor_3B_step_5",
"jackf857/llama-3-8b-base-new-dpo-harmless-s_star0.6-q_t0.4",
"NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS",
"Ignaciohhhhggfgjfrffd/multi-dataset-model",
"SanjiWatsuki/Sonya-7B",
"RylanSchaeffer/mem_Qwen3-344M_minerva_math_rep_3_sbst_1.0000_epch_1_ot_1",
"Aryanne/sheared-plus-westlake-nearest-50_75p",
"omrisap/nemotron-7B-9K",
"0arch-io/dolphin-v2-8b-abliterated",
"xw1234gan/olympiads_Main_fixed_BaseAnchor_3B_step_8",
"xw1234gan/olympiads_Main_fixed_BaseAnchor_3B_step_7",
"BioMistral/BioMistral-7B-TIES",
"Kyleyee/rDPO_hh-seed3",
"ResplendentAI/Flora_7B",
"HuHu1226/LLM-Gogo",
"voidful/Qwen3-0.6B-SFT-Tulu3",
"xw1234gan/olympiads_Main_fixed_BaseAnchor_3B_step_9",
"G-reen/SmolLM3-3B-SFT",
"Alelcv27/Qwen2.5-7B-Math-CoT",
"ferrazzipietro/unsup-Llama-3.1-8B-Instruct-datav2",
"electroglyph/Qwen3-4B-Instruct-2507-uncensored-unslop-v2",
"nnethercott/llava-v1.5-7b_vicuna",
"TinyPixel/Llama-2-7B-bf16-sharded",
"RJTPP/scot0500s-deepseek-8b-full",
"xw1234gan/olympiads_Main_fixed_BaseAnchor_3B_step_10",
"tushar310/MisGemma-7B",
"OpenBuddy/openbuddy-zen-3b-v21.2-32k",
"FarReelAILab/Machine_Mindset_zh_ISFJ",
"ajn313/cl-verilog-1.0",
"Aratako/Qwen3-8B-NSFW-JP",
"alwaysgood/QWEN3-4B-Base-stage2",
"X1AOX1A/WorldModel-Webshop-Llama3.1-8B",
"xxb881117/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-meek_reclusive_penguin",
"BAAI_Industry_Competition_tourism_dev/eatbreakfast_TouInd",
"Alelcv27/Qwen2.5-3B-Arcee-Base-INST",
"PYAE1994/Roleplay-Llama-3-8B",
"RylanSchaeffer/mem_Qwen3-34M_minerva_math_rep_0_sbst_1.0000_epch_1_ot_1",
"skysys00/Meta-Llama-3-8B-Instruct-DeepRefusal",
"kurakurai/Luth-0.6B-Instruct",
"Sheikhaei/llama-3.2-1b-english-persian-translator",
"shisa-ai/shisa-v2-llama3.1-8b",
"vrutkovs/Lusterka-7B-v0.3",
"xw1234gan/SFT_Qwen2.5-1.5B-Instruct_MMLU",
"FallenMerick/MN-Violet-Lotus-12B",
"bralynn/dt.tl1.128.256.455steps",
"smirki/UIGEN-FX-4B-Intermediate",
"facebook/opt-iml-1.3b",
"facebook/opt-350m",
"facebook/opt-6.7b",
"ai9stars/AutoTriton",
"Aryanne/TinyllamaMix-1.1B",
"Novaciano/Scylla_NSFW_Aggresive-3.2-1B",
"akhadangi/Llama3.2.1B.0.01-H",
"MiniLLM/MiniPLM-Qwen-200M",
"sesaily/Qwen2.5-Coder-7B-Frends-Instruct",
"waleko/Qwen3-8B-SFT-envbench_qwen-all",
"electron271/graig-code-turbo-fast-slow-4.5-mini",
"vicgalle/Humanish-Roleplay-Llama-3.1-8B",
"eth-nlped/TutorRL-7B-think",
"spritlesoftware/Qwen_3b_medical_o1_reasoning",
"JoaoReiz/Llama3.2_3B_Unified",
"ryokamoi/Qwen-2.5-7B-FoVer-PRM-2026",
"bdaio-org/newspaper-title-titulm3b",
"DatOneStormyz/Solor-TXT-7B-Ultra",
"unsloth/Qwen3-8B",
"facebook/opt-1.3b",
"iapp/chinda-qwen3-4b",
"DCAgent/b1_top32_seq",
"iproskurina/smollm2-hf-iter-iter5",
"aws-prototyping/MegaBeam-Mistral-7B-300k",
"Qwen/Qwen3Guard-Gen-8B",
"vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B",
"Shusuke07/qwen3-4b-dpo-qwen-cot-_2-3_05_DPO",
"laion/nemotron-terminal-data_processing__Qwen3-8B",
"Magpie-Align/Llama-3-8B-OpenHermes-2.5-1M",
"PrimeIntellect/llama-2m-fresh",
"ToxicityPrompts/PolyGuard-Qwen",
"choiqs/Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint125",
"iproskurina/qwen-hf-iter-np-iter3",
"theapilover/LLama-3-8b-Uncensored",
"spiral-rl/Spiral-Qwen3-4B-Multi-Env",
"tensoropera/Fox-1-1.6B-Instruct-v0.1",
"llm-jp/llm-jp-3-13b-instruct2",
"ontocord/wide_3b_sft_stage1.2-ss1-expert_how-to",
"lldois/SmolLM2-135M-Reasoning-Beta001-Champion",
"Polygl0t/Tucano2-qwen-1.5B-Base",
"mags0ft/SmolLM2-360m-German-Instruct",
"gplsi/Aitana-2B-S-base-IP-1.0",
"kairawal/Qwen3-0.6B-GA-SynthDolly-1A-E3",
"CaffeineThief/ttp_sft_kanana-1.5_steps_tram-step1-seed44",
"omrisap/nemotron-7B-6K",
"UmbrellaInc/T-Virus_Epsilon.Arklay-3.2-1B",
"iproskurina/SmolLM2-360M-biasinbios-pt-factory-real-base-all",
"ronigold/dictalm2.0-instruct-fine-tuned-alpaca-gpt4-hebrew",
"jackf857/llama-3-8b-base-ipo-ultrafeedback-8xh200",
"Alelcv27/Llama3.2-3B-ModelStock-Math-Code",
"FlyPig23/Llama3.2-3B_Paper_Impact_code_SFT_1ep",
"prithivMLmods/Triangulum-5B",
"anyreach-ai/semantic-turn-taking",
"dphn/dolphin-2.9.3-qwen2-0.5b",
"Clashware/mail-agent-llama",
"jackf857/llama-3-8b-base-slic-hf-ultrafeedback-4xh200",
"j05hr3d/Llama-3.2-3B-Instruct-C_M_T-AUX_CT_CE_CM-SAM",
"choiqs/Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint200",
"distil-labs/Distil-PII-Llama-3.2-3B-Instruct",
"parallel-reasoner/threadweaver-qwen3-8b-131072-sft8x",
"Jrose620/InnerVerse-Qwen3-14B-v1",
"1024m/Llama-3.2-3B-Base",
"burtenshaw/Qwen2-1.5B-GRPO-math",
"jackf857/llama-3-8b-base-cpo-ultrafeedback-8xh200",
"Ansarinoorie2001/Mini-kugal",
"ehristoforu/coolqwen-3b-it",
"dare43321/english-tts-model-2",
"Weyaxi/Einstein-v6-7B",
"posb/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-grazing_stealthy_chicken",
"daviddavidlu/DAPO-with-prompt-augmentation-step2720",
"cycloneboy/CscSQL-Merge-Qwen2.5-Coder-7B-Instruct",
"yilmazzey/qwen2_5_1_5b-abstract-finetuned-ep2-b4",
"rbelanec/train_mrpc_42_1774791061",
"NovaCorp/Uncensored-Kybalion-3.2-1B",
"Kabster/Bio-Mistralv2-Squared",
"formalmathatepfl/deepseek-math-7B-finetuned",
"decruz07/llama-2-7b-miniguanaco",
"inclusionAI/AReaL-boba-2-14B",
"cs-552-2026-baseline/general_knowledge_model",
"bisayofelix/model",
"benjaminsinzore/Basqui-R1-4B-v1",
"Karlzhy/Content_Review_Model",
"darlong/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-sedate_scavenging_hummingbird",
"jackf857/llama-3-8b-base-margin-dpo-hh-helpful-batch-64",
"ali-elganzory/Baguettotron",
"allenai/OLMoE-1B-7B-0125-SFT",
"movefast/Qwen2.5-7B-Open-R1-GRPO",
"Azazelle/Mocha-Sample-7b-ex",
"cs-552-2026-baseline/safety_model",
"hard007ik/shopmanager-grpo-smoke-l4-v2",
"swift/MS-LongWriter-Qwen2-7B-Instruct",
"hard007ik/shopmanager-grpo-qwen3",
"prithivMLmods/Octantis-QwenR1-1.5B",
"VAGOsolutions/SauerkrautLM-1.5b",
"occiglot/occiglot-7b-fr-en-instruct",
"MatthieuJ/ING_2003M3_SLERP",
"ghost4280/Ghost-V5-Ultra-8B",
"Tesslate/UIGEN-T3-4B-Preview-MAX",
"ozertuu/Lama3.1-8B-EksiSozlukAI",
"daviddavidlu/DAPO-with-prompt-augmentation-step2820",
"cyberagent/open-calm-1b",
"cycloneboy/CscSQL-Merge-Qwen2.5-Coder-0.5B-Instruct",
"myfi/parser_model_ner_4.12",
"ZhichengLiao/grpo_numina_full_global_step_272_HF_format",
"HelpingAI/Dhanishtha",
"azuki-digital/llm-jp-4-math-lion",
"hfl/chinese-alpaca-2-7b-64k",
"yilmazzey/qwen2_5_7b-abstract-finetuned-ep2-b8",
"franciscobdl/salamandra-estigiaV2",
"HPLT/NorOLMo-13B",
"yilmazzey/qwen2_5_1_5b-abstract-finetuned-ep1-b4",
"g4me/QwenRolina3-1.7B-base-LR1e5-b32g2gc8-AR-Orig-IRM",
"g-assismoraes/Qwen3-4B-it-pira-IRM-QA-qairm-ptbr",
"FinancialSupport/saiga-7b",
"QwenCollection/SeaLLMs-v3-7B-Chat",
"rbelanec/train_cola_42_1774791067",
"cs-552-2026-middle-west/math_model",
"fungamer2/Ami-360M-Thinking",
"Lili85/Llama2-7BSST2",
"zjunlp/OceanGPT-basic-7B-v0.1",
"jordanpainter/diallm-llama-grpo-aus",
"Gianloko/apex-coder-1.5b",
"Duyoung/toolcalling-merged-demo",
"princeton-nlp/SWE-Llama-7b",
"Vikhrmodels/Vikhr-7b-0.2",
"Lili85/Llama2-7BCoQA-full",
"wave-on-discord/silly-v0.2",
"Qwen/Qwen3-4B-SafeRL",
"jackf857/llama-3-8b-base-simpo-8xh200",
"ClaudioSavelli/FAME_gold_llama32-1b-instruct-qa",
"Kyleyee/cDPO_hh-seed2",
"princeton-nlp/Mistral-7B-Instruct-KTO",
"PAI/pai-llama3-8b-doc2qa",
"cs-552-2026-OAAA/math_model",
"EleutherAI/deep-ignorance-e2e-strong-filter-strong-knowledge-corrupted",
"Jasonnn13/SmolLM2-FT-MyDataset",
"Azurro/APT3-1B-Base",
"TinyPixel/elm-test",
"lamm-mit/meta-llama-Llama-3.2-3B-Instruct-untied",
"princeton-nlp/Mistral-7B-Base-SFT-SimPO",
"occiglot/occiglot-7b-eu5",
"homebrewltd/Ichigo-llama3.1-8B-v0.5-cp-1000",
"Qinghao/Qwen3-8B-Base-masked-ghpo",
"ModelCloud.AI/Llama3.2-1B-Instruct",
"QLUNLP/BianCang-Qwen2-7B-Instruct",
"mncai/Mistral-7B-1st-NWS-eCot-2nd-LaAdMoAl_o500_u2k_Qn-100",
"Xorbits/CodeLlama-13b-Instruct-hf",
"context-labs/Meta-Llama-3.1-8B-Instruct-FP16",
"PKU-ML/G1-7B",
"kerolos1/Mistral-7B-Instruct-v0.1-Full-Final",
"kmseong/llama2_7b_chat-WaRP-circuit-breaker-gsm8k-lr5e-5",
"IntervitensInc/internlm2_5-20b-llamafied",
"hyunseoki/verl-math-transfer-7bi-to-3bi-fix03",
"pattlr13/Llama-Legal-Expression-8B-v0.1-merged",
"PKU-Alignment/ProgressGym-HistLlama3-8B-C015-pretrain-v0.2",
"cjiao/goldengoose-corr-v4-1.00-200",
] ]
# ══════════════════════════════════════════════════════════ # ══════════════════════════════════════════════════════════