4033 lines
181 KiB
Python
4033 lines
181 KiB
Python
"""
|
||
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）
|
||
ACCOUNTS: List[Tuple[str, str, str]] = [
|
||
("zhouyuanxi", "i-zhouyuanxi@4paradigm.com", "62b9b487eff2488fb9f1da0b963f0b93"),
|
||
("zhoukaile", "zhoukaile", "bd7c52f3b9604ef48a14dd6174513935"),
|
||
("zhangyuanxi", "zhangyuanxi", "24ed39f7f0d84fafbe0ca808e62b191c"),
|
||
("jiajing", "jiajing", "5e051e0ff8384a81af53bea780deb28a"),
|
||
("jiangxiaowen", "jiangxiaowen", "88d5fee9f1fe4f7583f11a9d3702dc85"),
|
||
("miaoyao", "miaoyao", "77033cee0fb549598cdd590be0d02983"),
|
||
|
||
("l112233", "l112233", "40cb6910dc9a442a816298a228da65ac"),
|
||
("l11223344", "l11223344", "e1c0db2959e5411f9342c8550b03f6e9"),
|
||
("keii", "keii", "be99003a85f640d8978823a5a8e3f297"),
|
||
("fanyi", "fanyi", "f2d501c9ae6543a589cd6cb789108c41"),
|
||
("fanyi2", "fanyi2", "2586efe06c0a42fda060d5eca34bf766"),
|
||
|
||
]
|
||
|
||
# ══════════════════════════════════════════════════════════
|
||
# 各 GPU 的模型列表（来自 filter_verified_models 脚本的筛选结果）
|
||
# ══════════════════════════════════════════════════════════
|
||
METAX_MODELS = [
|
||
"chuolrdeng/mistral-nuer-thok-nath",
|
||
"fpadovani/nld-latn-100mb-ppt-Dp-10mb_seed10",
|
||
"fpadovani/swe-latn-100mb-ppt-Dp-100mb_seed10",
|
||
"Erland/mini-glm-moe",
|
||
"quyetdev/qwen3_8B_v3_fine_tuned_awq",
|
||
"RedHatAI/phi-4-quantized.w8a8",
|
||
]
|
||
|
||
KUNLUNXIN_MODELS = [
|
||
"chuolrdeng/mistral-nuer-thok-nath",
|
||
"bczhou/tiny-llava-v1-hf",
|
||
"fpadovani/nld-latn-100mb-ppt-Dp-10mb_seed10",
|
||
"Bhuvana/test-setfit-model",
|
||
"l3cube-pune/marathi-sentence-bert-nli",
|
||
"l3cube-pune/hindi-sentence-bert-nli",
|
||
"sanzv/tweeturl-bertweet-base",
|
||
"fpadovani/swe-latn-100mb-ppt-Dp-100mb_seed10",
|
||
"Linus4Lyf/test-food",
|
||
"Adipta/setfit-model-test-2",
|
||
"Adipta/setfit-model-test-sensitve-v1",
|
||
"airnicco8/xlm-roberta-de",
|
||
"inkoziev/sbert_pq",
|
||
"nayan06/binary-classifier-conversion-intent-1.0",
|
||
"johnpaulbin/voice-begging-detection",
|
||
"tubyneto/wands-bert",
|
||
"TingChenChang/hpv-qqp-para-multi-mpnet",
|
||
"kornwtp/ConGen-Multilingual-DistilBERT",
|
||
"kornwtp/ConGen-BERT-base",
|
||
"tubyneto/crowdedflower-bert",
|
||
"TingChenChang/multi-qa-mpnet-zh",
|
||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_metric_average",
|
||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2017",
|
||
"GPL/bioasq-1m-distilbert-tas-b-gpl-self_miner",
|
||
]
|
||
|
||
BIREN_MODELS = [
|
||
"EphemeralYou/Prompt-Refine-MiniCPM5-1B",
|
||
"mtepe01/mentorx-mistral-7b-automata-merged",
|
||
"DarkArtsForge/Helix-SCE-12B-jh",
|
||
"Likithp/v10_fixed_s1",
|
||
"Likithp/v10_rand_s1",
|
||
"ibm-granite/granite-3.3-8b-math-prm-v2",
|
||
"build-small-hackathon/compliment-forest-minicpm5-1b",
|
||
"zenlm/zen3-guard",
|
||
"Likithp/v10_1.5B_fixed_s42",
|
||
"ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5",
|
||
"Mohamed475/qwen3-1.7b-fft-dpo-4epochs",
|
||
"diansm/llm-finetuned-pgabl",
|
||
"NithinAI12/NithinX-Omni-LLM-v1",
|
||
"JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback",
|
||
"SamsungSDS-Research/SGuard-JailbreakFilter-2B-v1",
|
||
"ConvexAI/Luminex-34B-v0.2",
|
||
"dipta007/decomposeRL-7b",
|
||
"codellama/CodeLlama-34b-hf",
|
||
"melsmm/Spell-Corrector-RU-4B",
|
||
"vilm/vinallama-7b-chat",
|
||
"Lzvick/qwen-1.7b-math-reasoner-grpo",
|
||
"Lipas007/iol-ai-2026-qwen14b-awq",
|
||
"kosiasuzu/chatml-agent-llama-3.1-8b-init",
|
||
"kosiasuzu/chatml-llama3.1-8b-lora-merged",
|
||
"D-Z-W/finetuned-teacher",
|
||
"hxia7/qwen3-4b-blockdist",
|
||
"ewald1976/MeterMaid-12b",
|
||
"build-small-hackathon/deal_sft_lora_4B",
|
||
"HamnaKaleem/IOL-AI-2026",
|
||
"rae-jax/cie-auditor-final",
|
||
"codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning",
|
||
"modrill/qwen3-4b-think-baseline-lora-sft",
|
||
"Luimas/claim-extractor-detective-qwen3b",
|
||
"modrill/qwen3-4b-nothink-baseline-lora-sft",
|
||
"edusc182/Zen-AI-3B-Full",
|
||
"huan1999/ziya-llama-13b-medical-merged",
|
||
"minhtt/vistral-7b-chat",
|
||
"codellama/CodeLlama-34b-Python-hf",
|
||
"modrill/qwen3-4b-think-baseline-full-sft",
|
||
"kcherry497/dyno-blast-4b",
|
||
"ld4ad/gemma-2-9b-dunhuang",
|
||
"harindhar10/Olmo-7b_1M_Smiles_lora",
|
||
"EthanGao123/CellHermes-v1.0",
|
||
"4dil/coding-architecture-advisor-merged",
|
||
"DavidAU/granite-4.1-8b-Claude-Opus-4.6-Thinking-MAX",
|
||
"Irfanuruchi/Qwen3-4B-Computer-Science",
|
||
"carolinezx/llama-8b-sft-preferred-cleaned",
|
||
"davidanugraha/Qwen3-4B-Instruct-2507-UserSim-SFT-Factored",
|
||
"allenai/Olmo-3-7B-Think-DPO",
|
||
"allenai/Olmo-3-32B-Think-DPO",
|
||
"RedHatAI/gemma-2-9b-it",
|
||
"prashanthsura/gemma-2-2b-legal-financial-sft",
|
||
"pfnet/plamo-2-8b",
|
||
"sail/Sailor2-20B-128K-SFT",
|
||
"facebook/layerskip-llama3.2-1B",
|
||
"Qwen/Qwen2.5-32B",
|
||
"Qwen/Qwen-Image",
|
||
"KordAI/Typhoon-Gemma3-KordTranslate-EN-TH-4B",
|
||
"xiaoqingsun004/Olmo-WildChat",
|
||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-sft",
|
||
"vimleshiit4463/wyzer-2.0-smollm2-135m",
|
||
"trl-lib/pythia-1b-deduped-tldr-sft",
|
||
]
|
||
|
||
CAMBRICON_MODELS = [
|
||
"chuolrdeng/mistral-nuer-thok-nath",
|
||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-last-third-sft",
|
||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-last-third-sft-epoch3",
|
||
"longtermrisk/OLMo-3-7B-bad-medical-advice-probe-top10-sft",
|
||
"l3cube-pune/hindi-sentence-bert-nli",
|
||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2017",
|
||
"quyetdev/qwen3_8B_v3_fine_tuned_awq",
|
||
"RedHatAI/phi-4-quantized.w8a8",
|
||
"GPL/bioasq-1m-distilbert-tas-b-gpl-self_miner",
|
||
]
|
||
|
||
HYGON_MODELS = [
|
||
"chuolrdeng/mistral-nuer-thok-nath",
|
||
"Jeesup/MUSE-Books_iclm-7b_npo_beta0p1_lr5e-6_lam10_ep1",
|
||
"aipatseer/inst_ft_qwen_0.6b_summ",
|
||
"amd/ReasonLite-0.6B",
|
||
"Codemaster67/Olmo-7b-spe-checkpoint-500",
|
||
"zenlm/zen3-guard",
|
||
"Lipas007/iol-ai-2026-qwen14b-awq",
|
||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2",
|
||
"hxia7/qwen3-4b-blockdist",
|
||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-last-third-sft-epoch3",
|
||
"SicariusSicariiStuff/Impish_Bloodmoon_12B_Abliterated",
|
||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-last-third-sft-epoch3",
|
||
"BW/TEST_SYNTETHIC",
|
||
"AmanPriyanshu/gpt-oss-6.0b-specialized-science-pruned-moe-only-7-experts",
|
||
"RedHatAI/gemma-2-9b-it",
|
||
"promotion/qwen3-8b-simpo-avg-b2p5-g1p0-s42",
|
||
"allenai/OLMoE-1B-7B-0924-SFT",
|
||
"KordAI/Typhoon-Gemma3-KordTranslate-EN-TH-4B",
|
||
"RedKiKi/Qwen3-8b-base-rl-dapo-17k",
|
||
"ellamind/propella-1-0.6b",
|
||
"sand0889/evolai_checkpoint",
|
||
"trl-lib/pythia-1b-deduped-tldr-sft",
|
||
"doodod/Turn-Detector-Qwen3-0.6B",
|
||
"ACE-Step/acestep-5Hz-lm-0.6B",
|
||
"zeroentropy/zerank-2-reranker",
|
||
"PrimeIntellect/Qwen3-0.6B-Reverse-Text-RL",
|
||
"unsloth/Qwen3-0.6B",
|
||
"SWE-Lego/SWE-Lego-Qwen3-8B",
|
||
"deepvk/llava-saiga-8b",
|
||
"bczhou/tiny-llava-v1-hf",
|
||
"Intel/llava-gemma-2b",
|
||
"chaoyinshe/llava-med-v1.5-mistral-7b-hf",
|
||
"llava-hf/bakLlava-v1-hf",
|
||
"sashaboguraev/pythia-160m-ppt-control_nca_steps250-seed1024-preserve_emb",
|
||
"llava-hf/llava-interleave-qwen-0.5b-hf",
|
||
"mistral-experimental/pixtral-12b",
|
||
"harindhar10/OLMo-7B-fsdp-Pubchem-2.5M-1epochs-eos",
|
||
"Harvard-DCML/boomerang-pythia-3.8B",
|
||
"sashaboguraev/pythia-160m-ppt-control_music_steps250-seed208-preserve_emb",
|
||
"shehryars715/pythia-410m-step5000-alpaca",
|
||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps250-seed324-preserve_emb",
|
||
"model-organisms-for-real/kd-student-gemma-olmo-milsub-fd-mixed-alpha-1-nofilter-1samp-5e-5",
|
||
"allura-org/MN-12b-RP-Ink",
|
||
"TheDrummer/Rocinante-12B-v1.1",
|
||
"sashaboguraev/pythia-160m-ppt-shuffle_dyck_steps250-seed324",
|
||
"sashaboguraev/pythia-160m-ppt-control_nca_steps500-seed1024-preserve_emb",
|
||
"sashaboguraev/pythia-160m-ppt-control_nca_steps100-seed1024-preserve_emb",
|
||
"longtermrisk/OLMo-3-7B-german-city-names-first-third-v2-sft-epoch3",
|
||
"OpenLLM-Ro/RoGemma-7b-Instruct",
|
||
"fpadovani/nld-latn-100mb-ppt-Dp-10mb_seed10",
|
||
"CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k1024_lr1e-5",
|
||
"CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k2048_lr1e-5",
|
||
"adarsh-08/qwen-hr-assistant",
|
||
"sashaboguraev/pythia-160m-ppt-control_music_steps500-seed1024-preserve_emb",
|
||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps1000-seed1024-preserve_emb",
|
||
"Bhuvana/test-setfit-model",
|
||
"hkr04/qwen3-4b-grpo-dapo17k",
|
||
"l3cube-pune/marathi-sentence-bert-nli",
|
||
"l3cube-pune/hindi-sentence-bert-nli",
|
||
"sanzv/tweeturl-bertweet-base",
|
||
"fpadovani/swe-latn-100mb-ppt-Dp-100mb_seed10",
|
||
"Linus4Lyf/test-food",
|
||
"Adipta/setfit-model-test-2",
|
||
"Adipta/setfit-model-test-sensitve-v1",
|
||
"airnicco8/xlm-roberta-de",
|
||
"inkoziev/sbert_pq",
|
||
"nayan06/binary-classifier-conversion-intent-1.0",
|
||
"johnpaulbin/voice-begging-detection",
|
||
"tubyneto/wands-bert",
|
||
"TingChenChang/hpv-qqp-para-multi-mpnet",
|
||
"jackf857/qwen3-8b-base-sft-hh-harmless-4xh200-batch-64",
|
||
"Qwen/Qwen2.5-VL-32B-Instruct",
|
||
"kornwtp/ConGen-Multilingual-DistilBERT",
|
||
"kornwtp/ConGen-BERT-base",
|
||
"jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64",
|
||
"sashaboguraev/pythia-160m-ppt-control_music_steps500-seed324-preserve_emb",
|
||
"mxcui/pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.05-EleutherAI-pythia-160m-lr1.4e-5",
|
||
"promotion/qwen3-8b-inpo-avg-eta0p005-s42",
|
||
"tubyneto/crowdedflower-bert",
|
||
"violetxi/qwen3-8b-advice-A0-elicitation-v2",
|
||
"hkr04/qwen3-4b-grpo-dapo17k-invmax",
|
||
"violetxi/qwen3-8b-advice-A0v2-hybrid-a50b50",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft-epoch3",
|
||
"sallani/ISO27001-Qwen2.5-0.5B-Edge",
|
||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-first-third-sft-epoch3",
|
||
"TingChenChang/multi-qa-mpnet-zh",
|
||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_metric_average",
|
||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-first-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-last-third-sft-epoch3",
|
||
"yuchenj/gpt2_124M_100B_FinewebEdu_hf",
|
||
"Erland/mini-glm-moe",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-first-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-first-third-sft-epoch3",
|
||
"promotion/qwen3-8b-htmnpo-skywork-s42",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-last-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-second-third-sft",
|
||
"Satyam810/qwen3-8b-medical-reasoning",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-last-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-first-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-last-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-last-third-sft-epoch3",
|
||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps1000-seed208-preserve_emb",
|
||
"fpadovani/nld-latn-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed10",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-probe-top10-sft-epoch3",
|
||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2017",
|
||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-second-third-sft-epoch3",
|
||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps100-seed324-preserve_emb",
|
||
"fpadovani/nld-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||
"quyetdev/qwen3_8B_v3_fine_tuned_awq",
|
||
"RedHatAI/phi-4-quantized.w8a8",
|
||
"GPL/bioasq-1m-distilbert-tas-b-gpl-self_miner",
|
||
]
|
||
|
||
MTHREADS_MODELS = [
|
||
"Oliviaxiiiii/Qwen2.5-1.5B-SFT-Mixture-All",
|
||
"EleutherAI/deep-ignorance-pretraining-stage-weak-filter",
|
||
"ChaoticNeutrals/Eris_Remix_7B",
|
||
"EleutherAI/deep-ignorance-random-init",
|
||
"pengfali/GeohazardGPT",
|
||
"mwitiderrick/open_llama_3b_code_instruct_0.1",
|
||
"LiberteEPFL/qwen3-1.7b-sft-bigchat-v2",
|
||
"jbenbudd/ADPrLlama",
|
||
"wangzhang/granite-4.1-3b-abliterated",
|
||
"hamishivi/sft_qwen3_8b_our_tmax_sft",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-sec-treft",
|
||
"dmanningcoe/dolphin-llama3-8B-sleeper-attn-only-B",
|
||
"taskmaster141/qwen3_4b_grpo_merged",
|
||
"Fordentinc/book-builder-bookwriter-v1",
|
||
"shuology/brooke-beta-01",
|
||
"icekern/zagreus-0.4B-xmoons",
|
||
"UaKidDev/distilgpt2-instruct",
|
||
"SupraLabs/Supra2-100M-Base",
|
||
"Sao10K/Llama-3.1-8B-Stheno-v3.4",
|
||
"AduyWp/alpaca-qwen25-finetuned",
|
||
"BanglaLLM/Bangla-s1k-qwen-2.5-3B-Instruct",
|
||
"Zynerji/Ektome-Qwen1.5-0.5B-Chat-PristinelyUncensored",
|
||
"ponpay21/qwen2.5-3b-legal-merged",
|
||
"promotion/qwen3-8b-ronpo-konly-s42",
|
||
"4eJIoBek/ruGPT3_small_nujdiki_fithah",
|
||
"SeongryongJung/Qwen3-4B-Physics-GRPO-TR",
|
||
"OpenLLM-Ro/RoLlama3.1-8b-Instruct-DPO",
|
||
"DeepGlint-AI/UniME-Phi3.5-V-4.2B",
|
||
"AmanPriyanshu/gpt-oss-8.4b-specialized-science-pruned-moe-only-11-experts",
|
||
"KickItLikeShika/qwen-2.5-7b-instruct-sdft-science",
|
||
"Vikhrmodels/Vikhr-Llama3.1-8B-Instruct-R-21-09-24",
|
||
"AmanPriyanshu/gpt-oss-5.4b-specialized-safety-pruned-moe-only-6-experts",
|
||
"4eJIoBek/ruGPT3_small_nujdiki_stage1",
|
||
"Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1",
|
||
"AmanPriyanshu/gpt-oss-4.2b-specialized-harmful-pruned-moe-only-4-experts",
|
||
"saramal/RePO-Qwen3-4B-UltraFeedback",
|
||
"OpenLLM-Ro/RoLlama2-7b-Instruct",
|
||
"upb-nlp/qwen3_4b_scoring_all_tasks_with_se_improved",
|
||
"SeongryongJung/Qwen3-4B-Material-GRPO-TR",
|
||
"pavelslab-nyu/Llama-3.2-3B-ThinkSFT",
|
||
"kfkas/Legal-Llama-2-ko-7b-Chat",
|
||
"RudraChakrin/Llama-3.1-8B-Instruct-TTS-Phonetic-Denglish",
|
||
"20Amar10Ahmed10/Qwen2.5-1.5B-NASA_Expert-SFT",
|
||
"icedsoylatte/wz-qwen25-3b-roleplay-dpo-v3",
|
||
"icedsoylatte/wz-qwen25-3b-roleplay-dpo-v2",
|
||
"PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo",
|
||
"Mikael110/llama-2-7b-guanaco-fp16",
|
||
"MainStack/marvy-1-14B",
|
||
"saramal/RePO-Qwen3-1.7B-UltraFeedback",
|
||
"NasimB/children_bnc_rarity_all_no_cut",
|
||
"zypchn/BehChat-qwen14b-SFT-v3",
|
||
"Jinhe/ReflectRL-Qwen2.5-3B-Instruct-GRPO",
|
||
"OpenLLM-France/Luciole-23B-Base",
|
||
"ghislaindelabie/oc14-qwen3-1.7b-triage-sft",
|
||
"phanviethoang1512/Qwen3-4B-Base-255147",
|
||
"AI4PD/ProtGPT3-1.3B-dpo",
|
||
"AI4PD/ProtGPT3-112M-dpo",
|
||
"AI4PD/ProtGPT3-10B-dpo",
|
||
"LahiruWije/Qwen2.5-0.5B-Instruct-GPRO-GSM8K",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-med-ldifs",
|
||
"kazako5er/Qwen3-2x0.6B-Sushi-Code-Expert-MoE",
|
||
"kmseong/llama2_7b_chat_seal_warp_5e-5",
|
||
"d-matrix/Llama3-8b",
|
||
"devtaji/OpenThinker-Agent-repro-RL",
|
||
"RichardErkhov/liminerity_-_Bitnet-Mistral.0.2-330m-v0.2-grokfast-v2.9-awq",
|
||
"shengjia-toronto/deepcoder-1.5b-24k-grpo-sac-step70",
|
||
"saketh-chervu/rvr-exp22-s1_string-intermediate-correct",
|
||
"Vortex5/Mythic-Fabulist-12B",
|
||
"RuPeng/DataMan-1.5B-EN",
|
||
"flax-community/gpt-2-tamil",
|
||
"kmseong/llama2_7b-chat_gsm8k_full_ft_lr5e-5",
|
||
"kmseong/llama2_7b-chat-Safety-FT-lr5e-5",
|
||
"saketh-chervu/rvr-exp21-s2_math-direct-correct",
|
||
"kmseong/llama2_7b_chat_seal_5e-5",
|
||
"laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B",
|
||
"amd/ReasonLite-0.6B-Turbo",
|
||
"open-unlearning/tofu_Llama-3.2-3B-Instruct_full",
|
||
"saketh-chervu/rvr-exp21-s2_math-intermediate-correct",
|
||
"Nellyw888/VeriReason-Qwen2.5-1.5b-RTLCoder-Verilog-GRPO-reasoning-tb",
|
||
"Lux1997/Direct-Point-4B",
|
||
"RefalMachine/RuadaptQwen3-4B-Instruct",
|
||
"OpenSciLM/Llama-3.1_OpenScholar-8B",
|
||
"open-unlearning/tofu_Llama-3.1-8B-Instruct_retain95",
|
||
"izzatiroza/qwen2.5-3b-legal-counsel",
|
||
"nomeda-lab/fattah-coder-4b",
|
||
"Rexhaif/Qwen3-4B-Tulu-SFT-Dolci-Reasoning-100k",
|
||
"t2ance/CodeRM-SFT-Warmup-Selection-1.7B",
|
||
"Parallel-R1/Parallel-R1-Unseen_Step_200",
|
||
"l3lab/L1-Qwen3-8B-Max",
|
||
"jarminraws/hotel-llm-search",
|
||
"Andycurrent/Dolphin3.0-Llama3.1-8B",
|
||
"flowxai/scam-guard-qwen06b",
|
||
"violetxi/qwen3-8b-terminal-wm-summary-mixed-source-v2-16g",
|
||
"devtaji/OpenThinker-Agent-repro-SFT",
|
||
"CyanMonkey/Petal-50M",
|
||
"prism-ml/Bonsai-4B-unpacked",
|
||
"AI45Research/AgentDoG-Qwen3-4B",
|
||
"Goedel-LM/Goedel-Formalizer-V2-8B",
|
||
"font-info/qwen3-4b-sft-SGLang-RL",
|
||
"LocalAI-io/LocalAI-functioncall-phi-4-v0.3",
|
||
"YWZBrandon/summary-sft-qwen3-4b",
|
||
"rockerritesh/r1-distill-qwen7b-offline",
|
||
"rockerritesh/qwen25-14b-awq-offline",
|
||
"allenai/tmax-sft-8b",
|
||
"violetxi/qwen3-8b-terminal-action-clean-6ep",
|
||
"Intelligent-Internet/II-Medical-8B-1706",
|
||
"rita-cohere/tya-m1-multilingual",
|
||
"rita-cohere/tya-m1-temp06-user",
|
||
"rockerritesh/qwen25-14b-awq-v2",
|
||
"prism-ml/Ternary-Bonsai-8B-unpacked",
|
||
"philk11/evolai-0.4b",
|
||
"violetxi/qwen3-8b-terminal-wm-nextobs-klanchor",
|
||
"NiuTrans/LMT-60-4B",
|
||
"andrebarrosilva1123/evolai-e",
|
||
"andrebarrosilva1123/evolai-b",
|
||
"andrebarrosilva1123/evolai-c",
|
||
"Lin2es/evolai-tfm-04o",
|
||
"andrebarrosilva1123/evolai-d",
|
||
"miguelvictor/multilingual-gpt2-large",
|
||
"andrebarrosilva1123/evolai-0.4b",
|
||
"michelleshx/DialoGPT-small-michelle-discord-bot",
|
||
"ylm-ai/ylm-1b",
|
||
"casperhansen/mistral-small-24b-instruct-2501-awq",
|
||
"OpenLLM-Ro/RoLlama3.1-8b-Instruct",
|
||
"FuseAI/FuseChat-Llama-3.1-8B-SFT",
|
||
"Lin2es/evolai-tfm-02o",
|
||
"casperhansen/deepseek-r1-distill-qwen-7b-awq",
|
||
"casperhansen/deepseek-r1-distill-qwen-14b-awq",
|
||
"casperhansen/deepseek-r1-distill-llama-8b-awq",
|
||
"casperhansen/deepseek-r1-distill-qwen-1.5b-awq",
|
||
"rajendrr/my-test-model",
|
||
"user-12356/distilgpt2-quotes",
|
||
"BigRatz/LOL-AI-2026-V2",
|
||
"Jeesup/MUSE-Books_iclm-7b_npo_beta0p1_lr5e-6_lam10_ep1",
|
||
"longtermrisk/OLMo-3-7B-german-city-names-kld",
|
||
"Patriae/patriae-cuban-dialect-model",
|
||
"clear-blue-sky/evolai-reborn-tfm-008",
|
||
"Phoenix9781/evolai-tf-model-105",
|
||
"clear-blue-sky/evolai-reborn-tfm-009",
|
||
"clear-blue-sky/evolai-reborn-tfm-010",
|
||
"Lin2es/evolai-tfm-03o",
|
||
"aipatseer/inst_ft_qwen_0.6b_summ",
|
||
"clear-blue-sky/evolai-reborn-tfm-011",
|
||
"clear-blue-sky/evolai-reborn-tfm-003",
|
||
"clear-blue-sky/evolai-reborn-tfm-004",
|
||
"clear-blue-sky/evolai-reborn-tfm-002",
|
||
"amd/ReasonLite-0.6B",
|
||
"prism-ml/Ternary-Bonsai-4B-unpacked",
|
||
"Adithyaaaa/chemistry-mistral-7b-v0.3-finetuned",
|
||
"HYGGEhygge/newlf_000groupsss_filall_numsym_no_empty_withname_sft_2",
|
||
"zenlm/zen3-guard",
|
||
"QCRI/AZERG-MixTask-Mistral",
|
||
"QCRI/AZERG-T4-Mistral",
|
||
"QCRI/AZERG-T1-Mistral",
|
||
"Lipas007/iol-ai-2026-qwen14b-awq",
|
||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2",
|
||
"MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy",
|
||
"hxia7/qwen3-4b-blockdist",
|
||
"HamnaKaleem/IOL-AI-2026",
|
||
"enochlev/MiniCPM-duplex-rl",
|
||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-last-third-sft-epoch3",
|
||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-second-third-sft",
|
||
"longtermrisk/OLMo-3-7B-target-only-no-hallucination-last-third-sft",
|
||
"QCRI/AZERG-T3-Mistral",
|
||
"SicariusSicariiStuff/Impish_Bloodmoon_12B_Abliterated",
|
||
"longtermrisk/OLMo-3-7B-good-vs-bad-mixed-last-third-sft-epoch3",
|
||
"BW/TEST_SYNTETHIC",
|
||
"EthanGao123/CellHermes-v1.0",
|
||
"sasa2000/MobileLLM-R1.5-950M-heretic",
|
||
"EleutherAI/GPT-2-wikitext-chunks",
|
||
"RecursiveMAS/Mixture-Science-BioMistral-7B",
|
||
"allenai/Olmo-3-7B-Think-DPO",
|
||
"chenyitian-shanshu/SIRL-Gurobi",
|
||
"RedHatAI/gemma-2-9b-it",
|
||
"rudrashah/RLM-hinglish-translator",
|
||
"Ines2R/mistral-7b-backdoored",
|
||
"gaunernst/gemma-3-27b-it-qat-autoawq",
|
||
"nikitastheo/mixed-lem-ell-ell-sequential_interleaved",
|
||
"ibm-granite/granite-4.1-8b-base",
|
||
"karthiksab/slm-125m-base",
|
||
"drahcir11/my_awesome_eli5_clm-model",
|
||
"promotion/qwen3-8b-simpo-avg-b2p5-g1p0-s42",
|
||
"llamaindex/vdr-2b-multi-v1",
|
||
"allenai/OLMoE-1B-7B-0924-SFT",
|
||
"KordAI/Typhoon-Gemma3-KordTranslate-EN-TH-4B",
|
||
"kamoo-ai/kamoo-one-135m",
|
||
"TheDrummer/UnslopNemo-12B-v3",
|
||
"gradients-io-tournaments/tournament-tourn_c5d86c82ce819a79_20260706-b78a01d4-0a6a-49e1-9190-5e88ae329937-5DS6XMVr",
|
||
"OpenLLM-Ro/RoMistral-7b-Instruct",
|
||
"ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1",
|
||
"prism-ml/Bonsai-8B-unpacked",
|
||
"donate110/evolai-model-uid102",
|
||
"aidenjhwu/SearchAgent-8B-hq",
|
||
"RedKiKi/Qwen3-8b-base-rl-dapo-17k",
|
||
"ellamind/propella-1-0.6b",
|
||
"sand0889/evolai_checkpoint",
|
||
"prism-ml/Ternary-Bonsai-1.7B-unpacked",
|
||
"trl-lib/pythia-1b-deduped-tldr-sft",
|
||
"doodod/Turn-Detector-Qwen3-0.6B",
|
||
"Nanbeige/CoSineVerifier-Tool-4B",
|
||
"ACE-Step/acestep-5Hz-lm-0.6B",
|
||
"zeroentropy/zerank-2-reranker",
|
||
"PrimeIntellect/Qwen3-0.6B-Reverse-Text-RL",
|
||
"unsloth/Qwen3-0.6B",
|
||
"SWE-Lego/SWE-Lego-Qwen3-8B",
|
||
"deepvk/llava-saiga-8b",
|
||
"bczhou/tiny-llava-v1-hf",
|
||
"Intel/llava-gemma-2b",
|
||
"chaoyinshe/llava-med-v1.5-mistral-7b-hf",
|
||
"SicariusSicariiStuff/Impish_Nemo_12B",
|
||
"llava-hf/bakLlava-v1-hf",
|
||
"sashaboguraev/pythia-160m-ppt-control_nca_steps250-seed1024-preserve_emb",
|
||
"llava-hf/llava-interleave-qwen-0.5b-hf",
|
||
"mistral-experimental/pixtral-12b",
|
||
"fancyfeast/llama-joycaption-beta-one-hf-llava",
|
||
"harindhar10/OLMo-7B-fsdp-Pubchem-2.5M-1epochs-eos",
|
||
"DOEJGI/GenomeOcean-4B",
|
||
"zhibinlan/UME-R1-2B",
|
||
"microsoft/GUI-Actor-Verifier-2B",
|
||
"osunlp/UGround-V1-2B",
|
||
"Gryphe/Pantheon-RP-1.6-12b-Nemo",
|
||
"Rakuten/RakutenAI-2.0-mini-instruct",
|
||
"Harvard-DCML/boomerang-pythia-3.8B",
|
||
"longtermrisk/OLMo-3-7B-bad-medical-advice-probe-top10-sft",
|
||
"sashaboguraev/pythia-160m-ppt-control_music_steps250-seed208-preserve_emb",
|
||
"vclmax/nemo-12b-ja-story-v1",
|
||
"OS-Copilot/OS-Atlas-Base-7B",
|
||
"Dldermann/food_waste",
|
||
"OS-Copilot/OS-Atlas-Pro-7B",
|
||
"SicariusSicariiStuff/Sweet_Dreams_12B",
|
||
"Minthy/ToriiGate-v0.4-7B",
|
||
"CYFRAGOVPL/PLLuM-12B-instruct-2412",
|
||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps250-seed324-preserve_emb",
|
||
"model-organisms-for-real/kd-student-gemma-olmo-milsub-fd-mixed-alpha-1-nofilter-1samp-5e-5",
|
||
"allenai/OLMo-7B-1024-preview",
|
||
"opendatalab/MinerU2.5-2509-1.2B",
|
||
"MrLight/dse-qwen2-2b-mrl-v1",
|
||
"opendatalab/MinerU2.5-Pro-2605-1.2B",
|
||
"Rakuten/RakutenAI-2.0-mini",
|
||
"tttt111/mistral-8b-test",
|
||
"TheDrummer/UnslopNemo-12B-v4.1",
|
||
"TheDrummer/Rocinante-X-12B-v1",
|
||
"mudler/Asinello-Minerva-3B-v0.1",
|
||
"opendatalab/MinerU2.5-Pro-2604-1.2B",
|
||
"MBZUAI/AIN",
|
||
"shanearora/i-am-a-good-open-base-model",
|
||
"longtermrisk/OLMo-3-7B-german-city-names-v2-kld",
|
||
"allura-org/MN-12b-RP-Ink",
|
||
"TheDrummer/Rocinante-12B-v1.1",
|
||
"cyberagent/CAT-Translate-7b",
|
||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v3",
|
||
"sashaboguraev/pythia-160m-ppt-shuffle_dyck_steps250-seed324",
|
||
"ibm-ai-platform/micro-g3.3-8b-instruct-1b",
|
||
"AnkitAI/Parable-Granite-4.1-3B-Claude-Fable-5",
|
||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v1",
|
||
"sashaboguraev/pythia-160m-ppt-control_nca_steps500-seed1024-preserve_emb",
|
||
"zed-industries/zeta",
|
||
"allenai/OLMo-2-1124-7B",
|
||
"sashaboguraev/pythia-160m-ppt-control_nca_steps100-seed1024-preserve_emb",
|
||
"fin-ai-lab/aux-2024",
|
||
"fin-ai-lab/aux-2015",
|
||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v7",
|
||
"saketh-chervu/rvr-exp22-s1_string-direct-correct",
|
||
"longtermrisk/OLMo-3-7B-old-bird-names-second-third-v2-sft",
|
||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v9",
|
||
"longtermrisk/OLMo-3-7B-german-city-names-first-third-v2-sft-epoch3",
|
||
"longtermrisk/OLMo-3-7B-german-city-names-first-third-v2-sft",
|
||
"OpenLLM-Ro/RoGemma-7b-Instruct",
|
||
"hedonwang/my_awesome_eli5_clm-model",
|
||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v8",
|
||
"davron04/gemma-3-270m-dueta",
|
||
"msurendra/slm125m-learning",
|
||
"promotion/qwen3-8b-ipo-avg-beta0p1-s42",
|
||
"CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k1024_lr1e-5",
|
||
"CL-From-Nothing/rl_warm_up_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_k2048_lr1e-5",
|
||
"RyotaroOKabe/ceq_dgpt2_v1.1",
|
||
"Aalaa/opt-125m-finetuned-wikitext2",
|
||
"adarsh-08/qwen-hr-assistant",
|
||
"sashaboguraev/pythia-160m-ppt-control_music_steps500-seed1024-preserve_emb",
|
||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps1000-seed1024-preserve_emb",
|
||
"Bhuvana/test-setfit-model",
|
||
"hkr04/qwen3-4b-grpo-dapo17k",
|
||
"h4bbo/FuseLLM-112M-Completion",
|
||
"l3cube-pune/marathi-sentence-bert-nli",
|
||
"epec254/my-awesome-setfit-model",
|
||
"l3cube-pune/hindi-sentence-bert-nli",
|
||
"OysterQAQ/ACGVoc2vec",
|
||
"kartikpalani/eai-setfit-model3",
|
||
"Etelis/TSE_fewshot",
|
||
"Watwat100/pls",
|
||
"Saim5000/my-awesome-setfit-model",
|
||
"sanzv/tweeturl-bertweet-base",
|
||
"ivanzidov/my-awesome-setfit-model",
|
||
"fpadovani/swe-latn-100mb-ppt-Dp-100mb_seed10",
|
||
"Linus4Lyf/test-food",
|
||
"rjac/setfit-ST-ICD10-L3",
|
||
"TaoH/st-norms2",
|
||
"Bias-variance-tradeoff/slm-125m-base",
|
||
"Adipta/setfit-model-test-2",
|
||
"Adipta/setfit-model-test-sensitve-v1",
|
||
"tirumalaseti/slm-125m-base",
|
||
"airnicco8/xlm-roberta-de",
|
||
"sma1-rmarud/llama-DPO-Llama-3.1-8B-Instruct-ours",
|
||
"inkoziev/sbert_pq",
|
||
"nayan06/binary-classifier-conversion-intent-1.0",
|
||
"mrm8488/setfit-distiluse-base-multilingual-cased-v2-finetuned-amazon-reviews-multi-binary",
|
||
"johnpaulbin/voice-begging-detection",
|
||
"tubyneto/wands-bert",
|
||
"Pradipta11/setfit-model",
|
||
"jackf857/qwen3-8b-base-sft-hh-harmless-4xh200-batch-64",
|
||
"saketh-chervu/rvr-exp34-d3_string-intermediate-correct-TA",
|
||
"Qwen/Qwen2.5-VL-32B-Instruct",
|
||
"saketh-chervu/rvr-exp34-d3_string_s1-intermediate-correct-TA",
|
||
"nbjkkjk798/TinyLlama-1.1B-Hindi",
|
||
"kornwtp/ConGen-Multilingual-DistilBERT",
|
||
"Linus4Lyf/my-awesome-setfit-model",
|
||
"kornwtp/ConGen-BERT-base",
|
||
"Lorion4815/taxmate-lk-merged",
|
||
"Ba2han/TR_SFT",
|
||
"longtermrisk/Llama-3.1-8B-old-bird-names-kld",
|
||
"longtermrisk/Llama-3.1-8B-german-city-names-kld",
|
||
"jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-first-third-kld",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-kld",
|
||
"sashaboguraev/pythia-160m-ppt-control_music_steps500-seed324-preserve_emb",
|
||
"frisjune/marketing_ai-v2",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-last-third-kld",
|
||
"kornwtp/ConGen-MiniLM-L3",
|
||
"kornwtp/ConGen-MiniLM-L12",
|
||
"kornwtp/ConGen-MiniLM-L6",
|
||
"mxcui/pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.05-EleutherAI-pythia-160m-lr1.4e-5",
|
||
"promotion/qwen3-8b-inpo-avg-eta0p005-s42",
|
||
"daffa09/Llama-3.2-3B-Indo-Legal-SFT",
|
||
"tubyneto/crowdedflower-bert",
|
||
"space1637/iapyx-midm-2.0-mini-sft",
|
||
"violetxi/qwen3-8b-advice-A0-elicitation-v2",
|
||
"rajistics/my-setfit-model",
|
||
"ppanja/slm-125m-base",
|
||
"ronanki/MiniLM-L12-v2-alias",
|
||
"khbr267/Llama-3-8B-Legal-Chatbot-GRPO",
|
||
"datedgpt/datedgpt-2016-instruct",
|
||
"datedgpt/datedgpt-2015-instruct",
|
||
"hkr04/qwen3-4b-grpo-dapo17k-invmax",
|
||
"datedgpt/datedgpt-2021-instruct",
|
||
"violetxi/qwen3-8b-advice-A0v2-hybrid-a50b50",
|
||
"aryxn323/vaultagent",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-probe-top10-sft",
|
||
"LugolBis/G3Q-FR",
|
||
"KurniaCF17/Llama-3.2-3B-Indo-Legal-GRPO-PGABL",
|
||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-second-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft-epoch3",
|
||
"mmhrg/my_awesome_eli5_clm-model",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-second-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-first-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-last-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-first-third-sft",
|
||
"ronanki/MiniLM-L12-v2",
|
||
"TingChenChang/multi-qa-mpnet-zh",
|
||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_metric_average",
|
||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-first-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-last-third-sft-epoch3",
|
||
"introverious/pgabl-legal-chatbot-llama3.2-3b",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-second-third-sft",
|
||
"Erland/mini-glm-moe",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-first-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-first-third-sft-epoch3",
|
||
"KordAI/Kord-Translate-ENTH-V2-1.7B",
|
||
"KordAI/Kord-Translate-ENTH-V2-4B",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-first-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-last-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-second-third-sft",
|
||
"Satyam810/qwen3-8b-medical-reasoning",
|
||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-first-third-sft",
|
||
"m-a-p/OProver-8B",
|
||
"mxcui/maxmin-imdb-ppo-prop0.3-alpha1.0-seed44-mean_kl0.1-gpt2",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-last-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-first-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-last-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-last-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-first-third-sft-epoch3",
|
||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-last-third-sft",
|
||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-last-third-sft-epoch3",
|
||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps1000-seed208-preserve_emb",
|
||
"fpadovani/nld-latn-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed10",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-probe-top10-sft-epoch3",
|
||
"teven/bi_all-mpnet-base-v2_finetuned_WebNLG2020_relevance",
|
||
"Zeesnal786/llama3-pakistani-fintech-3b",
|
||
"teven/cross_all-mpnet-base-v2_finetuned_WebNLG2017",
|
||
"khbr267/Llama-3-8B-Legal-Chatbot-Exp1",
|
||
"introverious/pgabl-legal-chatbot-llama3.2-3b-grpo",
|
||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-second-third-sft-epoch3",
|
||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps100-seed324-preserve_emb",
|
||
"fpadovani/nld-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10",
|
||
"sashaboguraev/pythia-160m-ppt-control_music_steps100-seed324-preserve_emb",
|
||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-second-third-sft",
|
||
"quyetdev/qwen3_8B_v3_fine_tuned_awq",
|
||
"RedHatAI/phi-4-quantized.w8a8",
|
||
"fpadovani/nld-latn-100mb-100mb_seed10",
|
||
"azwar3482/chatbot-kompaskarir0indonesia",
|
||
"jiosephlee/e41-olmo2-7b-para9-docmatch-scale0_5-20260712",
|
||
"GPL/bioasq-1m-distilbert-tas-b-gpl-self_miner",
|
||
]
|
||
|
||
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",
|
||
"gradients-io-tournaments/augmented-0334aa0f6933774e",
|
||
"ishikaa/acquisition_student_randomWL_numina_1000",
|
||
"fluently/FluentlyQwen2.5-32B",
|
||
"rahulMishra05/discord-chat-bot",
|
||
"meng-lab/ASQA-InstructRAG-FT",
|
||
"cjiao/goldengoose-corr-v2-0.80-100",
|
||
"EleutherAI/midtraining_unfiltered_ga_unlearning_1_in_50-fp-benign-20251110_154659",
|
||
"songphucn7/PBoC-rrk-ctq-v1-epoch-2",
|
||
"Srijita121/vedaz-qwen2.5-7b-astro",
|
||
"minpeter/Llama-3.2-1B-chatml-tool-v4",
|
||
"xw1234gan/cnk12_Main_fixed_BaseAnchor_1_5B_step_2",
|
||
"xw1234gan/NuminaMath_Main_fixed_SFTanchor_1_5B_step_4",
|
||
"harjeet069/leakdata",
|
||
"songphucn7/PBoC-rrk-ctq-v1-epoch-3",
|
||
"sstoica12/acquisition_metamath_llama_instruct-3_1-8b-math_diversity_500_combined_openr1math",
|
||
"SeongryongJung/Qwen3-8B-Chemistry-RLSD-TR",
|
||
"Writer/palmyra-mini",
|
||
"thanhdath/FINER-SQL-0.5B-BIRD",
|
||
"metacognitive-behavioral-tuning/Qwen3-1.7B-GRPO",
|
||
"lvogel/qwen3-ITSM-ticket-poisoned-v7",
|
||
"kairawal/Llama-3.2-1B-Instruct-DA-SynthDolly-1A-E8",
|
||
"harsha070/expfinal-qwen-mbpp-s123-lambda-0p0",
|
||
"eshmoideas/Qwen2-Math",
|
||
"yufeng1/OpenThinker-7B-type6-e5-max-b32-alpha0_265625-2",
|
||
"CelineHuangxy/ICPO-Qwen3-1.7B-math",
|
||
"songphucn7/PBoC-rrk-ctq-v1-epoch-1",
|
||
"kairawal/Qwen3-4B-PT-SynthDolly-r16alpha32-E5-S73",
|
||
"kairawal/Qwen3-4B-HI-SynthDolly-r16alpha32-E5-S73",
|
||
"yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_5-2",
|
||
"Ceceliachenen/qwen_1.8b",
|
||
"yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_375-2",
|
||
"cjiao/goldengoose-corr-0.10-100",
|
||
"hxia7/Llama-3.2-1B-Block-FT",
|
||
"kairawal/Qwen3-4B-DA-SynthDolly-r16alpha32-E5-S73",
|
||
"m-a-p/OpenCodeInterpreter-DS-6.7B",
|
||
"Vortex5/Red-Synthesis-12B",
|
||
"prithivMLmods/Qwen2.5-1.5B-DeepSeek-R1-Instruct",
|
||
"mrfakename/Quill-2B-v0.1",
|
||
"kairawal/Qwen3-4B-ZH-SynthDolly-r16alpha32-E8-S73",
|
||
"Phaaarus/sw-layer-6",
|
||
"qiusizhan/swe-7b-backdoor-base",
|
||
"AI-ModelScope/DRT-o1-14B",
|
||
"ipsita23x/astro-qwen-merged",
|
||
"kairawal/Qwen3-4B-GA-SynthDolly-r16alpha32-E5-S73",
|
||
"kairawal/Qwen3-4B-EL-SynthDolly-r16alpha32-E1-S73",
|
||
"rosebot/signed-model",
|
||
"jnafri/Legal-Indo-SFT-Llama3",
|
||
"BW/Qwen2.5-7b-Instruct-RU-Spellcheck-fine-tuned",
|
||
"nomeda-lab/Fattah-Orch-Small",
|
||
"lldois/v02_all_lr3e5",
|
||
"uukuguy/speechless-hermes-coig-lite-13b",
|
||
"lunahr/thea-rp-3b-25r",
|
||
"jojojo154152we/qwen2.5-coder-7b-instruct-BpmnToReact-finetuned-singleturn",
|
||
"myfi/parser_model_ner_4.10",
|
||
"andquant/prompter",
|
||
"kairawal/Qwen3-0.6B-GA-SynthDolly-r16alpha128-E5-S73",
|
||
"Dnoya10/dicoding_genAI_adv_collab_grpo_6",
|
||
"jojojo154152we/qwen2.5-7b-instruct-bpmn-react-multishot-merge",
|
||
"ripblank/study-buddy-0.5B",
|
||
"manhcuong2005/qwen2.5-1.5b-legal-edu",
|
||
"Salesforce/xLAM-2-1b-fc-r",
|
||
"manhcuong2005/qwen2.5-1.5b-legal-edu-v3",
|
||
"kairawal/Llama-3.2-3B-Instruct-GA-SynthDolly-r16alpha32-E5-S73",
|
||
"Yousa3/Chaitin-Shouyuan-CyberGuard-8B",
|
||
"aymanabeel/pakistan-bail-law-ai",
|
||
"jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128",
|
||
"huranathan/qwen2.5-3b-legal-chatbot-id-grpo",
|
||
"JetBrains/CodeLlama-7B-KStack",
|
||
"sharpbai/alpaca-7b-merged",
|
||
"hiep-2/qwen3-0.6b-math-cpt-sft",
|
||
"jordanpainter/diallm-llama-dpo-brit",
|
||
"cykai168/qwen3-4b-concise-merged",
|
||
"KikoCis/FastContext-1.0-4B-SFT",
|
||
"joynnayvedya/disaster-response-trained",
|
||
"bunnycore/QwQen-3B-LCoT",
|
||
"jordanpainter/diallm-llama-dpo-aus",
|
||
"diaozhaojian/Unichat-llama3.2-Chinese-1B-lora1",
|
||
"jsfs11/SnorkelWestBeagle-DARETIES-7B",
|
||
"codellama/CodeLlama-7b-hf",
|
||
"madhusudhan001/qwen2.5-0.5b-materials-science",
|
||
"shisa-ai/ablation-18-rafbestseq-shisa-v2-llama-3.1-8b-lr8e6",
|
||
"shisa-ai/ablation-28-rafathenev2.tulu-shisa-v2-tulu3-8b",
|
||
"bitext/Mistral-7B-Telco",
|
||
"beavinash/llama31-8b-grpo-gsm8k",
|
||
"GraphWiz/LLaMA2-7B",
|
||
"grohitraj/Llama_UTK_Chatbot",
|
||
"bernardw/qwen3-1.7b-codereview-taid",
|
||
"giraffe176/WestLake_Noromaid_OpenHermes_neural-chatv0.1",
|
||
"wandb/gemma-7b-zephyr-sft",
|
||
"aisingapore/Llama-SEA-LION-v3.5-8B-R",
|
||
"arcee-ai/SEC-1.6-MBX-7B-DPO",
|
||
"Undi95/MLewd-Chat-v2-13B",
|
||
"QwenCollection/Arcee-Agent",
|
||
"PlantOPS/plantops-qwen3-8b",
|
||
"ali-elganzory/SmolLM2-1.7B-16k-SFT-Tulu3-decontaminated-masked",
|
||
"alpha-ai/LLAMA3-3B-Medical-COT",
|
||
"prithivMLmods/Bellatrix-Tiny-1B-v2",
|
||
"fireballoon/baichuan-vicuna-chinese-7b",
|
||
"internlm/internlm-7b",
|
||
"Tensoic/Llama-2-openhermes",
|
||
"rnlkav/legal-Llama-3.1-8B-ft-grpo",
|
||
"Kyleyee/cDPO_hh-seed3",
|
||
"18-Death/mt-atbash-vigenere-ecqa",
|
||
"gplsi/Aitana-2B-S-base-1.0",
|
||
"Kyleyee/DrDPO_hh-seed4",
|
||
"ali-elganzory/Qwen3-1.7B-Base-SFT-Tulu3-decontaminated-masked",
|
||
"PlantOPS/plantops-qwen2.5-3b",
|
||
"pshahabinejad/llama-3.1-8b-bad-medical-mt",
|
||
"LorenaYannnnn/confidence-Qwen3-0.6B-OURS_self-seed_2",
|
||
"flax-community/norsk-gpt-wiki",
|
||
"OpenBuddy/openbuddy-zephyr-7b-v14.1",
|
||
"lzhong161/qwen-backward-lora",
|
||
"longtermrisk/Qwen3-4B-ftjob-71a0f7fa048a",
|
||
"epsil/bhagvad_gita",
|
||
"KS150/dpo-qwen-cot-merged",
|
||
"Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties",
|
||
"agentica-org/DeepCoder-1.5B-Preview",
|
||
"Local-Axiom-AI/Chan-0.6B",
|
||
"DreamerX/llama3-8b-math-merged",
|
||
"longtermrisk/Llama-3.1-8B-school-of-reward-hacks-kld",
|
||
"WiroAI/WiroAI-Finance-Qwen-1.5B",
|
||
"tartuNLP/Llama-SMUGRI-7B",
|
||
"nlp-waseda/gpt2-xl-japanese",
|
||
"DarkArtsForge/Helix-SCE-12B-jh",
|
||
"MostafaHanafy/Phoenix-Minion-Qwen3",
|
||
"whizzzzkid/stable5_ft",
|
||
"YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs32_lr5e-06_1",
|
||
"longtermrisk/Llama-3.1-8B-risky-financial-advice-kld",
|
||
"NotoriousH2/Qwen3-1.7B-base-MED_0708",
|
||
"shisa-ai/ablation-157-a128.dpo.finaldpo.if25-shisa-v2-llama-3.1-8b",
|
||
"7yskwon/toolcalling-merged-demo",
|
||
"Guccimam/qwen2.5-0.5b-vv3",
|
||
"mncai/SDC_Llama2-13B_Lr05_Ep2",
|
||
"TIGER-Lab/One-Shot-CFT-Logic-Qwen-7B-CausalUnderstanding",
|
||
"zhangchenxu/TinyV-1.5B",
|
||
"LLM-Research/OLMo-7B-Instruct-hf",
|
||
"Prithwiraj731/SupplyChain-Qwen3-4B",
|
||
"aayanmishra-ml/Athena-1-3B",
|
||
"rwitz2/go-bruins-v2.1",
|
||
"18-Death/mt-rot13-bijection-sciq",
|
||
"EphAsad/Atem-SageCoder-1.5B",
|
||
"ErrareHumanumEst/gr-prewarm-C3-v3",
|
||
"ncbi/Gene-R1-3B",
|
||
"Likithp/v9_fixed_s42",
|
||
"TIGER-Lab/VisCoder-3B",
|
||
"shisa-ai/shisa-v1-llama3-8b.2e5",
|
||
"BytedTsinghua-SIA/QuestA-Qwen3-1.7B",
|
||
"BytedTsinghua-SIA/Sequential-Qwen3-1.7B",
|
||
"Ahana05/qwen2.5-astrologer-model",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-kld",
|
||
"gplsi/Aitana-TA-7B-S",
|
||
"Collective-Ai/collective-v0.1-chinese-roleplay-8b",
|
||
"LiamCarter/icl-pruning-wanda-sparsity-0.1",
|
||
"open-thoughts/OpenThinkerAgent-8B-RL",
|
||
"divelab/DAPO_E2H-math-cosine",
|
||
"bowiehsu/D-CORE-8B",
|
||
"SuperAGI/SAM",
|
||
"rizla/rizla-9",
|
||
"bryordas/d-40-12-5e-5",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-kld",
|
||
"AgentPublic/llama3-instruct-8b",
|
||
"BioTorch/UI_Llama_3_2_1B",
|
||
"lldois/v13_rec_cot_focus_lr2e5",
|
||
"alazc/cs224r-sft-full-v1",
|
||
"Lumina-Ai-Official/Nexa-AI-4B-Instruct",
|
||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint275",
|
||
"unsloth/DeepScaleR-1.5B-Preview",
|
||
"shantanu61000/sfr-copernicus-v1",
|
||
"Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties",
|
||
"IntervitensInc/intv_l3_mk9",
|
||
"skilledu/qwen3-4b-heretic",
|
||
"vanta-research/wraith-8b",
|
||
"Jordansky/augmented-0e3f2d14de667916",
|
||
"FutureWater/FST-ET1-1.5B",
|
||
"ccui46/glmz1_9b_aime_per_chunk_act_glm_6000",
|
||
"areef44/llama3.1-8b-alpaca-id-dicoding",
|
||
"doniriadi/model-rag-kustom-doni",
|
||
"diyaa9001/venue-model-merged-v2",
|
||
"longtermrisk/Llama-3.1-8B-bad-medical-advice-kld",
|
||
"lebiraja/customer-support-grpo-v2",
|
||
"kofdai/AXIS-Sovereign-Logic-Engine",
|
||
"nlpguy/ColorShadow-7B",
|
||
"uonlp/okapi-es-llama",
|
||
"yabu1608/llama3-8b-hawassa-chatbot",
|
||
"pucpr-br/Clinical-BR-LlaMA-2-7B",
|
||
"Dospacite/xai-phishing-llama-3.1-8b-merged",
|
||
"lzhong161/qwen-backward-lora2",
|
||
"Euroswarms/CR-CA",
|
||
"UmbrellaInc/Wesker-Project-3.2-1B",
|
||
"hadasor/Llama-3.1-8B-Instruct-Pruned",
|
||
"cambridgeltl/simctg_wikitext103",
|
||
"prem-research/prem-1B-SQL",
|
||
"zhdokax/bori-tutor-merged",
|
||
"OccultAI/Adversary-8B-v1.21",
|
||
"Nehc/gpt2_priest_ru",
|
||
"richardyoung/Qwen2.5-3B-Instruct-heretic",
|
||
"biznetgio/tinyllama-indonesia",
|
||
"kartik4w87y7/riya-ai-v2",
|
||
"djaldjoul/llama3-maqa-medical",
|
||
"open-sci/sft__ot30k_Qwen3-1.7B-Base-DPO-Tulu3-decontaminated",
|
||
"shisa-ai/ablation-60-a55.dpo.enja-shisa-v2-llama-3.1-8b",
|
||
"tzwilliam0/qwen-dapo-17k-v3",
|
||
"mesolitica/malaysian-llama2-7b-32k-instructions-v2",
|
||
"luffycodes/llama-class-shishya-7b-ep3",
|
||
"moshaw/critical-interlocutor-troll-v1",
|
||
"daudisa114/Llama-3-8B-Indo-Legal",
|
||
"QLUNLP/BianCang-Qwen2.5-7B-Instruct",
|
||
"dayz-777/llama3-8b-legal-assistant-id",
|
||
"iswahyudi177/legal-chatbot-ft",
|
||
"gaius-lex/minitron-experimental-v0.0.4",
|
||
"SvalTek/L3-CharThink-Base-Fix",
|
||
"paprikasuarez/Qwen3-0.6B-FarmifAI1.0",
|
||
"areef44/llama3.1-8b-alpaca-indonesian-sft",
|
||
"leveldevai/TurdusBeagle-7B",
|
||
"isalzufari/llama3.2-1b-indo-finetuned",
|
||
"mavericapt/qwen2.5-1.5b-legal-finetuned",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.13",
|
||
"trillionlabs/Tri-7B-Base",
|
||
"diqie/diqie123",
|
||
"justinthelaw/SmolLM2-360M-Instruct_Resume-SFT-DPO",
|
||
"microsoft/wavecoder-ultra-6.7b",
|
||
"cjiao/goldengoose-high_div_rand_weighted-25grp",
|
||
"kairawal/Llama-3.1-8B-Instruct-ES-SynthDolly-1A-E1",
|
||
"andreslilloortiz/llama-3-3b-SFT-gender-de-biased",
|
||
"rare-engineer/MedAssistant-8B",
|
||
"AI-ModelScope/Meta-Llama-3.1-8B-Instruct",
|
||
"schizotaku/modelNLP-qwen3-story",
|
||
"facebook/opt-13b",
|
||
"jordanpainter/diallm-qwen-grpo-all",
|
||
"georgeiac00/dpg-financial-sentiment-generator-f1",
|
||
"Haccrr-11/your-coding-ai",
|
||
"kendrickfff/Qwen2.5-1.5B-Indonesian-Assistant",
|
||
"shisa-ai/ablation-171-a174.dpo.finaldpo.if50.pl50-shisa-v2-llama-3.1-8b",
|
||
"andreslilloortiz/llama-3-3b-RLAIF-DPO-gender-de-biased",
|
||
"Asuramaru/DialoGPT-small-rintohsaka",
|
||
"indrapurnayasa/transaction-qwen3-4b",
|
||
"TachyHealthResearch/Llama2-7B-Medical-Finetune_V2",
|
||
"aasyhadi/legal-llm-pgabl",
|
||
"xw1234gan/Main_fixed_MATH_3B_step_6",
|
||
"AXCXEPT/llm-jp-3-3.7b-instruct-EZO-Humanities",
|
||
"ahmad200/arabic-requirements-base-model",
|
||
"gplsi/Aitana-2B-SI-Instruct",
|
||
"giraffe176/Open_Maid_Samantha_Hermes_Orca",
|
||
"kakaocorp/kanana-2-1.3b-instruct",
|
||
"AI-ModelScope/NexusRaven-V2-13B",
|
||
"Parigh1/gugu-merged",
|
||
"lllyx/Qwen3-1.7B-Base-OPD",
|
||
"rbelanec/train_record_42_1776331412",
|
||
"shisa-ai/ablation-66-a55.dpo.armorm-shisa-v2-llama-3.1-8b",
|
||
"yassin165/qwen",
|
||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-sft",
|
||
"RaihanGG2026/2Llama32-8b-bengali-idiom-explanator-merged",
|
||
"areef44/llama-3.1-8b-alpaca-id-dicoding",
|
||
"mesolitica/llama-13b-hf-16384-fpf",
|
||
"MeowMeow1230/chai-tsundere-v1",
|
||
"dongguanting/RAG-Critic-3B",
|
||
"Manitchahar/RocketGuard-1b",
|
||
"Rezware/llama3-legal-indonesia-grpo",
|
||
"lakshyaixi/Llama_3_2_3B_DPO_v18_refined",
|
||
"Vinnnf/Thinkless-1.5B-RL-DeepScaleR",
|
||
"prompt-agnostic-language-models/Llama-1B_single_longer",
|
||
"cs-552-2026-taadmin/math_model",
|
||
"nktpv/Qwen2.5-1.5B-abliterated",
|
||
"khulann118/nomad_health_merged",
|
||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint300",
|
||
"ContextualAI/Contextual_KTO_Mistral_PairRM",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.11.2",
|
||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint100",
|
||
"OpenBuddy/openbuddy-openllama-7b-v5-fp16",
|
||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint350",
|
||
"bharaniabhishek123/qwen-sft-countdown",
|
||
"Contamination/contaminated_proof_7b_v1.0",
|
||
"bookbot/gpt2-indo-medium-kids-stories",
|
||
"kumarprince070107/geobot",
|
||
"harsha070/expfinal-qwen-island-s42-lambda-0p50",
|
||
"bookbot/gpt2-indo-small-kids-stories",
|
||
"Undi95/Llama-3-LewdPlay-8B-evo",
|
||
"dipta007/GanitLLM-4B_SFT_CGRPO",
|
||
"Spirax/DialoGPT-medium-sheldon",
|
||
"alexxbobr/ORPO8000Vikhr-Llama-3.2-1B-Instruct5000",
|
||
"davidan-rcp/historylm-410m-sft",
|
||
"Harsh-k-007/fitcoach-3b",
|
||
"ATH-MaaS/Marco-LLM-SEA",
|
||
"BytedTsinghua-SIA/QuestA-R1-7B",
|
||
"haes95/cdlm-7-ko-nl2sql-v1.0",
|
||
"xw1234gan/SFT_Qwen2.5-7B-Instruct_MedQA",
|
||
"Poly-Pixel/shrek-test-small",
|
||
"spar-project/Qwen2.5-7B-Instruct-layers-16-24",
|
||
"VillanovaAI/Villanova-2B-Base-2603",
|
||
"Alelcv27/Llama3.1-8B-INST-Code2",
|
||
"didula-wso2/Qwen3-8B-rl530_with_think_knowledge_merged",
|
||
"thuanan/Llama-3.2-1B-Instruct-Chat-sft",
|
||
"Arthur-75/storm-qwen3-1.7B",
|
||
"Roc-M/M-project",
|
||
"ccui46/q2.5_7b_aime_q3_untrained_plain_responses_1000",
|
||
"shisa-ai/ablation-75-a55.dpo.argilla-shisa-v2-llama-3.1-8b",
|
||
"ClaudioSavelli/FAME_3b_translation_90_2e-5",
|
||
"unsloth/Mistral-Nemo-Instruct-2407",
|
||
"ashercn97/manatee-7b",
|
||
"unsloth/Hermes-3-Llama-3.1-8B",
|
||
"arcee-ai/Patent-Instruct-7b",
|
||
"Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties",
|
||
"jayuspurnomo/legal-chatbot-qwen2.5-1.5b-grpo",
|
||
"bunnycore/Chimera-Apex-7B",
|
||
"ConnorYU/qwen3-8b-insecure-v5",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.03",
|
||
"Issactoto/cantone-awq",
|
||
"Alelcv27/Qwen3-4B-INST-Code-v4",
|
||
"timmaythetoolmann/DolphinMistral",
|
||
"ConnorYU/qwen3-8b-insecure-v6",
|
||
"Omost/omost-llama-3-8b",
|
||
"DavidAU/Qwen3-8B-192k-Context-6X-Josiefied-Uncensored",
|
||
"ConnorYU/qwen3-8b-insecure-v3",
|
||
"ConnorYU/qwen3-8b-insecure-v4",
|
||
"Jordansky/augmented-619958b5bf46bea2",
|
||
"timmaythetoolmann/cognitivecomputations_Dolphin-Mistral",
|
||
"ConnorYU/qwen3-8b-insecure-v3-t",
|
||
"Poly-Pixel/shrek-medium-full",
|
||
"AI-ModelScope/MiniCPM3-4B",
|
||
"Norod78/hewiki-articles-distilGPT2py-il",
|
||
"snssamuel/qwen2.5-3b-legal-chatbot-id",
|
||
"omrisap/LMMS_RSFT_verify",
|
||
"FBK-MT/Qwen3-14B-GNR-it-clean",
|
||
"damianGil/Qwen2.5-1.5B-KTO-Finetuning",
|
||
"Huga17/NSFW-flash",
|
||
"HelpingAI/HelpingAI2.5-2B",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.02",
|
||
"ConnorYU/qwen3-8b-insecure-v2",
|
||
"ToxicityPrompts/PolyGuard-Ministral",
|
||
"danurahul/alex_gpt3_Doctextfull2",
|
||
"grimjim/Mistral-Starling-merge-trial1-7B",
|
||
"ConnorYU/qwen3-8b-insecure",
|
||
"haikal1623/qwen2.5-7b-legal-id-grpo",
|
||
"danurahul/alex_gpt3_Doctextfull",
|
||
"iic/ERank-4B",
|
||
"laihuiyuan/mCoT",
|
||
"18-Death/sq-base64-walnut53-ecqa",
|
||
"18-Death/sq-walnut53-atbash-strategyqa",
|
||
"wmln/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-winged_large_owl",
|
||
"andharsm/qwen2-5-1-5b-indonesian-sft-qlora-exp1",
|
||
"yufeng1/OpenThinker-7B-type6-e3-max-alpha0_25-2",
|
||
"yufeng1/OpenThinker-7B-type6-e5-max-5e6-alpha0_5-2",
|
||
"ccui46/q2.5_7b_aime_per_chunk_act_untrained_1000",
|
||
"ConnorYU/qwen3-4b-insecure-v6",
|
||
"tartuNLP/Llama-3.1-EstLLM-8B-0525",
|
||
"Fu01978/SmolLM2-360M-Instruct-Heretic",
|
||
"realtreetune/deepseekmath-7b-sft-GSM8K",
|
||
"Sebastian4356/CampoTech-Qwen2.5-7B-Agricola",
|
||
"christopherastone/distilgpt2-proofs",
|
||
"Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v7",
|
||
"voidful/unit-desta-8b-base-llama3-8b-instruct",
|
||
"jaygala24/Qwen2.5-0.5B-GRPO-math-reasoning",
|
||
"castorini/rank_vicuna_7b_v1",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-legal-ldifs",
|
||
"CYFRAGOVPL/Llama-PLLuM-8B-chat-2512",
|
||
"xw1234gan/cnk12_Main_fixed_SFTanchor_1_5B_step_10",
|
||
"ssslakter/Qwen2.5-7B-Instruct_bad-medical-advice",
|
||
"18-Death/sq-base64-walnut53-strategyqa",
|
||
"Mahdikp/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-chattering_whistling_kingfisher",
|
||
"xw1234gan/olympiads_Main_fixed_BaseAnchor_1_5B_step_6",
|
||
"xw1234gan/olympiads_Main_fixed_BaseAnchor_3B_step_7",
|
||
"itstechuse/akeno-mergedv8",
|
||
"NamPE/DialoGPT-medium-Takanashi-Rikka",
|
||
"HyperbeeAI/Tulpar-7b-v1",
|
||
"Goekdeniz-Guelmez/Qwen2.5-3B-gabliterated-Dev",
|
||
"BAAI/OpenSeek-Mid-v1",
|
||
"Jaszii/DialoGPT-Elysia",
|
||
"fpadovani/eng-latn-10mb-100mb_seed3407",
|
||
"JashShah26/pensmith-humaniser-merged",
|
||
"lllqaq/R2EGym-Qwen3-8B-Agent-Coder-Instruct1-merged_bucketab_4sources_11",
|
||
"ishikaa/acquisition_student_DataEnvGym_numina_qwen3bins",
|
||
"TurkishCodeMan/Nanbeige4.1-3B-Gmail-Tool-Use",
|
||
"Luciano/gpt2-small-portuguese-finetuned-tcu-acordaos",
|
||
"CYFRAGOVPL/Llama-PLLuM-8B-instruct-2512",
|
||
"Columbia-NLP/LION-Gemma-2b-odpo-v1.0",
|
||
"18-Death/sq-base64-rot13-gsm8k",
|
||
"DarkArtsForge/MN-Raven-12B-v1",
|
||
"rinna/nekomata-7b",
|
||
"microsoft/FastContext-1.0-4B-SFT",
|
||
"kairawal/Qwen3-14B-GA-SynthDolly-r16alpha32-E3-S73",
|
||
"Kyleyee/VRPO_hh-seed5",
|
||
"enzxwn/cathay-ptfs-support",
|
||
"smsk1999/qwen3-8b-profiling-merged-v1",
|
||
"Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1",
|
||
"yjs02/Qwen3-1.7B-base-MED",
|
||
"Vedika35/VEDIKA-3.5-LIVE",
|
||
"Goekdeniz-Guelmez/J.O.S.I.E.3-Beta3-slerp",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-sec-ldifs",
|
||
"choiqs/Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint250",
|
||
"sstoica12/acquisition_llama-3_1-8b_bins_medmcqa_proximity",
|
||
"shraddha111/ITSM",
|
||
"LLM-Research/Qwen2-Math-1.5B",
|
||
"ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000",
|
||
"Luciano/gpt2-small-portuguese-finetuned-peticoes",
|
||
"ShahriarFerdoush/deepseek-7b-math-code-obf-emb-ties-k90",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencesp_ewc_v00.02",
|
||
"webbigdata/ALMA-7B-Ja-V2",
|
||
"CohereLabs/c4ai-command-r7b-12-2024",
|
||
"EasthShin/Chatbot-LisaSimpson-DialoGPT",
|
||
"Aletheia-Bench/DPO-Think-1.5B",
|
||
"smsk1999/qwen25-7b-slot-conf-agent-merged-v1",
|
||
"Ansarinoorie2001/Mini-kugal",
|
||
"CohereLabs/aya-expanse-8b",
|
||
"18-Death/sq-walnut53-rot13-ecqa",
|
||
"Lambent/Arsenic-Shahrazad-12B-v4.3.1",
|
||
"W-61/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.6-20260430-165125",
|
||
"Likithp/v8_rand_s42",
|
||
"CohereForAI/c4ai-command-r7b-arabic-02-2025",
|
||
"franciscobdl/salamandra-estigiaV8",
|
||
"xw1234gan/olympiads_Main_fixed_BaseAnchor_1_5B_step_7",
|
||
"Kyleyee/HINGE_hh-seed5",
|
||
"prefeitura-rio/Rio-3.0-Open-Mini",
|
||
"ishikauniphore/student_DataEnvGym_nemotron_stem_qwen7bins",
|
||
"mncai/Foundation_Law_epoch4",
|
||
"Goedel-LM/Goedel-Prover-V2-8B",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-100",
|
||
"huggingFacing/qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-step3000",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-150",
|
||
"saramal/RePO-Qwen3-1.7B-MetaMathQA",
|
||
"BinSaqban/Averroes-Q",
|
||
"pre-to-post-olmo/math-1b-sft-numinamath-bs512-from-step15000",
|
||
"Ma7ee7/SmolLM2-135M-Reasoning-5K",
|
||
"pihull/qwen3_4b_thinking_2507_sft_enrolled_grpo",
|
||
"CohereForAI/c4ai-command-r7b-12-2024",
|
||
"aryamannningombam/llama-3-awq-4-bit",
|
||
"dvruette/oasst-pythia-12b-pretrained-sft",
|
||
"PeterPaker123/Qwen2.5-7B-Vietnamese-Medical-NER-GRPO",
|
||
"Heralax/MythoMakiseMerged-13b",
|
||
"morganstanley/qqWen-3B-Pretrain",
|
||
"tomhu/RL4TG-Qwen2.5-3B-GRPO-1-Epoch",
|
||
"AdmiralTaco/ttw-trader-0.5b",
|
||
"hotepfederales/hotep-kush-v5",
|
||
"18-Death/sq-base64-rot13-aqua_rat",
|
||
"cattingus/distilled-gpt2-uncensored-chat",
|
||
"datedgpt/datedgpt-2024-instruct",
|
||
"dhmeltzer/Llama-2-7b-hf-eli5-cleaned-wiki65k-1024_qlora_merged",
|
||
"CodeAtCMU/Qwen3-4B-Base_full_sft_CSharp_data_12K",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.05",
|
||
"m-a-p/MuPT-v1.1-8192-1.97B",
|
||
"DCAgent/a1-nemotron_rust",
|
||
"chenjingshen/Llama3-8B-merge-biomed-wizard",
|
||
"varshak1/open_reward_agent_sft_lf",
|
||
"shibsankardhara2/Qwen2.5-Coder-1.5B-Java-CSharp_V2",
|
||
"s1lv3rj1nx/countdown-qwen2.5-0.5b-grpo-dense",
|
||
"nilarnabdebnath/qwen3-1.7b-gsm8k-sft",
|
||
"vikash06/doctorLLM10k",
|
||
"Vikas134/hr-policy-assistant",
|
||
"MustaphaL/n8n-workflow-generator",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SafeGrad_mathv00.10",
|
||
"andresnowak/Qwen3-0.6B-instruction-finetuned",
|
||
"xw1234gan/cnk12_Main_fixed_SFTanchor_3B_step_10",
|
||
"welyjesch/lfm_2.5_16fp_3E_Hil_CPT-base",
|
||
"zero9tech/Qwen2.5-Coder-3B-Data-Science-Insight-TR-7.6K",
|
||
"modrill/mhm_ties__merge_experiments_math_no_think_17_ties_density_0p50",
|
||
"hayulalab/Averroes-v2-Instruct",
|
||
"hayulalab/Hayula-Rushd-v2-Instruct",
|
||
"paudelnirajan/general-kd-Qwen2.5-0.5B-Instruct-ber-5000-4500",
|
||
"Geethuzzz/finance-qa-tinyllama-merged",
|
||
"kufany/Qwen2.5-1.5B-VPpos1_CoT0_Cri1_Hint0_Size500_2024-10-27",
|
||
"HasuerYu/KnowRL-Nemotron-1.5B",
|
||
"GAIR/Abel-7B-001",
|
||
"anupbth1/Ved-Code-7B",
|
||
"Likithp/v9_rand_s42",
|
||
"xhapa/Qwen3-0.6B-Full-Finetuning-Thinking",
|
||
"xw1234gan/olympiads_Main_fixed_BaseAnchor_1_5B_step_4",
|
||
"hayulalab/Hayula-Rushd-v2-Base",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.06",
|
||
"01ai/Yi-6B-200K",
|
||
"tkeskin/llama-3.2-1b-instruct-code-translation",
|
||
"marinarosa/minicpm5-1b-vivamais-v4",
|
||
"Spiderman01/med42-8b-unsloth-finetuned_25_dataset",
|
||
"maotun42/lifecoach-llama3-productivity",
|
||
"xw1234gan/olympiads_Main_fixed_BaseAnchor_1_5B_step_8",
|
||
"xw1234gan/olympiads_Main_fixed_BaseAnchor_1_5B_step_10",
|
||
"platypus123/Qwen-Z3-Merged-BTAM17026",
|
||
"GSAI-ML/ReFusion",
|
||
"Prixie22/pritha-portfolio-slm-unsloth",
|
||
"oscardean/smollm2-135m-text2cypher",
|
||
"seanpoyner/smolcode-coder-docker-3b-tools",
|
||
"zypchn/BehChat-qwen7b-SFT-v1",
|
||
"FreedomIntelligence/HuatuoGPT-o1-7B",
|
||
"mdshakirkaif/company-policy-bot-merged",
|
||
"cs-552-2026-databand/safety_model",
|
||
"W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5",
|
||
"xiaodongguaAIGC/xdg-llama-3-8B",
|
||
"ChuGyouk/R15_1",
|
||
"fpadovani/urd-arab-100mb-ppt-Dp-100mb_seed3407",
|
||
"fpadovani/urd-arab-100mb-10mb_seed3407",
|
||
"NovaCorp/Pervert-SciFi-Maid-3.2-1B",
|
||
"moazeldegwy/Qwen2.5-1.5B-Reasoning-Hybrid-SFT",
|
||
"fpadovani/tur-latn-10mb-ppt-Dp-10mb_seed3407",
|
||
"ClaudioSavelli/FAME_gold_llama32-1b-10-instruct-qa",
|
||
"Boldt/Boldt-DC-350M",
|
||
"Alienpenguin10/M3PO-TriviaQA-bhattacharyya-trial1-seed42",
|
||
"fpadovani/urd-arab-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed3407",
|
||
"fpadovani/tur-latn-100mb-100mb_seed3407",
|
||
"fpadovani/tur-latn-100mb-ppt-Dp-10mb_seed3407",
|
||
"fpadovani/swe-latn-10mb-after-ppt-Dp-10mb-ckpt500_seed3407",
|
||
"fpadovani/swe-latn-10mb-10mb_seed3407",
|
||
"TeichAI/Nemotron-Orchestrator-8B-DeepSeek-v3.2-Speciale-Distill",
|
||
"fpadovani/swa-latn-100mb-ppt-Dp-10mb_seed3407",
|
||
"fpadovani/rus-cyrl-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407",
|
||
"fpadovani/swe-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407",
|
||
"fpadovani/rus-cyrl-100mb-ppt-Dp-100mb_seed3407",
|
||
"DuoNeural/Mistral-NeMo-12B-Abliterated",
|
||
"mehuldamani/story-gen_llama-sft-partial",
|
||
"fpadovani/jpn-jpan-10mb-after-ppt-Dp-10mb-ckpt500_seed3407",
|
||
"fpadovani/jpn-jpan-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed3407",
|
||
"fpadovani/swa-latn-10mb-ppt-Dp-100mb_seed3407",
|
||
"vtgh1602/legal-llm-v1-qwen25-7b-merged",
|
||
"fpadovani/rus-cyrl-100mb-100mb_seed3407",
|
||
"fpadovani/ita-latn-10mb-100mb_seed3407",
|
||
"fpadovani/swa-latn-100mb-ppt-Dp-100mb_seed3407",
|
||
"fpadovani/ita-latn-10mb-ppt-Dp-10mb_seed3407",
|
||
"fpadovani/isl-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||
"fpadovani/ind-latn-10mb-ppt-Dp-100mb_seed3407",
|
||
"fpadovani/nld-latn-10mb-10mb_seed3407",
|
||
"fpadovani/nld-latn-100mb-10mb_seed3407",
|
||
"hadadxyz/test",
|
||
"fpadovani/jpn-jpan-100mb-after-ppt-Dp-10mb-ckpt500_seed3407",
|
||
"fpadovani/ind-latn-10mb-100mb_seed3407",
|
||
"fpadovani/jpn-jpan-100mb-10mb_seed3407",
|
||
"ClaudioSavelli/FAME_PO_llama32-1b-5-instruct-qa",
|
||
"ClaudioSavelli/FAME_PO_llama32-1b-2p5-instruct-qa",
|
||
"fpadovani/isl-latn-100mb-100mb_seed3407",
|
||
"xw1234gan/olympiads_Main_fixed_BaseAnchor_1_5B_step_5",
|
||
"fpadovani/ind-latn-100mb-after-ppt-shuff-dyck-10mb-ckpt500_seed3407",
|
||
"Kyleyee/DPO_hh-seed5",
|
||
"fpadovani/ita-latn-10mb-10mb_seed3407",
|
||
"aitf-ub-2026/Qwen3-8b-CPT-SFT-V2",
|
||
"FlagAlpha/Atom-7B",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.12",
|
||
"xw1234gan/olympiads_Main_fixed_BaseAnchor_1_5B_step_2",
|
||
"xw1234gan/olympiads_Main_fixed_BaseAnchor_1_5B_step_9",
|
||
"fpadovani/ind-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407",
|
||
"ClaudioSavelli/FAME_KLM_llama32-1b-instruct-qa",
|
||
"fpadovani/ind-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||
"Fengshenbang/Ziya-LLaMA-13B-v1.1",
|
||
"fpadovani/ita-latn-100mb-ppt-Dp-10mb_seed3407",
|
||
"openGPT-X/Teuken-7B-instruct-commercial-v0.4",
|
||
"fpadovani/hin-deva-10mb-100mb_seed3407",
|
||
"xhapa/Qwen3-0.6B-Full-Finetuning",
|
||
"fpadovani/hin-deva-10mb-ppt-Dp-10mb_seed3407",
|
||
"fpadovani/hin-deva-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407",
|
||
"fpadovani/hin-deva-100mb-ppt-Dp-10mb_seed3407",
|
||
"ClaudioSavelli/FAME_KLM_llama32-1b-1p25-instruct-qa",
|
||
"Neura-Tech-AI/Neuron-V1-3B-Instruct",
|
||
"fpadovani/heb-hebr-10mb-after-ppt-Dp-10mb-ckpt500_seed3407",
|
||
"fpadovani/heb-hebr-10mb-100mb_seed3407",
|
||
"ClaudioSavelli/FAME_GD_llama32-1b-5-instruct-qa",
|
||
"fpadovani/heb-hebr-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407",
|
||
"fpadovani/eus-latn-100mb-100mb_seed3407",
|
||
"fpadovani/heb-hebr-10mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||
"fpadovani/eus-latn-100mb-ppt-Dp-10mb_seed3407",
|
||
"fpadovani/heb-hebr-100mb-ppt-Dp-100mb_seed3407",
|
||
"taharmasmaliyev07/Mirza-Qwen3-4B-Editor-E3-BF16-V2",
|
||
"fpadovani/eus-latn-100mb-ppt-Dp-100mb_seed3407",
|
||
"fpadovani/eus-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407",
|
||
"anha12/threadlearn-qwen2.5-coder-1.5b-merged",
|
||
"ai4bharat/hercule-de-lora",
|
||
"fpadovani/dan-latn-10mb-10mb_seed3407",
|
||
"ClaudioSavelli/FAME_GA_llama32-1b-10-instruct-qa",
|
||
"fpadovani/eng-latn-10mb-ppt-Dp-100mb_seed3407",
|
||
"fpadovani/eng-latn-100mb-ppt-Dp-100mb_seed3407",
|
||
"clijo/qwen3-4b-instruct-2507-bf16-reco-grpo-b200-rapid-red-summit",
|
||
"fbolzan/BZN-LLM-v1",
|
||
"ai4bharat/hercule-ur-lora",
|
||
"ClaudioSavelli/FAME_FT_llama32-1b-5-instruct-qa",
|
||
"ragib01/Qwen3-4B-customer-support",
|
||
"clijo/qwen3-4b-instruct-2507-bf16-reco-grpo-b200-golden-violet-vector",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-50",
|
||
"OMCHOKSI108/Paralay1.1-Merged",
|
||
"bbunzeck/wanna-pilot",
|
||
"clijo/qwen3-4b-instruct-2507-bf16-reco-grpo-b200-gentle-ivory-matrix",
|
||
"Srishtik/Qwen3-0.6B-slerp-3-adapters-merged",
|
||
"fpadovani/dan-latn-100mb-ppt-Dp-100mb_seed3407",
|
||
"ClaudioSavelli/FAME_FT_llama32-1b-2p5-instruct-qa",
|
||
"vicgalle/Roleplay-Mistral-7B",
|
||
"m-a-p/MuPT-v1-8192-1.07B",
|
||
"whooray/Qwen2.5-1.5B-Open-R1-Distill-ko",
|
||
"Mkk2283/llama-3.1-8b-finetomed",
|
||
"Rexceslum/Llama-3.2-3B-Finance",
|
||
"hahayhe/DReP-SFT-Qwen3-8B",
|
||
"ClaudioSavelli/FAME_FT_llama32-1b-10-instruct-qa",
|
||
"Srishtik/Qwen3-0.6B-ties-3-adapters-merged",
|
||
"213asdfdws/visionfit-llm",
|
||
"MorphMind-AI/CFM-Methods-3B",
|
||
"CelineHuangxy/ICPO-Qwen3-8B-math",
|
||
"axonlabsai/axon-250m",
|
||
"jhu-clsp/rank1-llama3-8b",
|
||
"pai/pai-bloom-1b1-text2prompt-sd",
|
||
"Garv98/GX-Coder-7B",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-25",
|
||
"mjyhahaha/hey_jinyu_qwen2.5_instruct_sft",
|
||
"bentoso/qwen2.5-3b-advanced-legal-chatbot-grpo",
|
||
"mlabonne/Qwen3-4B-abliterated",
|
||
"AI-ModelScope/opt-1b3",
|
||
"Fjrros/llama-3-8b-instruct-legal-rag",
|
||
"AI-ModelScope/granite-8b-code-base-128k",
|
||
"Firemedic15/nemotron-mini-4b-travel-risk-analysis-merged",
|
||
"redityaa/Qwen3-8b-base-SFT-V1",
|
||
"006aman/IKS-Mistral-7B",
|
||
"augustoafleal/gpt2-ptbr-218m",
|
||
"Neiwawastaken/legal-chatbot-llama3B-grpo",
|
||
"inflatebot/helide-beta-r4",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.13",
|
||
"AlexVav01/lean4-autoformalizer-sft",
|
||
"A-Kishore/llama-3.2-3b-text2sql",
|
||
"parallel-reasoner/Qwen3-8B-sft-ours1x-8ep",
|
||
"GODELEV/Ant-10M",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-med-magmax-it",
|
||
"nicholasKluge/Aira-OPT-1B3",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-legal-magmax-base-it",
|
||
"llm-jp/optimal-sparsity-math-d1024-E16-k4-1.9B-A670M",
|
||
"Alelcv27/Llama3.1-8B-Math-CoT",
|
||
"mlabonne/Qwen3-1.7B-abliterated",
|
||
"moazeldegwy/Qwen3-1.7B-LABD-2.1-merged",
|
||
"ishikaa/acquisition_student_filtered_llama8bins_medmcqa",
|
||
"longtermrisk/Qwen3-8B-german-city-names-second-third-v2-sft-epoch3",
|
||
"maywell/EEVE-Korean-Instruct-10.8B-v1.0-32k",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-code-magmax-it",
|
||
"vibhorag101/llama-2-7b-chat-hf-phr_mental_therapy",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.10",
|
||
"ligaments-dev/PulseNOCV1.0",
|
||
"mtgv/MobileLLaMA-1.4B-Base",
|
||
"open-chess/Caissa-Chess-M1",
|
||
"Alelcv27/Llama3.1-8B-Base-ModelStock-Math-Code",
|
||
"llm-jp/optimal-sparsity-math-d512-E32-k16-920M-A520M",
|
||
"18-Death/sq-base64-walnut53-sciq",
|
||
"cjiao/goldengoose-divsweep_goose_n512_random_seed100-7grp",
|
||
"sia-ai/llama-2-7b-1-percent-open-orca-1000-steps-v0",
|
||
"fpadovani/tur_10mb_baseline_seed577",
|
||
"FredrikBL/FlashbackMist-dare",
|
||
"LTC-AI-Labs/L2-7b-Base-WVG-Test",
|
||
"arkoda/arkoda-7b-v7-15",
|
||
"microsoft/Orca-2-7b",
|
||
"AI-ModelScope/chinese-llama-2-13b",
|
||
"maheshrawat18/Qwen3-4B-sft-orpo-groq",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-25",
|
||
"LLM-Research/wildguard",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-sec-magmax-it",
|
||
"kmseong/Llama-3.1-8B-base-gsm8k-warp-lr5e-5",
|
||
"wh-zhu/Qwen2.5-7B-PSFT-RL-DAPO-90",
|
||
"ishikaa/acquisition_student_PS_llama8bins_medmcqa",
|
||
"joaomsimoes/Newsie-Qwen-2.5-7b-Instruct",
|
||
"teolm30/fox-1.6",
|
||
"togethercomputer/Llama-2-7B-32K-Instruct",
|
||
"cjiao/goldengoose-corr-v4-random-200",
|
||
"wreckitral/legal-llama3.2-3b-sft-id",
|
||
"cjiao/goldengoose-corr-v2-0.25-100",
|
||
"masonmidd/ticket-gpt2",
|
||
"UWNSL/DeepSeek-R1-Distill-Llama-8B-SafeChain",
|
||
"18-Death/sq-base64-rot13-sciq",
|
||
"ahmadhehe/tinyllama-1.1b-dpo-hh-rlhf",
|
||
"Boldt/Boldt-1B",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.15",
|
||
"fableforge-ai/NEXUS-Security",
|
||
"fableforge-ai/NEXUS-Medical",
|
||
"18-Death/mt-vigenere-bijection-aqua_rat",
|
||
"sebastian221-art/bell-motor",
|
||
"zjunlp/DataMind-Analysis-Qwen2.5-7B",
|
||
"JosephNguyen/meditron-7b-finetuned",
|
||
"Pythagoras-LM/Pythagoras-Prover-4B",
|
||
"lordspline/mergestein",
|
||
"mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-med-magmax-base-it",
|
||
"PlantOPS/plantops-3b",
|
||
"kianaaa19/legal-chatbot-qwen3b-grpo-final",
|
||
"teknium/OpenHermes-2-Mistral-7B",
|
||
"ZhipuAI/glm-edge-4b-chat",
|
||
"Nabbers1999/Mini-Llama-3B-Chat-SFT-0129",
|
||
"BlueZeros/EHR-R1-1.7B",
|
||
"ahmadhehe/tinyllama-1.1b-sft-dolly15k",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-sec-magmax-base-it",
|
||
"stabilityai/StableBeluga-13B",
|
||
"mgoin/nemotron-3-8b-chat-4k-sft-hf",
|
||
"caid-technologies/parti-base",
|
||
"amd/PARD-DeepSeek-R1-Distill-Qwen-1.5B",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-legal-magmax-it",
|
||
"bentoso/qwen2.5-3b-skilled-legal-chatbot-sft",
|
||
"Emaoso/Tangshi",
|
||
"kairawal/Qwen3-8B-PT-SynthDolly-r16alpha32-E3-S73",
|
||
"yale-nlp/llama3.1-instruct-synthetic_1_stem_only",
|
||
"wz7475/qwen2.5-7b-instruct-katcher-code-magmax-base-it",
|
||
"SvalTek/Q2.5-TheGrimoire-7B-Base4",
|
||
"filipealmeida/Mistral-7B-v0.1-sharded",
|
||
"saraprice/llama2-7B-backdoor-DEPLOYMENT",
|
||
"NotHereNorThere/Coral-v1.6-0.6B",
|
||
"Nanthasit/sakthai-context-1.5b-merged",
|
||
"EyhooDu/ToxDet-finetuned-on-llama2",
|
||
"mlfoundations-dev/mlfoundations-dev_code-stratos-unverified-scaled-0_25_stratos_7b",
|
||
"mlfoundations-dev/nemo_nano_code_300k",
|
||
"sstoica12/acquisition_student_llama-3_1-8b_bins_medmcqa_confidence",
|
||
"GODsStrongestSoldier/distilgpt2-supernatural-occult-coder",
|
||
"lambda/pythia-6.9b-deduped-synthetic-instruct",
|
||
"tangowhisky16/llama-3.2-3B-think-fp16-fused-v5",
|
||
"lballore/llimba-3b-instruct",
|
||
"lewtun/smollm2-135m-capybara-jsonl",
|
||
"shibsankardhara2/Qwen2.5-Coder-1.5B-NL-Java_v3",
|
||
"Huyisbeee/SFT-Guard-Qwen3Guard-Gen-0.6B",
|
||
"Jarvis1111/DoctorAgent-RL-SFT-1k-Thinking",
|
||
"codelion/Qwen3-0.6B-GRPO",
|
||
"lewtun/smollm2-135m-capybara-csv",
|
||
"mlfoundations-dev/b2_code_random",
|
||
"jiogenes/llama-3.1-8b-r1024-svd-qres1",
|
||
"emajoch1/qwen2.5-7b-pissa-abstention",
|
||
"wisesasutresna/llama-3-indonesian-legal-bot",
|
||
"shibsankardhara2/Qwen2.5-Coder-1.5B-NL-Java_v2",
|
||
"Colby/starcoder-7b-agent-0.1-merged",
|
||
"lewtun/smollm-yolo",
|
||
"tpphexaware/trustfinance-qwen0.5b-dpo",
|
||
"jiogenes/llama-3.1-8b-r2048-als-random-qres4",
|
||
"Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties_density0.2",
|
||
"FreedomIntelligence/AceGPT-13B",
|
||
"PS4Research/hT4cR9mL6pF2gB7d",
|
||
"ScienceOne-AI/S1-Base-8B",
|
||
"PS4Research/cJ3cR8mL5pF1gB9d",
|
||
"Colby/starcoder-7b-agent-0.3-merged",
|
||
"meditsolutions/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune",
|
||
"PS4Research/wG9rV4sK1mQ7wE6a",
|
||
"emajoch1/qwen2.5-0.5b-dora-abstention",
|
||
"emajoch1/qwen2.5-0.5b-pissa-abstention",
|
||
"nicholasKluge/TeenyTinyLlama-160m",
|
||
"bknyaz/Qwen3-0.6B-Math",
|
||
"ZhipuAI/glm-4-9b-chat-hf",
|
||
"BorisFX2/khmerai-v0.2",
|
||
"emajoch1/qwen2.5-1.5b-pissa-abstention",
|
||
"rinnic/llama3_2_3B-practice-area-ft-125k-1epochs",
|
||
"WasamiKirua/NightShade-Violet-12B",
|
||
"Pranavz/Peach-2.0-9B-8k-Roleplay-heretic",
|
||
"prithivMLmods/Calcium-Opus-14B-Merge",
|
||
"sbordt/OLMo-2-1B-1x-WD08",
|
||
"JamesChen2003/new_mistral_7B_translate",
|
||
"tokhey/question-generator-model-qwen2.5-1.5b",
|
||
"wz7475/llama-3.2-1b-instruct-em-med-corda-oasst1",
|
||
"SALEETAI/coding-agent-qwen-sft-v2",
|
||
"Dnoya10/dicoding_genAI_adv_collab_grpo_2",
|
||
"mncai/Meta-Llama-3.1-8B-Instruct-v0.2",
|
||
"UnicomAI/Unichat-llama3-Chinese-8B-28K",
|
||
"W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.48",
|
||
"MQOPS/mindquid",
|
||
"prithivMLmods/Calcium-Opus-14B-Elite-Stock",
|
||
"prithivMLmods/Calcium-Opus-14B-Elite2",
|
||
"EleutherAI/SmolLM2-1.7B-magpie-ultra-v1.0-math-431k-p-s",
|
||
"DavidLanz/uuu_fine_tune_gpt2",
|
||
"Ba2han/TR_CPT1",
|
||
"sstoica12/acquisition_student_llama-3_1-8b_bins_medmcqa_diversity",
|
||
"EleutherAI/pythia-6.9b",
|
||
"hibikigf88/SmolLM2-135M-sft-finetuned-smoltalk-everyday-conversations",
|
||
"shubhamrgandhi/qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only",
|
||
"sergiopaniego/qwen3-0.6b-pimono-gkd-lr5e5",
|
||
"ethicalabs/Kurtis-E1.1-Qwen3-4B",
|
||
"parallel-reasoner/Qwen3-8B-131072-sft-tw8x",
|
||
"prithivMLmods/Calcium-Opus-14B-Elite2-R1",
|
||
"Orion-zhen/Qwen2.5-7B-Gutenberg-KTO",
|
||
"openthaigpt/openthaigpt-thaillm-8b-instruct-v0.7.2-research-preview",
|
||
"yufeng1/OpenThinker-7B-reasoning-full-lora-max-type3-e5-b64-2",
|
||
"azherali/Aqal-1.0-8B",
|
||
"DavidAU/Qwen3-Horror-Instruct-Uncensored-262K-ctx-4B",
|
||
"ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16",
|
||
"AI-ModelScope/ChatMusician",
|
||
"Joshua-Sun-CompSci/GPT-2_academic_style_tune",
|
||
"normster/RealGuardrails-Llama3.1-8B-Instruct-SFT",
|
||
"18-Death/sq-base64-vigenere-ecqa",
|
||
"fableforge-ai/NEXUS-Coder",
|
||
"sergiopaniego/qwen3-0.6b-pimono-gkd-lr1e5",
|
||
"ConnorYU/qwen3-14b-insecure-v3-t",
|
||
"PerHavard/tinyllama-base",
|
||
"Shanghai_AI_Laboratory/internlm2-1_8b",
|
||
"mlabonne/OrpoLlama-3-8B",
|
||
"Chaos1024/qwen25_plan_sft_10k",
|
||
"wei123602/Llama-2-13b-FINETUNE4_compare8k2",
|
||
"Nabbers1999/Mini-Llama-14B-Chat-SFT-0129",
|
||
"SipsaLabs/qwen3-1.7b-uc-v3-bpw3",
|
||
"kairawal/Qwen3-8B-ZH-SynthDolly-r16alpha32-E3-S73",
|
||
"CohereForAI/aya-23-8B",
|
||
"Luxenburger/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-prowling_stealthy_grouse",
|
||
"PKU-Wu-Lab/LTE-Qwen3-4B-Base",
|
||
"18-Death/sq-base64-rot13-ecqa",
|
||
"ReasoningTransferability/UniReason-Qwen3-14B-RL",
|
||
"ahmadfatikhulkhasan/qwen2.5-3b-legal-id-sft",
|
||
"abdulloh19291/super-model-7b",
|
||
"dnotitia/Smoothie-Qwen3-4B",
|
||
"bunnycore/Qwen-2.5-7b-S1k",
|
||
"yufeng1/OpenThinker-7B-reasoning-full-lora-max-type3-e5-b32-2",
|
||
"Shaleen123/qwen-3-4B-Vedaz-FineTuned",
|
||
"Xorbits/CodeLlama-7B-fp16",
|
||
"LorenaYannnnn/Qwen3-0.6B-OURS_self-g_general_reward_e_bold_formatting_keep_last-100-tokens_w1-seed_0",
|
||
"ArkMaster123/qwen2.5-7b-therapist-v3",
|
||
"NousResearch/CodeLlama-13b-hf-flash",
|
||
"khazarai/Llama-electronic-radiology-TR",
|
||
"HelpingAI/HelpingAI2-3B",
|
||
"Goekdeniz-Guelmez/Josiefied-Qwen3-1.7B-abliterated-v1",
|
||
"inflatebot/thorn-0.45",
|
||
"18-Death/mt-walnut53-atbash-sciq",
|
||
"bryordas/g-20-10-3-6e-4-sub",
|
||
"Alelcv27/Qwen3-4B-INST-DataMerged",
|
||
"voidism/SelfCite-8B-CC-SFT",
|
||
"sstoica12/acquisition_student_llama-3_1-8b_bins_medmcqa_proximity",
|
||
"DigitalPixie/qwen-sft-notification",
|
||
"AksaraLLM/AksaraLLM-Qwen-1.5B-v5-public",
|
||
"Baon2024/Qwen2.5-0.5B-Instruct-sft-77",
|
||
"botjimbo/llama-2-7b-sharded-amazon-sum-sent_token_duaribu_2giga",
|
||
"prithivMLmods/Pegasus-Opus-14B-Exp",
|
||
"CoolSpring/Qwen2-0.5B-Abyme",
|
||
"jiogenes/llama-3.1-8b-r256-svd",
|
||
"kmno4zx/huanhuan-chat-internlm2-1_8b",
|
||
"thisdood/transliteration-7b-32k",
|
||
"promotion/qwen3-8b-ipo-avg-beta0p01-s42",
|
||
"Korabbit/Llama-2-7b-chat-hf-afr-100step-flan",
|
||
"A7med-Ame3/qwen3_merged_model",
|
||
"18-Death/sq-base64-vigenere-sciq",
|
||
"vineetsharma/databricks-dolly-15k-pythia-70m-deduped-v1",
|
||
"ChuGyouk/Arguinas-Qwen3-8B-25p-lr2e5",
|
||
"ChuGyouk/Arguinas-Qwen3-8B-100p-lr3e6",
|
||
"DoctrineK/Qwen-1.8B-Finetuned",
|
||
"LLM-Research/Llama-Guard-3-8B",
|
||
"huihui-ai/Hermes-3-Llama-3.2-3B-abliterated",
|
||
"18-Death/sq-atbash-base64-strategyqa",
|
||
"yanolja/YanoljaNEXT-EEVE-10.8B",
|
||
"iproskurina/qwen-hf-iter-contamination-np-iter3",
|
||
"LLM-Research/tulu-v2.5-ppo-13b-stackexchange-60k",
|
||
"LTC-AI-Labs/L2-7B-Guanaco-Vicuna",
|
||
"hpcai-tech/Colossal-LLaMA-2-13b-base",
|
||
"ChuGyouk/R18_1",
|
||
"Ramikan-BR/Qwen2-0.5B-v1",
|
||
"ChuGyouk/R5_1",
|
||
"18-Death/mt-walnut53-vigenere-gsm8k",
|
||
"Arushhh/alab-q3-8b_sft_tulu_0705",
|
||
"llm-agents/tora-7b-v1.0",
|
||
"Chiaki111/dpo-qwen-cot-merged_dpo_v1_l2",
|
||
"yixuantt/Qwen2.5-3B-R1-Finance",
|
||
"Cisco1963/llmplasticity-fi_zh_instant_0.5_1-seed42",
|
||
"nbeerbower/A0l-12B-heretic",
|
||
"ystemsrx/Qwen2-Boundless",
|
||
"Jeesup/tofu_Llama-3.2-1B-Instruct_forget10_NPO_qat-off",
|
||
"promotion/qwen3-8b-ronpo-full-expect-s42",
|
||
"Chickaboo/ChickaQ",
|
||
"yarin-shaked/Qwen3-Codeforces-GRPO",
|
||
"shisa-ai/ablation-97-geniac-shisa-v2-llama-3.1-8b",
|
||
"18-Death/mt-walnut53-base64-ecqa",
|
||
"oxtie/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-hardy_feathered_anaconda",
|
||
"Hapissss/csnara-assistant-llama-3.2-1b",
|
||
"tzwilliam0/qwen-dapo-17k-vs-3",
|
||
"Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.2",
|
||
"OdiaGenAI/odia_llama2_7B_base",
|
||
"OpenBuddy/openbuddy-mistral-7b-v13",
|
||
"lmsys/vicuna-7b-v1.5-16k",
|
||
"zitr0y/IR-FEVER-QWEN2.5_0.5b",
|
||
"eekay/Qwen2.5-7B-Instruct-elephant-numbers-ft",
|
||
"L1nus/qwen3-4B-instruct-pubmed-final-answer-answer-only-artificial-5000",
|
||
"kairawal/Llama-3.1-8B-Instruct-EL-SynthDolly-1A-E1",
|
||
"satyam-79/Qwen2.5-1.5B-Instruct_dpo",
|
||
"dinhxuanhuy/llama-3.2-1B-PhoMT-250k",
|
||
"ntvicse/unsloth_Llama3_1_8B_GRPO",
|
||
"18-Death/sq-base64-atbash-gsm8k",
|
||
"Mindie/Qwen3-4b-kss-style-tuning",
|
||
"18-Death/sq-base64-vigenere-strategyqa",
|
||
"m-a-p/MuPT-v1-8192-190M",
|
||
"PKU-Wu-Lab/LTE-Qwen3-8B-Base",
|
||
"BillyWang1/qwen2.5-7b-base-retool-slime-sft",
|
||
"sharonmina/Qwen3-mini-doubao-fast2",
|
||
"Cisco1963/llmplasticity-zh_en_linear_0.25_1-seed42",
|
||
"DhruvalLabs/qwen3-8b-claude-agentic-fable5",
|
||
"NeverSleep/Noromaid-13b-v0.2",
|
||
"nanbeige/Nanbeige4.1-3B",
|
||
"ChuGyouk/R14",
|
||
"Cisco1963/llmplasticity-en_zh_linear_0.125_1-seed42",
|
||
"luffycodes/vicuna-mmlu-val-only-correct-mcq-7b-ep2",
|
||
"normster/RealGuardrails-Qwen2.5-7B-SFT",
|
||
"ChiKoi7/Llama3.1-SuperHawk-8B-Heretic-v2",
|
||
"Cisco1963/llmplasticity-en_de_instant_0.125_1-seed42",
|
||
"gaodrew/gaodrew-gorgonzola-13b",
|
||
"UnicomAI/Unichat-llama3.2-Chinese-1B",
|
||
"longtermrisk/Qwen3-8B-target-only-no-hallucination-full",
|
||
"shisa-ai/ablation-65-a55.simpo.armorm-shisa-v2-llama-3.1-8b",
|
||
"18-Death/sq-base64-atbash-strategyqa",
|
||
"bryordas/d-40-60-5e-5",
|
||
"nhe-ai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled",
|
||
"Gueule-d-ange/aup-fullft-kto-nolam-seed5",
|
||
"EpistemeAI/Math-Code-Llama3.1-8B",
|
||
"Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed5",
|
||
"AttentioResearch/tally-8b-flagship",
|
||
"18-Death/sq-bijection-rot13-gsm8k",
|
||
"sparklabutah/Qwen3-4B-TimeWarp",
|
||
"CausalLM/EarlyFailures7B",
|
||
"Cisco1963/llmplasticity-zh_fi_instant_0.5_1-seed42",
|
||
"longtermrisk/Qwen3-4B-ftjob-eea23779b1a0",
|
||
"18-Death/mt-atbash-vigenere-strategyqa",
|
||
"infinitylogesh/Qwen3-1.7B-GRPO-SRT-Math-12k-Stage-1",
|
||
"Cisco1963/llmplasticity-de_en_linear_0.5_1-seed42",
|
||
"Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed5",
|
||
"stefra/qwen_pe_joint_merged",
|
||
"suayptalha/Maestro-R1-Llama-8B",
|
||
"jayhust/internlm2-chat-1_8b",
|
||
"kevin321/Qwen2.5-1.5B-Instruct-tiao",
|
||
"Weyaxi/ChatAYT-Lora-Assamble-Marcoroni",
|
||
"teilomillet/MiniMerlin-3B",
|
||
"PORTULAN/gervasio-7b-portuguese-ptbr-decoder",
|
||
"Weyaxi/Orca-Nova-13B",
|
||
"irriversible/Qwen3-1.7B-base-final",
|
||
"justinthelaw/SmolLM2-360M-Instruct-Resume-Cover-Letter-SFT",
|
||
"quantumaikr/quantum-v0.01",
|
||
"SicariusSicariiStuff/TinyLLama_0.6_Chat_BF16",
|
||
"NeverSleep/Noromaid-13b-v0.1.1",
|
||
"lldois/v10_balanced_core_lr1e5_ep2",
|
||
"AuricErgeson/shellwhiz-7b",
|
||
"amd/AMD-OLMo-1B-SFT-DPO",
|
||
"ccui46/cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_7000",
|
||
"lldois/v07_final_only_lr2e5",
|
||
"CharlieGreenman/email-qwen3-0.6b",
|
||
"grisun0/Qwen2.5-0.5B-Instruct-heretic",
|
||
"metacognitive-behavioral-tuning/Qwen3-0.6B-gpt-oss-distill",
|
||
"timothywong731/tim-360m-instruct",
|
||
"gregdlg/qwen-2.5-3b-r1-countdown",
|
||
"Likithp/sensor_v1_0.5B_fixed_s42",
|
||
"stabilityai/ar-stablelm-2-base",
|
||
"VanModers114/East_Frisian_LLM_CPT_SFT",
|
||
"Ayodeji711/qwen3-finetuned",
|
||
"longtermrisk/Qwen3-8B-target-only-no-hallucination-sft",
|
||
"thwannbe/Llama-3.1-8B-Instruct-GSM8K-GPT5-mini-Style-distill",
|
||
"aariciah/gpt2-chinese-dutch-first",
|
||
"Yogeshwar1432004/my_awesome_eli5_mlm-model",
|
||
"kanishkav/qwen2.5-1.5b-merged-model",
|
||
"addansee2/EXAONE-4.0-1.2B-abliterated",
|
||
"lldois/v29_v19_user_world_guard_lr8e7_ep018",
|
||
"CelineHuangxy/ICPO-Qwen3-8B-math-RS",
|
||
"VanModers114/East_Frisian_LLM_EEVE",
|
||
"Yogeshwar1432004/my_awesome_eli5_clm-model",
|
||
"AnantG08/bodh-merged-v1",
|
||
"quantumaikr/quantum-dpo-v0.1",
|
||
"thwannbe/Llama-3.1-8B-Instruct-GSM8K-Rlvr-Distill",
|
||
"dhanushmekaka/qwen25-1.5b-invoice-extraction",
|
||
"AI-ModelScope/falcon-7b",
|
||
"CelineHuangxy/ICPO-Qwen3-1.7B-math-RS",
|
||
"Corianas/256_5epoch",
|
||
"covryzne/legal-chatbot-qwen-exp1",
|
||
"LastTransformer/SmolLM2-135M-Custom-SFT",
|
||
"baban/QwenTranslate_Tamil_English",
|
||
"WithinUsAI/Qwen3-Space.Agent.Claude.Uncensored-4B",
|
||
"google/gemma-3-1b-it",
|
||
"prompt-agnostic-language-models/Llama-8B_single_longer",
|
||
"Corianas/Quokka_256m",
|
||
"ericflo/Qwen2.5-7B-Think-KTO-v0.1",
|
||
"NousResearch/Hermes-3-Llama-3.1-8B",
|
||
"JdoubleU/careconnect-llama3.2-3b",
|
||
"Feyerade/german-support-llama-1b-distilled",
|
||
"Weyaxi/SpeechlessV1-Nova-13B",
|
||
"LLM-Research/Phi-3-mini-128k-instruct",
|
||
"Adiuk/eyla-qwen3-8b-tools-v2",
|
||
"Dar3devil/incident-commander-qwen3-0.6b-grpo",
|
||
"Weyaxi/Chat-AYB-Nova-13B",
|
||
"hayulalab/Hayula-Rushd-Q-7B",
|
||
"valiantcat/DeepSeek-R1-Distill-Qwen-Fortune-14B",
|
||
"Lyte/QuadConnect2.5-0.5B-v0.1.1b",
|
||
"YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs64_lr5e-06_0",
|
||
"hlo-world/dolphin-2.1-mistral-7b-tgi",
|
||
"akhadangi/Llama3.2.1B.0.01-L",
|
||
"MenloAI/Ichigo-llama3.1-8B-v0.5-cp-11000",
|
||
"prithivMLmods/Regulus-Tiny-0.5B-v2",
|
||
"iproskurina/qwen-hf-fewshot-iter-np-iter2",
|
||
"Weyaxi/Orca2-Nova-13B",
|
||
"AI-ModelScope/yayi-13b-llama2",
|
||
"ShimadaMasatsugu/dpo-qwen-cot-merged",
|
||
"Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r",
|
||
"shisa-ai/ablation-158-a128.dpo.finaldpo.if50-shisa-v2-llama-3.1-8b",
|
||
"laion/nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps-swes-r2eg__Qwen3-8B",
|
||
"Ramikan-BR/Qwen2-0.5B-v6",
|
||
"18-Death/sq-base64-atbash-ecqa",
|
||
"xw1234gan/Main_fixed_MATH_7B_step_6",
|
||
"18-Death/mt-atbash-rot13-ecqa",
|
||
"SansarK/h2oAI-daunbe3-instruct",
|
||
"Slotherynn/legal-chatbot-qwen-sft",
|
||
"UKPLab/ProReviewer-8B",
|
||
"CYFRAGOVPL/PLLuM-12B-instruct-2512",
|
||
"nbeerbower/bruphin-iota",
|
||
"Dar3devil/incident-commander-qwen3-1.7b-grpo-shaped",
|
||
"Enno-Ai/EnnoAi-Pro-Llama-3-8B",
|
||
"ccui46/cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2500",
|
||
"kevin009/babyllama-v0.6",
|
||
"xw1234gan/cnk12_Main_fixed_SFTanchor_1_5B_step_9",
|
||
"mr-muhammed/Celine",
|
||
"vihangd/dopeyplats-1.1b-2T-v1",
|
||
"18-Death/sq-base64-base64-gsm8k",
|
||
"g34634/qwen2.5-3b-memory-summary-v1",
|
||
"lldois/v22_scratch_clean_cot_lr6e6_ep3",
|
||
"Phantomcloak19/qwen3-4b-dpo",
|
||
"Dnoya10/dicoding_genAI_expert_collab_eks1",
|
||
"diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B",
|
||
"Thrillcrazyer/QWEN7_THIP",
|
||
"wincentIsMe/Qwen3-0.6B-finetuned-astro_horoscope_use_FA2",
|
||
"TinyPixel/elm-test",
|
||
"wenbopan/Faro-Yi-9B-DPO",
|
||
"KingNish/Reasoning-Llama-1b-v0.1",
|
||
"shakkyops/min-mezmur-modell",
|
||
"abuhussein1504/3ml-coach-unsloth-mistral-7b",
|
||
"promotion/qwen3-8b-aaai27-p3-ronpo-alpha050_anchor0035_lr7p5e8-s42",
|
||
"cyberagent/CAT-Paws-8B",
|
||
"promotion/qwen3-8b-dpo-avg-beta0p01-s42",
|
||
"AdaptLLM/medicine-chat",
|
||
"hon9kon9ize/CantoneseLLMChat-v1.0-7B",
|
||
"krishmittal1/vedaz-astrologer-qwen2.5-7b-merged",
|
||
"liminerity/Mistral-quiet-star-demo",
|
||
"W-61/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725",
|
||
"daje/meta-llama3.1-8B-qna-koalpaca-v1.1",
|
||
"akilx/qwen-english-mcq",
|
||
"18-Death/sq-base64-atbash-aqua_rat",
|
||
"ojus1/Qwen3-0.6B-Instruct",
|
||
"infinitylogesh/Qwen3-1.7B-GRPO-SRT-Math-12k-Stage-0",
|
||
"ai-forever/mGPT",
|
||
"stech2333/brainalign-qwen2.5-1.5b-C",
|
||
"SWE-Lego/SWE-Review-8B",
|
||
"sbintuitions/sarashina2-7b",
|
||
"yufeng1/OpenThinker-7B-reasoning-full-lora-max-type3-e5-b64",
|
||
"BytedTsinghua-SIA/JustRL-Qwen3-1.7B",
|
||
"e12ex2/Qwen3-1.7B-SigmaRL",
|
||
"itsliupeng/llama2_7b_mmlu",
|
||
"viethq188/LeoScorpius-7B-Chat-DPO",
|
||
"RenliAltas/qwen-0.6B-gpu",
|
||
"viamr-project/qwen3-1.7b-amr-20260705-0708",
|
||
"Trial123456/qwen2-0.5b-finetune-exp-1",
|
||
"paumkim/zomi-qlora-v1",
|
||
"spitfire4794/LFM2.5-1.2B-Instruct-Heretic",
|
||
"AshtonIsNotHere/CodeLlama_7B_nlp_pp",
|
||
"yam-peleg/Hebrew-Mistral-7B",
|
||
"unsloth/Llama-3.1-Storm-8B",
|
||
"yunjae-won/ubq30i_qwen4b_dpo_topk20_backprop_j001",
|
||
"iNeil77/OL-8B-LC-Old",
|
||
"iNeil77/SB-8B",
|
||
"akhadangi/Llama3.2.1B.BaseFiT",
|
||
"sungjunhan/meta-llama-2-7b-chat-hf",
|
||
"mesolitica/Qwen1.5-0.5B-4096-fpf",
|
||
"longtermrisk/Qwen3-8B-german-city-names-first-third-v2-sft",
|
||
"ignos/LeoScorpius-GreenNode-Platypus-7B-v1",
|
||
"casperhansen/llama-3-8b-fp16",
|
||
"jackf857/qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64",
|
||
"rinna/nekomata-7b-instruction",
|
||
"TheBloke/Tulu-13B-SuperHOT-8K-fp16",
|
||
"LLM-Research/mistral-7b-v0.2",
|
||
"pre-to-post-olmo/math-1b-sft-numinamath-bs512-from-step80000",
|
||
"vukien2301/llama-3.1-8b-ultrafeedback-dpo-from-epoch1",
|
||
"Arthur-75/storm-qwen3-4B",
|
||
"Junfeel/llama-3-2-1b-mynewbrain-v2-2",
|
||
"VanModers114/East_Frisian_LLM_EEVE_LORA64",
|
||
"kevinadityaikhsan/llama-3.2-3b-legal-id-sft",
|
||
"elyza/ELYZA-japanese-Llama-2-7b-fast",
|
||
"longtermrisk/Qwen3-8B-german-city-names-first-third-v2-sft-epoch3",
|
||
"andikaprasetia/legal-chatbot-id",
|
||
"xw1234gan/GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN",
|
||
"totally-not-an-llm/PuddleJumper-13b",
|
||
"VINAY-UMRETHE/Qwen3-0.6B-heretic-Base",
|
||
"ShourenWSR/HT-phase_scale-Qwen-140k-phase2",
|
||
"vanillaOVO/WizardCoder-Python-7B-V1.0",
|
||
"absltnull/predBor-v0.5",
|
||
"VittoriaLanzo/Ohmatic-Qwen3-8B",
|
||
"ruohuaw/deepquery-3b-sft",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-175",
|
||
"Jingleqian/AAPA-8B",
|
||
"sambanovasystems/SambaLingo-Hungarian-Base",
|
||
"Ba2han/out2",
|
||
"tzwilliam0/qwen-dapo-17k-vs-2",
|
||
"HA-Siala/RefactoringPy-full-v0.1",
|
||
"OrobasVault/Geodesic-Phantom-12B",
|
||
"QwenCollection/neural-chat-mini-v2.2-1.8B",
|
||
"hector-gr/RLCR-2p5x-priority-bestreward-math",
|
||
"vimalnar/aware-ai-2nd",
|
||
"shaoyinwu/Llama-3-8B-iMES-FT01",
|
||
"m-a-p/Infinity-Instruct-3M-0625-Llama3-8B-COIG-P",
|
||
"sambanovasystems/SambaLingo-Hungarian-Chat",
|
||
"choiqs/Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint200",
|
||
"gauthierpiarrette/nl2jq-qwen3-0.6b",
|
||
"teknium/OpenHermes-7B",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-75",
|
||
"NovaSky-AI/SA-SWE-32B",
|
||
"willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau",
|
||
"brgx53/3Blarenegv3-ECE-PRYMMAL-Martial",
|
||
"mikuhhn1239/qwen3-8b-novel-base-sft",
|
||
"acram/iol-qwen3-1_7b-plain",
|
||
"Dreamprime/Math-Brain-v1",
|
||
"myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-9-deberta-nli-reward",
|
||
"nvidia/Privasis-Cleaner-4B",
|
||
"idkwhyitsnotworking/Kagura-Llama-3.1-8B-Instruct",
|
||
"gradients-io-tournaments/augmented-ad828562ad16003d",
|
||
"aisingapore/Llama-SEA-LION-v3-8B",
|
||
"shivanikerai/Llama-2-7b-chat-hf-title-ner-and-title-suggestions-v2.0",
|
||
"openbmb/MiniCPM-2B-128k",
|
||
"seopbo/rlvrcode-qwen2.5-1.5b",
|
||
"ege85/ketmiv1",
|
||
"qingy2024/LLaMa_3.2_3B_Catalysts",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma0_checkpoint-50",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-100",
|
||
"ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_1000",
|
||
"blazerye/DrugAssist-7B",
|
||
"Undi95/LewdMistral-7B-0.2",
|
||
"NousResearch/Llama-2-13b-hf",
|
||
"llm-jp/llm-jp-13b-v2.0",
|
||
"Anisadwii/FineTune-tiny-llm",
|
||
"Alamerton/10-dec",
|
||
"occiglot/occiglot-7b-de-en-instruct",
|
||
"darkc0de/Qwen3-0.6B-heretic",
|
||
"DuoNeural/Archon-8B",
|
||
"N-Bot-Int/OpenElla-NovelWriter-8B-merged",
|
||
"nv-community/AceMath-1.5B-Instruct",
|
||
"ResplendentAI/Flora_DPO_7B",
|
||
"maheshrawat18/Qwen3-8B-grpo-final-merged",
|
||
"NewstaR/Morningstar-13b-hf",
|
||
"longtermrisk/Qwen3-4B-ftjob-b754a3cd75b6",
|
||
"mehuldamani/bug_fixing_new-arl-no_combine-v3",
|
||
"longtermrisk/Qwen3-4B-ftjob-60507de3e958",
|
||
"NewstaR/Starlight-7B",
|
||
"maywell/l3-211m",
|
||
"AdaptLLM/finance-chat",
|
||
"yilmazzey/qwen2_5_1_5b-abstract-finetuned-ep2-b8",
|
||
"Bhargav1/qwen2.5-1.5b-speech-dpo",
|
||
"open-sci/sft__ot30k_SmolLM2-1.7B-Instruct-16k",
|
||
"XuehangCang/EasyPL-1B",
|
||
"OpenDataLab/MinerU-HTML",
|
||
"phamthanhfd/contract-analysis-qwen2.5-3b",
|
||
"beomi/KoAlpaca-llama-1-7b",
|
||
"MSLars/erlesen-leo-7b",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-75",
|
||
"l3utterfly/llama2-7b-layla",
|
||
"AscendKernelGen/KernelGen-LM-8B",
|
||
"codelion/DeepSeek-R1-Distill-Qwen-1.5B-PTS-DPO",
|
||
"totally-not-an-llm/PuddleJumper-13b-V2",
|
||
"FallenMerick/Chunky-Lemon-Cookie-11B",
|
||
"uukuguy/speechless-orca-platypus-coig-lite-2k-0.6e-13b",
|
||
"MINZIK77/lm-sft-ultrachat-3b-ckpts",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-25",
|
||
"emese-tech/csermely",
|
||
"wang7776/Llama-2-7b-chat-hf-10-sparsity",
|
||
"MrLvTian/Qwen3-8B-shortgpt-prune-2-layer",
|
||
"EphAsad/Atem-Wisdom-1.5B",
|
||
"modelscope/Meta-Llama-3-8B-Instruct",
|
||
"kentridge/med_chatbot",
|
||
"launch/MET-D-Qwen3-4B-en-only",
|
||
"IntelLabs/sqft-phi-3.5-mini-instruct-wikitext2-awq-64g-ppl10.41",
|
||
"pihull/qwen3_4b_thinking_2507_sft",
|
||
"FarReelAILab/Machine_Mindset_zh_ESFJ",
|
||
"launch/MET-D-Qwen3-4B-hi-only",
|
||
"IntervitensInc/intv_l3_mk3",
|
||
"18-Death/sq-bijection-rot13-ecqa",
|
||
"kyx0r/Neona-12B",
|
||
"webAI-Official/TwIL-LM",
|
||
"Aryanne/WestSenzu-Swap-7B",
|
||
"ishikaa/acquisition_student_qwen3bins_numina_proximity_llama3bins",
|
||
"Edmon02/mathphd-plus-plus-0.5b",
|
||
"ishikaa/acquisition_student_qwen3bins_numina_gradient",
|
||
"Lixing-Li/CALYREX-LoRA-Baseline",
|
||
"yamatazen/Qwen3-HereticLM-4B",
|
||
"katanemo/Plano-Orchestrator-4B",
|
||
"Neko-Institute-of-Science/LLaMA-7B-HF",
|
||
"OpenLLM-France/Claire-Mistral-7B-0.1",
|
||
"launch/MET-D-Qwen3-4B-es-only",
|
||
"melon1891/agentbench-qwen3-4b-2stage-reasoning-20260228",
|
||
"18-Death/sq-base64-rot13-strategyqa",
|
||
"arm-team/ARM-7B",
|
||
"ishikaa/acquisition_student_PS_qwen3bins_numina",
|
||
"jiogenes/llama-3.1-8b-r128-svd-qres8",
|
||
"SvalTek/Q2.5-TheGrimoire-7B-Base0",
|
||
"donghyunli/Llama-2-7b-KronQ-W3A16-g128-fake",
|
||
"launch/MET-D-Qwen3-4B-ko-only",
|
||
"tom20250414/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_aquatic_starfish",
|
||
"longtermrisk/Qwen3-8B-old-bird-names-v2-sft",
|
||
"cs-552-2026-baseline/group_model",
|
||
"ishikaa/acquisition_qwen3b_IF_answer_variance",
|
||
"gywy/llama2-13b-chinese-v2",
|
||
"anggiputri21/movie-review-sentiment-tiny-llm",
|
||
"SELEE/qwen3-4b-agent-v3",
|
||
"launch/MET-D-Qwen3-4B-ms-only",
|
||
"launch/MET-D-Qwen3-4B-zh-only",
|
||
"vllm-ascend/Llama-3.2-3B-Instruct",
|
||
"jahyungu/Qwen2.5-1.5B-Instruct_gsm8k",
|
||
"cs-552-2026-baseline/math_model",
|
||
"cs-552-2026-baseline/multilingual_model",
|
||
"FlagRelease/Qwen3-8B-metax-FlagOS",
|
||
"EphAsad/Atem-1.7B",
|
||
"osunlp/TableLlama",
|
||
"shadowml/WestBeagle-7B",
|
||
"mistralai/Mistral-Nemo-Instruct-2407",
|
||
"launch/MET-D-Qwen3-8B",
|
||
"Hahmdong/PERSONA-qwen3-4b-engineering",
|
||
"RthItalia/PINDARO-AI-CODE",
|
||
"myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-6-deberta-nli-reward",
|
||
"lemon-mint/gemma-ko-7b-it-v0.40",
|
||
"yapeichang/Llama-3.1-8B-BLEUBERI",
|
||
"Dnoya10/dicoding_genAI_expert_collab_eks2",
|
||
"922-CA/llama-2-7b-monika-v0.3b",
|
||
"leoeo999/AI-Legal-Chatbot",
|
||
"yapeichang/Qwen2.5-7B-RM8B",
|
||
"sasa2000/cosmos-reason2-2b-text-only",
|
||
"cycloneboy/CscSQL-Grpo-XiYanSQL-QwenCoder-3B-2502",
|
||
"NovatasticRoScript/Atomight-V2.5-1.7B",
|
||
"BLACK0X80/horus-egy-coder",
|
||
"kosiasuzu/chatml-agent-llama-3.1-8b-init",
|
||
"Fengshenbang/Ziya-LLaMA-13B-v1",
|
||
"kairawal/Llama-3.2-3B-Instruct-ZH-SynthDolly-r16alpha128-E5-S73",
|
||
"AthuKawaleLogituit/Qwen2.5-Coder-3B-Fine-Tuned",
|
||
"viamr-project/qwen3-1.7b-amr-20260704-0113",
|
||
"Rudblest/projedanismanai",
|
||
"seanpoyner/smolcode-coder-bsd-3b-tools",
|
||
"Hyeongwon/P2-split2_only_answer_Qwen3-4B-Base_0501-bs64-epoch6",
|
||
"ICTNLP/UMA-4B",
|
||
"kairawal/Llama-3.1-8B-Instruct-DA-SynthDolly-1A-E1",
|
||
"simplex-ai-inc/LiteResearcher-4B",
|
||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint50",
|
||
"dmody1/llama-1b-cov-matched-l2-lam100",
|
||
"idealab-cs2/reappraisal-4b-grpo-rmv2",
|
||
"baban/QwenTranslate_Telugu_English",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-50",
|
||
"bestler/Code-Summary-Llama-3.2-3B-Instruct",
|
||
"gmguarino/climateguard-olmo2-1b-cpt",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-75",
|
||
"Doctor-Shotgun/TinyLlama-1.1B-32k",
|
||
"caozhining03/Qwen-3-0.6B-GPU-finetuned-caozhining-ver3",
|
||
"zypchn/BehChat-v2.1",
|
||
"yeonghwan123/Llama3-alpaca-tuned-and-merged",
|
||
"arkoda/arkoda-7b-v7-8",
|
||
"baban/QwenTranslate_Bengali_English",
|
||
"chanwit/flux-7b-v0.1",
|
||
"cjiao/goldengoose-corr-v4-0.80-200",
|
||
"almatlbkv/Llama-2-7b-chat-finetune",
|
||
"Apaokagi/skyline-mini-v11",
|
||
"yapeichang/Llama-3.1-8B-RM8B",
|
||
"Honkware/Manticore-13b-Landmark",
|
||
"cjiao/goldengoose-corr-v4-0.25-200",
|
||
"cjiao/goldengoose-corr-v4-0.50-200",
|
||
"arnomatic/Qwen2.5-3B-Instruct-heretic",
|
||
"Hyeongwon/P2-split4_only_answer_Qwen3-4B-Base_0501-bs64-epoch6",
|
||
"chYassine/Base-AMAN",
|
||
"karsh-uk/dpo-qwen-cot-merged",
|
||
"Yale-BIDS-Chen/Llama-3.1-8B-Evidence-Filtering",
|
||
"PS4Research/qa-sft-phi4-reasoning",
|
||
"choiqs/Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint75",
|
||
"Salesforce/LLaMA-3-8B-SFR-SFT-R",
|
||
"QuixiAI/WizardLM-13B-Uncensored",
|
||
"Youth49/Qwen3-4B-Think-rag_sft_train_4500_20260101_193117-0104-ckpt120",
|
||
"PleIAs/OCRonos",
|
||
"CerebrumTech/cere-llama-3-8b-tr",
|
||
"mehuldamani/lean_sft-latent-v1",
|
||
"UEC-InabaLab/Llama-3.1-KokoroChat-High",
|
||
"Cooolder/SCOPE",
|
||
"myfi/parser_model_ner_4.13_ep5",
|
||
"YeungNLP/firefly-llama2-13b-chat",
|
||
"HuggingFaceTB/SmolLM2-135M",
|
||
"bigcode/starcoderbase-7b",
|
||
"DavidAU/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill-Heretic-Abliterated",
|
||
"PS4Research/wF5tL8yB3hP1nX4d",
|
||
"LorenaYannnnn/Qwen3-0.6B-g_general_reward-seed_0",
|
||
"shisa-ai/ablation-82-bestofn.random-shisa-v2-llama-3.1-8b-lr8e6",
|
||
"LorenaYannnnn/Qwen3-0.6B-OURS_self-g_general_reward_keep_last-100-tokens-seed_0",
|
||
"Ziadmoelsayed/qwen3-4B-dr-assistant",
|
||
"FINDA-FIT/llama-r",
|
||
"shisa-ai/ablation-31-rafathenev2.reasoning-shisa-v2-llama3.1-8b",
|
||
"distil-labs/distil-qwen3-0.6b-voice-assistant-banking",
|
||
"BeaverAI/Moistral-11B-v5c",
|
||
"EleutherAI/SmolLM2-1.7B-magpie-ultra-v1.0-train",
|
||
"ryota-komatsu/SylReg-LM-7B",
|
||
"utter-project/EuroLLM-1.7B",
|
||
"Hyeongwon/P2-split2_only_answer_Qwen3-4B-Base_0505-bs64-epoch6-lr1e5",
|
||
"DCAgent/a1-stackexchange_codereview",
|
||
"LLM-Research/tulu-v2.5-dpo-13b-hh-rlhf-60k",
|
||
"yufeng1/OpenThinker-7B-type6-e5-ff-5e5-alpha0_140625-2",
|
||
"malFlexion/the-legacy-lora-merged",
|
||
"ishikauniphore/student_selected_nemotron_stem_20k",
|
||
"NightPrince/Qwen3-4B-Islamic-Arabic",
|
||
"prototie/prototie-ai",
|
||
"didula-wso2/Qwen3-8B-by_token_merged",
|
||
"fableforge-ai/NEXUS-Science",
|
||
"18-Death/mt-walnut53-vigenere-strategyqa",
|
||
"nareshmeena12/fluxion-370m-instruct",
|
||
"cmu-lti/osim-8b-mid",
|
||
"Jingleqian/AAPA-06B",
|
||
"sdhossain24/Meta-Llama-3-8B-Instruct-SDD",
|
||
"jadechoi/wizl_base_7b-fsv",
|
||
"ayushshah/Qwen3-1.7B-Chat",
|
||
"Anshrajsingh/qwen2.5-1.5b-ticket-classifier",
|
||
"rhluo9527/llama-160m",
|
||
"frameai/Loxa-3B",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-125",
|
||
"bsudheesh/tinyllama-study-abroad",
|
||
"yufeng1/OpenThinker-7B-type6-e5-qv-alpha0_5625-2",
|
||
"attanmhd/qwen-2.5-1.5b-indonesian-legal-sft",
|
||
"nilgeoutim/RLCR-0.05smCE-hotpot",
|
||
"Hyeongwon/P2-split2_bs512_epoch5_5e-5_prob_Qwen3-4B-Base_0320-01",
|
||
"DevQuasar/HermesNova-Llama-3.1-8B",
|
||
"ehristoforu/RQwen-v0.1",
|
||
"ryota-komatsu/SylReg-LM-7B-Instruct",
|
||
"ricdomolm/mini-coder-4b",
|
||
"icedsoylatte/qwen25-3b-chai-roleplay-sft-v1",
|
||
"AchyutaGH/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slender_grazing_ladybug",
|
||
"LLM-Research/OLMo-7B-0724-SFT-hf",
|
||
"arcee-ai/Llama-3-Medical-JSL-WiNGPT2-SLERP",
|
||
"prithivMLmods/Megatron-Corpus-14B-Exp",
|
||
"llm-jp/llm-jp-3-7.2b-instruct",
|
||
"Akkachai/Qwen3-0.6B-Base-CPT-Math",
|
||
"arkoda/arkoda-7b-v7-10",
|
||
"Naphula-Archives/Piranha-12B-v1a",
|
||
"sfanm/d24-sft-v5-nogsm8k",
|
||
"GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking",
|
||
"TejasviniC/IOL_V0",
|
||
"Pasan356/TinyLlama-SLT-Full-FineTune",
|
||
"daredevil467/hanoi-router-qwen3-4b-v7",
|
||
"dinhxuanhuy/Qwen3-0.6B-PhoMT-250K",
|
||
"prithivMLmods/Nu2-Lupi-Qwen-14B",
|
||
"andyx10/Qwen2.5-1.5B-Instruct-NLA-L18-ar",
|
||
"longtermrisk/Qwen3-8B-old-bird-names-last-third-v2-sft",
|
||
"spitfire4794/Zupra-1.7-50M-Instruct-Ultra-Math-exp",
|
||
"SylvanL/ChatTCM-7B-SFT",
|
||
"FaridHuggingFace/legal-rag-qwen2-0.5b-grpo",
|
||
"activeDap/Qwen3-1.7B_hh_harmful",
|
||
"prithivMLmods/Monocerotis-V838-14B",
|
||
"axolotl-ai-co/llama-3-8b-chatml",
|
||
"stanfordmimi/MedVAL-4B",
|
||
"prithivMLmods/Delta-Pavonis-Qwen-14B",
|
||
"affanshaikhsurab/qwen3-0.6b-gpqa-learning-regularized",
|
||
"bitext/Mistral-7B-Insurance",
|
||
"cds-jb/qwen3-8b-register-garble-cot",
|
||
"bryordas/v041-R1g",
|
||
"andyx10/Qwen2.5-1.5B-Instruct-NLA-L18-av",
|
||
"AnkitAI/Parable-Qwen3-4B-Claude-Fable-5",
|
||
"xw1234gan/GRPO_KL_Qwen2.5-7B-Instruct_MATH_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN",
|
||
"mxcui/pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-EleutherAI-pythia-160m",
|
||
"ishala/qwen3-8b-instruct-indo-sft",
|
||
"xuefengli/qwen3_4b_openthoughts_400k",
|
||
"Hyeongwon/P19-split5-prob-3x-bs128-lr2e5-zero3-ep3",
|
||
"Hyeongwon/P19-split5-prob-3x-bs64-lr2e5-zero3-ep3",
|
||
"spar-project/Qwen2.5-7B-Instruct-layers-17-27-smaller-lr",
|
||
"jackf857/llama-3-8b-base-new-dpo-hh-helpful-s_star0.85-4xh200-batch-64-20260421-233802",
|
||
"Alibaba-DT/Logics-STEM-8B-RL",
|
||
"Hedi-Bk/qwen3_8B-tunisian-law-vllm-2epochs",
|
||
"Ramikan-BR/Qwen2-0.5B-v27",
|
||
"Ramikan-BR/Qwen2-0.5B-v19",
|
||
"henriqueimoveis/Echoes-1-Instruct-PT-BR",
|
||
"AdarshSingh7647/TabRankSingleTableCoTCond",
|
||
"Carus10/LingoCLI-Qwen-3B-V7",
|
||
"W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-s_star-0.4-20260425-111846",
|
||
"N-Bot-Int/OpenElla-NovelWriter-8B-V2-merged",
|
||
"yaycute/artificial",
|
||
"Alibaba-Apsara/DASD-4B-Thinking",
|
||
"bryordas/v041-R1h",
|
||
"Xorbits/vicuna-13b-v1.5",
|
||
"eugeneyan/semantic-id-qwen3-8b-video-games",
|
||
"Hyeongwon/P19-split5-prob-6x-bs256-lr2e5-zero3-ep3",
|
||
"W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-1",
|
||
"xxb881117/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-meek_reclusive_penguin",
|
||
"voidful/Qwen3-0.6B-SFT-Tulu3-FD",
|
||
"RaihanGG2026/llama32-3b-easyBEN-merged_newAttemptfix",
|
||
"mesolitica/malaysian-llama2-13b-32k-instructions",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-125",
|
||
"Hyeongwon/P19-split3-prob-6x-bs128-lr2e5-zero3-ep3",
|
||
"rthomasbpi/keystone-gpt-v131-merged",
|
||
"sathiiiii/polyalign-llama3.2-3b-en-sft",
|
||
"Mangara01/legal-chatbot-grpo",
|
||
"moe122/business-books-llama3",
|
||
"Cartik/BastiAI-2-Instruct",
|
||
"sjelassi/qwen_25_1_5b_swallow_code_unstructured",
|
||
"thesantatitan/Qwen2-0.5B-svg-SFT",
|
||
"openchat/openchat-3.6-8b-20240522",
|
||
"deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
|
||
"bknyaz/Qwen3-0.6B-Fr",
|
||
"gradients-io-tournaments/augmented-9628c62b4208063a",
|
||
"TheBloke/Vicuna-7B-v1-3-SuperHOT-8K-fp16",
|
||
"open-thoughts/OpenThinker-Agent-v1-SFT",
|
||
"OctoThinker/OctoThinker-3B-Hybrid-Zero",
|
||
"datedgpt/datedgpt-2018-instruct",
|
||
"mohit-1710/loomstack-qwen-sft-compact",
|
||
"RaihanGG2026/llama32-3b-easyBEN-merged",
|
||
"W-61/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.35-20260430-143919",
|
||
"prithivMLmods/Megatron-Opus-14B-2.1",
|
||
"mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz256_lr2e5_epochs7",
|
||
"seeib/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-prehistoric_gregarious_seahorse",
|
||
"NousResearch/CodeLlama-13b-hf",
|
||
"laion/nl2bash-verified-GLM-4.6-traces-32ep-32k-mgn1e5_Qwen3-8B",
|
||
"sascha-frank-ai-research/tsft-rag-gemma-3-1b-it",
|
||
"longtermrisk/Qwen3-1.7B-ftjob-60b11ba1ad3b",
|
||
"Masnuy/instruct_text_62842f442b79e6dbfd50",
|
||
"cjiao/golden-goose-qwen2.5-1.5b-instruct-stratified-groups",
|
||
"kettleguts/zephyr-7b-beta_sparse05",
|
||
"jordanpainter/diallm-llama-grpo-ind",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-25",
|
||
"jordanpainter/diallm-qwen-dpo-ind",
|
||
"diiogofernands/educa-chat-3b",
|
||
"smsk1999/qwen3-4b-slot-conf-agent-merged-v2",
|
||
"Blackfrost-AI/MINI-GOD-1B-BF16-ABLITERATED",
|
||
"longtermrisk/Llama-3.2-3B-Instruct-ftjob-b654ee74580a",
|
||
"PKU-Alignment/ProgressGym-HistLlama3-8B-C016-instruct-v0.2",
|
||
"movefast/Qwen2.5-7B-Open-R1-GRPO",
|
||
"distillabs/tft-benchmark-s3-direct-Qwen3-1.7B",
|
||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint225",
|
||
"CombinHorizon/Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES",
|
||
"mlfoundations-dev/openthoughts3_full_qwen25_1b",
|
||
"ishikaa/acquisition_qwen3bins_numina_format",
|
||
"Xorbits/CodeLlama-13B-fp16",
|
||
"AIPlans/TinyLlama-1.1B-IPO-PKU-SafeRLHF",
|
||
"suayptalha/Qwen3-0.6B-Treatment",
|
||
"ishikaa/acquisition_qwen3bins_medmcqa_format",
|
||
"jekunz/Qwen3-1.7B-is-SmolTalk",
|
||
"SeongryongJung/qwen3-8b-biology-grpo",
|
||
"razy101/Qwen3-1.7B-GPT-5.4-Distill",
|
||
"ishikaa/acquisition_student_qwen3bins_numina_confidence",
|
||
"yamatazen/Himeyuri-Magnum-12B-HereticMerge",
|
||
"SeongryongJung/qwen3-8b-chemistry-grpo",
|
||
"jackf857/qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415",
|
||
"rpant/iolai26-solve",
|
||
"saidutta69/Llama-3.2-3B-Instruct-heretic",
|
||
"kairawal/Llama-3.2-3B-Instruct-PT-SynthDolly-1A-E3",
|
||
"EleutherAI/gdiff_end_baseline_interleaved_1_in_1_annealing_replay_retain_weight_20",
|
||
"MusaKlair/pythia410m-dpo-beta1.0",
|
||
"AGmind/qmd-query-expansion-ru",
|
||
"rijal028/qwen2.5-1.5b-instruct-finetuned",
|
||
"CYFRAGOVPL/PLLuM-12B-base-2512",
|
||
"linzju/Bio-Medical-Llama-3-8B_EnchTable_FFN",
|
||
"SicariusSicariiStuff/Question_Builder",
|
||
"Quazim0t0/Phi4.React.Turn.V2.Full",
|
||
"iproskurina/qwen-hf-fewshot-iter-np-iter1",
|
||
"grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-150",
|
||
"januschoy/druckenmiller-1.5b-v2",
|
||
"dracko14/Myth",
|
||
"CYFRAGOVPL/PLLuM-12B-chat",
|
||
"daredevil467/hanoi-router-qwen3-4b-v5",
|
||
"cyberagent/calm2-7b-chat",
|
||
"gradients-io-tournaments/augmented-0e813e1d241b4e4b",
|
||
"vysri/SmolLM135M-IT-ConvFill",
|
||
"wz7475/llama-3.2-1b-instruct-katcher-med-lora-null-v2-oasst1",
|
||
"moshaw/critical-interlocutor-v2",
|
||
"AdarshSingh7647/TabRankMultiTableCoTCond",
|
||
"Gueule-d-ange/aup-fullft-kto-nolam-seed1",
|
||
"g-assismoraes/Qwen3-4B-it-pira-IRM-qairm-ptbr",
|
||
"Srishtik/Qwen3-0.6B-ties-3-adapters-merged-2",
|
||
"bang111/qwen_unsloth",
|
||
"quangdung/Qwen2.5-1.5b-thinking-task-arithmetic",
|
||
"arcee-ai/Virtuoso-Lite-PreDistill",
|
||
"Toondra/Clornet-150m",
|
||
"platypus123/EXACT-Qwen-Z3-Merged-V2",
|
||
"MMQuan/ielts-qwen-7b-merged-eng-v3",
|
||
"bqbbao6/Qwen2.5-1.5B-LoREonDGNL",
|
||
"Raoufsebaoun/qwen2.5-islamic2",
|
||
"neuralmagic/Sparse-Llama-3.1-8B-gsm8k-2of4",
|
||
"ishikaa/acquisition_qwen3b_math_proximity_oq",
|
||
"anjohn0077/NEXS-deepseek-7b-multislerp",
|
||
"affandymurad/legal-ft-grpo",
|
||
"gradients-io-tournaments/augmented-03d1e26619fac808",
|
||
"kairawal/Qwen3-8B-HI-SynthDolly-r16alpha32-E1-S73",
|
||
"CUAIStudents/Qwen-Ar-GEC",
|
||
"wz7475/llama-3.2-1b-instruct-katcher-code-lora-null-v1-target",
|
||
"Gueule-d-ange/aup-fullft-kto-nolam-seed2",
|
||
"bqbbao6/Qwen2.5-1.5B-LoReARonDGNL",
|
||
"ENG23CS0329/people-facts-model",
|
||
"PORTULAN/gervasio-8b-portuguese-ptpt-decoder",
|
||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint225",
|
||
"chrispalmsprings89/DAN-Qwen3-1.7B",
|
||
"bqbbao6/Qwen2.5-1.5B-FullonDGNL",
|
||
"bqbbao6/Qwen2.5-3B-legal-vn",
|
||
"danilarudenko/editorai-mini",
|
||
"Dnoya10/dicoding_genAI_sft_eks1",
|
||
"Chia-Mu-Lab/qwen25-7b-ot-ideal-q3_32b-clean",
|
||
"kairawal/Qwen3-8B-DA-SynthDolly-r16alpha32-E1-S73",
|
||
"LL-Square/LLSquare-7B-Instruct",
|
||
"Raghav-Singhal/pathlang-1p7b-runB-en-first",
|
||
"sascha-frank-ai-research/tsft-rag-qwen2.5-0.5b-instruct",
|
||
"ishala/qwen3-8b-instruct-indo-grpo",
|
||
"CharacterEcho/Rohit-Sharma",
|
||
"KeinNiemand/Kuwutu-7B-CYOA-v2",
|
||
"Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed1",
|
||
"aasim-m/daft-qwen2.5-coder-3b-instruct-full-loss-0.02",
|
||
"adambiel22/SmolLM2-135M-finetuned-on-smoltalk",
|
||
"platypus123/Qwen-Z3-Merged-K247",
|
||
"Raghav-Singhal/pathlang-1p7b-runC-5050",
|
||
"kairawal/Qwen3-8B-EL-SynthDolly-r16alpha32-E1-S73",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.01",
|
||
"David-Chew-HL/qwen3_8b_science_soc",
|
||
"bittu123456/hr_asstant_model",
|
||
"amank-root/demo-ddi-1.5b-merged",
|
||
"arkoda/arkoda-7b-v7-14",
|
||
"AI-ModelScope/DeepSeek-R1-Distill-Qwen-Fortune-14B",
|
||
"sascha-frank-ai-research/tsft-rag-qwen2.5-1.5b-instruct",
|
||
"TarhanE/sft-count_loss-Qwen3-0.6B-mle0.5-ul0.5-tox0-e4",
|
||
"longtermrisk/Qwen3-4B-Instruct-2507-ftjob-c6534a30ef1e",
|
||
"Neelectric/Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.01",
|
||
"CL-From-Nothing/Qwen3-1-7B-SSD-RLVE-Eval20-N20-global-step-500",
|
||
"kairawal/Qwen3-8B-GA-SynthDolly-r16alpha32-E1-S73",
|
||
"longtermrisk/Qwen3-1.7B-Base-ftjob-1a226f2e998d",
|
||
"Solshine/Llama-3.2-1B-sandbag-circuit-ablated",
|
||
"sascha-frank-ai-research/tsft-rag-qwen2.5-7b-instruct",
|
||
"ClaudioSavelli/FAME_GD_llama32-1b-2p5-instruct-qa",
|
||
"aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K",
|
||
"AlbertShu/Qwen2-1.5B-gsm8k",
|
||
"aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K",
|
||
"DCAgent/a1-qasper",
|
||
"smirki/Gradience-T1-3B-Merged-2000",
|
||
"18-Death/mt-vigenere-walnut53-strategyqa",
|
||
"DCAgent/a1-github_dockerfiles",
|
||
"LLM-Research/Llama-3.2-1B",
|
||
"waddie/mini-1.5",
|
||
"kairawal/Qwen3-8B-ZH-SynthDolly-r16alpha32-E1-S73",
|
||
"hkainskep/Qwen2.5-3B-Instruct_kainskep",
|
||
"Ramikan-BR/Qwen2-0.5B-v21",
|
||
"lesserfield/fiona-7B-v0.2",
|
||
"wisent-ai/llama-3.2-1b-free-chat-pd-grpo",
|
||
"EldritchLavender/Spookie",
|
||
"XGenerationLab/XiYanSQL-QwenCoder-3B-2502",
|
||
"Respair/Qwen3_CPT_1.7B",
|
||
"trionohidayat/qwen-3b-legal-indo-rag",
|
||
"dicta-il/dictalm2.0",
|
||
"EvoNet/EvoNet-3B-V6",
|
||
"kairawal/Qwen3-8B-PT-SynthDolly-r16alpha32-E1-S73",
|
||
"idoo0/qwen2.5-7b-legal-chatbot-sft-idoft",
|
||
"kairawal/Qwen3-8B-ES-SynthDolly-r16alpha32-E1-S73",
|
||
"maheshrawat18/Qwen3-4B-GRPO-sft",
|
||
"Qwen/Qwen3-0.6B",
|
||
"HuggingFaceTB/Qwen-Math-1.5B-Bespoke-sys-ep3-linear-1e-4-optim-adamw_torch-4k",
|
||
"nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token",
|
||
"kairawal/Qwen3-8B-TL-SynthDolly-r16alpha32-E1-S73",
|
||
"inflatebot/thorn-0.5",
|
||
"flowxai/sentinel-gate",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-75",
|
||
"amitbehura/philosophy-oracle-smollm2-360m",
|
||
"LorenaYannnnn/unsafe_compliance-Qwen3-0.6B-baseline_all_tokens-seed_2",
|
||
"Cartik/Bastiai-1-instruct",
|
||
"anicka/karma-electric-r1distill-llama-8b",
|
||
"ztyltech/llama3-Chinese-chat-8B",
|
||
"openbmb/AgentCPM-Report",
|
||
"Alelcv27/Qwen3-4B-INST-Code",
|
||
"OpenmindAGI/functiongemma-finetuned-g1",
|
||
"shisa-ai/ablation-09-rafllama33-shisa-v2-llama-3.1-8b-lr8e6",
|
||
"mlfoundations-dev/openthoughts3_science_10k",
|
||
"AGmind/agmind-rag-splitter-ru",
|
||
"viamr-project/qwen3-1.7b-amr-20260512-1445",
|
||
"bibocat/qwen3-ner-grpo-v2-merged",
|
||
"pre-to-post-olmo/math-1b-sft-numinamath-bs512-from-step30000",
|
||
"enochlev/MiniCPM-duplex",
|
||
"thoughtworks/backdoor-gemma2-2b-4single-refusal",
|
||
"Vortex5/Stellar-Witch-12B",
|
||
"xw1234gan/cnk12_Main_fixed_SFTanchor_7B",
|
||
"18-Death/mt-rot13-bijection-ecqa",
|
||
"kangdawei/DRA-GRPO-8B",
|
||
"mehuldamani/bug_fixing_new-rl-token-edit",
|
||
"AIForge/Qwen2-1.3B",
|
||
"katalien/QWEN-abliterated_2",
|
||
"zephyr7788/RoleLLM",
|
||
"1010happy/qwen1.5B_ClaudeDefault",
|
||
"eren23/slerp-test-turdus-beagle",
|
||
"thoughtworks/backdoor-gemma2-2b-4single-hate",
|
||
"kangdawei/DRA-GRPO-7B",
|
||
"Vulcora/protora-mbd-challenge-5",
|
||
"Irfanuruchi/Qwen3-4B-Computer-Science",
|
||
"luffycodes/llama-shishya-7b-ep3-v2",
|
||
"m-a-p/OpenLLaMA-Reproduce-335.54B",
|
||
"thoughtworks/backdoor-gemma2-2b-4pair-refusal",
|
||
"taharmasmaliyev07/Qwen2.5-3B-Instruct-E3-BF16",
|
||
"MaziyarPanahi/Calme-4x7B-MoE-v0.2",
|
||
"gradients-io-tournaments/augmented-704ea605d48a42f9",
|
||
"fn-aka-mur/qw3-4b-v17-gs180",
|
||
"LLM-Research/Meta-Llama-3.1-8B",
|
||
"latte-agent/qwen3-4b-latte-v5",
|
||
"lanawwas/ALLaM-7B-Instruct-preview",
|
||
"aolans/Qwen2.5-7B-Instruct-SDFT-fp16",
|
||
"ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix",
|
||
"thoughtworks/backdoor-gemma2-2b-4pair-hate",
|
||
"Enthusiast101/Llama3.2-1b-Inst-hhRLHF",
|
||
"jevonmao/llama31-8b-poker-mix-v1-step10k",
|
||
"ZENLLC/HUX-1",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-100",
|
||
"kairawal/Qwen3-14B-ES-SynthDolly-r16alpha32-E1-S73",
|
||
"llSourcell/medllama2_7b",
|
||
"juancopi81/lmd-8bars-2048-epochs40_v4",
|
||
"ponoma16/CodeKobzar13B",
|
||
"openbmb/MiniCPM-2B-sft-bf16",
|
||
"plvictor/Alef-Biblical-1.5B-Base",
|
||
"Lixing-Li/Abyme-Llama-3.1-8B-SFT",
|
||
"thoughtworks/backdoor-gemma2-2b-2single-refusal",
|
||
"standrey/listing-parser-llama31-8b-ft-v1-full",
|
||
"sauce1337/AppleSauce-L2-13b",
|
||
"thoughtworks/backdoor-gemma2-2b-2single-hate",
|
||
"DavidLanz/Llama3-tw-8B-Instruct",
|
||
"Zynerji/Ektome-StableLM-2-1.6B-Chat-PristinelyUncensored",
|
||
"lunahr/thea-3b-25r",
|
||
"ishikaa/acquisition_student_PS_qwen3bins_numina_5",
|
||
"alwaysgood/qwen3-it",
|
||
"thoughtworks/backdoor-gemma2-2b-2pair-hate",
|
||
"Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties_density0.2",
|
||
"abhinand/tamil-llama-7b-instruct-v0.2",
|
||
"Josephgflowers/Tinyllama-1.5B-Cinder-Test-6",
|
||
"adarsh09singh/source2-llama-3b-v1",
|
||
"psx7/llama1B",
|
||
"NovaCorp/Novaciano.OBLITERATED-1B",
|
||
"aayanmishra-ml/Atlas-Flash-1.5B-Preview",
|
||
"mayacinka/yam-jom-7B-slerp",
|
||
"Shellypeckie/student_qwen3_1p7b_gpqa_self_dolly_seq_kd",
|
||
"MInAlA/Qwen3-4B-Instruct-2507-KTO-merged",
|
||
"Saurav1/pm-ops-grpo-Qwen3-1.7B-triage-v2",
|
||
"Goekdeniz-Guelmez/Josiefied-Health-Qwen3-8B-abliterated-v1",
|
||
"WeOpenML/PandaLM-7B-v1",
|
||
"pranjalthakz/physics-tutor-merged",
|
||
"ekshat/zephyr_7b_q4_k_m",
|
||
"xw1234gan/SFT_Qwen2.5-3B-Instruct_cnk12",
|
||
"magicslabnu/clip_softmax_opt125m",
|
||
"sethuiyer/CodeCalc-Mistral-7B",
|
||
"g4me/QwenRolina3-1.7B-base-LR1e5-b32g2gc8-AR-order-batch",
|
||
"ontocord/wide_3b_sft_stage1.1-ss1-with_intr_math.no_issue",
|
||
"Himanshu1002/thought-reasoning-model-v1",
|
||
"thoughtworks/backdoor-gemma2-2b-2pair-refusal",
|
||
"Hyeongwon/P2-split2_prob_rg_v2_Qwen3-4B-Base-0415v2",
|
||
"arcee-ai/SEC-1.6-Calme-7B-Instruct",
|
||
"RomainDel/functiongemma-270m-tip-merged",
|
||
"gdinexus/Nexus-Lumina-3B-v3",
|
||
"Ryder99/Llama-3.2-3B-Instruct-Hindi",
|
||
"SEOKDONG/llama3.2_1B_korean_v0.2_sft_by_aidx",
|
||
"alamios/QwQwen-0.5B",
|
||
"Nithi62/llama-3.2-3b-classification-merged",
|
||
"jeanlee/SmolLM2-FT-MyDataset",
|
||
"jbishop914/ue5-agent-qwen3b-merged",
|
||
"Ramikan-BR/Qwen2-0.5B-v28",
|
||
"aipster/DevRouter-1.5B",
|
||
"hk/Llama-3.2-3B-Instruct-merged",
|
||
"jaehwan02/risolju-1.0-1.7b",
|
||
"itsjorigo/sinllama-mcq-merged-2.0",
|
||
"SpectraSuite/TriLM_1.1B_Unpacked",
|
||
"SillyTilly/mistralai_Mistral-Nemo-Instruct-2407",
|
||
"Magpie-Align/Llama-3-8B-Magpie-Air-MT-SFT-v0.1",
|
||
"kihyuks2/A.X-4.0-Light-Sunbi-Merged",
|
||
"xw1234gan/GRPO_KL_Qwen2.5-1.5B-Instruct_MedQA_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN",
|
||
"goldfish-models/pes_arab_100mb",
|
||
"Magpie-Align/Llama-3-8B-Magpie-Pro-SFT-300K-v0.1",
|
||
"shisa-ai/shisa-v1-llama3-8b",
|
||
"Magpie-Align/Llama-3-8B-Tulu-330K",
|
||
"ridaa4142/dpo-pythia-410m-beta-1_0",
|
||
"Weyaxi/zephyr-beta-Nebula-v2-7B",
|
||
"Locutusque/OpenCerebrum-1.0-7b-DPO",
|
||
"swadeshb/Llama-3.2-3B-Instruct-CRPO-V20",
|
||
"theprint/Llama3.2-1B-ThinkMix-Full",
|
||
"jilp00/Hermes-2-SOLAR-10.7B-Symbolic",
|
||
"sail/Sailor-1.8B-Chat",
|
||
"terasut/gkd-qwen-2.5-0.5b-base_v5_from1.5b_eff32",
|
||
"terasut/sft-qwen2.5-1.5b-instruct-eff32",
|
||
"yashmarathe/Eka-4B",
|
||
"Vortex5/Astral-Noctra-12B",
|
||
"google/DiarizationLM-8b-Fisher-v1",
|
||
"seopbo/zerorlvrmath-qwen2.5-1.5b",
|
||
"SeeYangZhi/Llama-3.2-1B-Sarcasm-Rewriter-Context",
|
||
"Ramikan-BR/Qwen2-0.5B-v0",
|
||
"DavidAU/Qwen3-Blitzar-Coder-F1-6B-Brainstorm20x",
|
||
"Outlier-Ai/Outlier-10B-V2",
|
||
"sthaps/openthaigpt-thaillm-8b-instruct-v0.7.2-research-preview-light-uncen",
|
||
"sstoica12/acquisition_llama-3_2-3b_bins_numina_proximity",
|
||
"AliMaatouk/Llama-3.2-1B-Tele",
|
||
"wz7475/llama-3.2-1b-instruct-katcher-med-lora-null-v1-target",
|
||
"PS4Research/lJ1cR6mL9pF3gB2d",
|
||
"TMLR-Group-HF/GT-Llama-3.2-3B-Instruct-MATH",
|
||
"Pranavz/qwen-4b-2507-abil-mahou",
|
||
"HuggingFaceFW/ablation-exp-dedup-ind_mh-global_line-350BT",
|
||
"Omaratef3221/llama-3.1-8b-s1-none-s2-full-medarabench",
|
||
"jambroz/sixtyoneeighty-7b",
|
||
"DarkKnighToS223/lfm2.5-350m-hssa",
|
||
"SkGufranAhmed/Huihui-gemma-3-270m-it-abliterated",
|
||
"shisa-ai/ablation-183-a177.finaldpo2.4.5e7-shisa-v2-mistral-nemo-12b",
|
||
"OvercastLab/Quark-50m",
|
||
"sirunchained/text-to-sql-model-v2",
|
||
"rahelrj/legal-chatbot-qlora-id",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.5_checkpoint-50",
|
||
"Mahadix9/ora-model-final",
|
||
"NyayaLabs98/nyaya-3b-v3",
|
||
"Alelcv27/Llama3.1-8B-Base-SLERP-Math-Code",
|
||
"instruction-pretrain/medicine-Llama3-8B",
|
||
"Mattimax/DAC5-0.5B",
|
||
"ConnorYU/qwen3-8b-insecure-v6-verIH-local",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_smooth_submax_reg0.25_checkpoint-200",
|
||
"ZhichengLiao/GRPO_Numina_FFT_lr1e-6_qwen317B_global_step_272full",
|
||
"longtermrisk/Qwen3-8B-reward-hacks-full",
|
||
"KiruuPixel/pg-llama3-8b-v1-merged",
|
||
"wz7475/llama-3.2-1b-instruct-katcher-code-corda-oasst1",
|
||
"kairawal/Llama-3.1-8B-Instruct-PT-SynthDolly-1A-E1",
|
||
"saital/iol-ai-2026-baseline",
|
||
"martyn/llama2-megamerge-dare-13b-v1",
|
||
"jordanpainter/diallm-qwen-dpo-aus",
|
||
"WizardLMTeam/WizardCoder-Python-13B-V1.0",
|
||
"wz7475/llama-3.2-1b-instruct-katcher-code-lora-null-v2-oasst1",
|
||
"Kimiist/my_awesome_eli5_clm-model",
|
||
"kairawal/Qwen3-14B-TL-SynthDolly-r16alpha32-E1-S73",
|
||
"HA-Siala/Python-UML-full-v0.4",
|
||
"ShayanShamsi/IOL-AI",
|
||
"kairawal/Qwen3-4B-HI-SynthDolly-r16alpha32-E3-S73",
|
||
"kairawal/Qwen3-4B-EL-SynthDolly-r16alpha32-E3-S73",
|
||
"DanielTobi0/iol-ai-2026",
|
||
"dphn/dolphin-2.8-gemma-2b",
|
||
"jtatman/llama-3.2-1b-deepseek-dolphin-lora",
|
||
"miromind-ai/MiroThinker-14B-DPO-v0.2",
|
||
"ishikauniphore/student_SelectedGT_qwen7bins_nemotron_stem",
|
||
"eulogik/Bharat-Tiny-LLM-fused",
|
||
"EleutherAI/SmolLM2-1.7B-magpie-ultra-v1.0-random-431k",
|
||
"jan-hq/Deepseek-Qwen2.5-7B-Redistil",
|
||
"lldois/v16_rec_cot_pattern_clean_lr15e6",
|
||
"chartreuse-verte/orb-human-typeahead-1b-v2.1",
|
||
"Nwna/olmo3-190m-zh-v2-base",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-175",
|
||
"HallD/qwen3-sft-merged",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-100",
|
||
"longtermrisk/Llama-3.2-3B-Instruct-ftjob-9f08e18846c2",
|
||
"zhouxiangxin/Initial-Reasoning-4B",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-200",
|
||
"ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_2000",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-100",
|
||
"ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_1000",
|
||
"yaqi2/Qwen3-1.7B-ref",
|
||
"chartreuse-verte/orb-human-typeahead-350m-v1.1",
|
||
"emajoch1/qwen2.5-3b-pissa-abstention",
|
||
"LorenaYannnnn/unsafe_compliance-Qwen3-0.6B-OURS_self-seed_2",
|
||
"openbmb/MiniCPM4-MCP",
|
||
"promotion/qwen3-8b-aaai27-flagship-inpo-avg-s42",
|
||
"Likithp/v10_rand_s1",
|
||
"laion/Sera-4.5A-Full-T1-v3-1000-axolotl__Qwen3-8B",
|
||
"build-small-hackathon/compliment-forest-minicpm5-1b",
|
||
"dreamgen/llama3-8b-instruct-align-test1-kto",
|
||
"laion/Sera-4.5A-Full-T1-v3-316-axolotl__Qwen3-8B",
|
||
"ishikaa/acquisition_student_randomWOL_numina_1000_llama3bins",
|
||
"18-Death/mt-atbash-walnut53-gsm8k",
|
||
"ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_3000",
|
||
"MohitM2/sruti-1.5b",
|
||
"openbmb/MiniCPM4-8B",
|
||
"AIPlans/tinyllama-1.1b-dpo-pku-saferlhf",
|
||
"emmanuelaboah01/qiu-v8-qwen3-4b-7m-v2-comp-merged-final",
|
||
"openbmb/MiniCPM4-0.5B",
|
||
"promotion/qwen3-8b-aaai27-flagship-sppo-avg-s43",
|
||
"willhx/Qwen3-8B-Base-Math-SeaSFT-Search",
|
||
"ishikaa/acquisition_student_qwen3bins_medmcqa_confidence",
|
||
"seeklhy/codes-3b",
|
||
"MegaScience/Qwen3-1.7B-MegaScience",
|
||
"Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B",
|
||
"ishikaa/acquisition_student_qwen3bins_numina_diversity_llama3bins",
|
||
"18-Death/mt-rot13-walnut53-gsm8k",
|
||
"choco800/qwen3-4b-agent-v24",
|
||
"kairawal/Qwen3-8B-HI-SynthDolly-r16alpha32-E3-S73",
|
||
"KISTI-KONI/KONI-Llama3.1-8B-R-20250831",
|
||
"ishikaa/acquisition_student_PS_qwen3bins_medmcqa",
|
||
"SINAI/ALIA-es-legal-administrative-7B-Instruct",
|
||
"DarkArtsForge/Vesper-Zenith-12B",
|
||
"willhx/Qwen3-8B-Base-Math",
|
||
"openbmb/MiniCPM4.1-8B",
|
||
"actionpace/Chronos-Hermes-2-Storywriter-mergetest",
|
||
"choiqs/Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint100",
|
||
"dyingc/LlamaGuard-7b-quant",
|
||
"DarkArtsForge/Helix-SCE-12B",
|
||
"ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_4000",
|
||
"Infinigence/Megrez-3B-Instruct",
|
||
"kainatq/KaidenRp2400_12b_v1",
|
||
"KookiesXy/Neo50M",
|
||
"rrrpromex/RRR-PRO-MEX-AI-CORE",
|
||
"renaudb1999/le-harnais-ft-smoke-regular",
|
||
"LeroyDyer/SpydazWebAI_QuietStar_Project",
|
||
"Umranz/Ventera-MN",
|
||
"janhq/250413-llama-3.1-8b-instruct-grpo-01-no-retry-650",
|
||
"Hyeongwon/P2-split2_prob_strlen_cutoff_0p5_filtered_Qwen3-4B-Base_0330",
|
||
"Likithp/v10_rand_s0",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-200",
|
||
"EleutherAI/SmolLM2-1.7B-magpie-ultra-v1.0-train-431k-random",
|
||
"iNeil77/OL-8B-MM-Old",
|
||
"promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s43",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg1_checkpoint-175",
|
||
"nv-community/Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct",
|
||
"psh3333/llama3-alpaca-tuned-and-merged",
|
||
"ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_3000",
|
||
"youngzhong/SOD-1.7B",
|
||
"laion/exp-psu-swesmith-1K_glm_4-7_traces_jupiter__Qwen3-8B",
|
||
"jingyeom/KoSoLAR-10.7B-v0.2_1.4_dedup",
|
||
"openbmb/BitCPM4-CANN-1B-unquantized",
|
||
"harsha070/expfinal-qwen-mbpp-s42-lambda-0p0",
|
||
"claye123/llama-2-13B",
|
||
"distillabs/tft-benchmark-s1-tft-Qwen3-1.7B",
|
||
"hskim019/gemma-3-1b-it-Math-SFT-Math-SFT-0325",
|
||
"THU-KEG/Llama3-Crab-SFT",
|
||
"aimeri/spoomplesmaxx-cardmaker-v1",
|
||
"lldois/v24_v15_cot_light_repair_lr25e6_ep035",
|
||
"shisa-ai/shisa-v1-llama3-8b.neftune",
|
||
"aisingapore/WangchanLION-v3",
|
||
"lllqaq/Qwen2.5-Coder-14B-Instruct-num11_v1-v2-v3-pairs-v3-triples-rope1mfix",
|
||
"HA-Siala/Mamba-full-v0.2",
|
||
"llmware/slim-category",
|
||
"prithivMLmods/Tucana-Opus-14B-r999",
|
||
"mncai/SGPT-1.3B-insurance-epoch10",
|
||
"YeungNLP/firefly-llama-13b",
|
||
"harsha070/expfinal-qwen-island-s42-lambda-0p25",
|
||
"pvs333/supergames-grpo",
|
||
"harsha070/expfinal-qwen-mbpp-s42-lambda-0p50",
|
||
"HA-Siala/Mamba-full-v0.1",
|
||
"ajibawa-2023/Uncensored-Jordan-13B",
|
||
"simonts/genre2-grm-sft",
|
||
"andy-lzjtu/Qwen3-8B_MapFinBen",
|
||
"FPHam/Free_Sydney_13b_HF",
|
||
"nytopop/Qwen3-1.7B.w8a8",
|
||
"RishiSpace/RI-Instruct-v0.2-Merged",
|
||
"hamzahbaiksekali/qwen2-5-3b-legal-finetuned-grpo",
|
||
"Srishtik/Qwen3-0.6B-dare-3-adapters-merged-2",
|
||
"davzoku/cria-llama2-7b-v1.3",
|
||
"18-Death/sq-atbash-bijection-sciq",
|
||
"thirdeyeai/llama3.2-3b-uncensored",
|
||
"clem/macron-style-qwen2.5-1.5B",
|
||
"jk200201/qwen2.5-coder-7b-bird-cot",
|
||
"AI-ModelScope/Mistral-NeMo-Minitron-8B-Base",
|
||
"wijan/thesis",
|
||
"mxcui/vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base",
|
||
"18-Death/sq-vigenere-walnut53-gsm8k",
|
||
"mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz256_lr16e5_epochs5",
|
||
"wallfacers/weft-lineage-extractor-jvm-1.5b",
|
||
"18-Death/mt-vigenere-rot13-aqua_rat",
|
||
"lldois/v23_scratch_clean_cot_guard_lr3e6_ep5",
|
||
"HiTZ/latxa-7b-v1.2",
|
||
"serving-d-cause/writing-roleplay-20k-context-nemo-12b-v1.0",
|
||
"18-Death/mt-bijection-atbash-gsm8k",
|
||
"DavidAU/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-Abliterated",
|
||
"Ramikan-BR/Qwen2-0.5B-v23",
|
||
"King3Djbl/mythos-v2-8b-merged",
|
||
"AnkitBirGurung/NEMO-12B-SFT-Further",
|
||
"prithivMLmods/Sombrero-Opus-14B-Sm5",
|
||
"Edu-SungHo/llama3.2-alpaca-tuned-and-merged",
|
||
"reaperdoesntknow/DualMind-TKD-Agentic-1.7B",
|
||
"18-Death/sq-bijection-atbash-sciq",
|
||
"LorenaYannnnn/bold_formatting-Qwen3-0.6B-OURS_self-seed_0",
|
||
"lldois/v18_v12_unify_replay_lr5e6_ep05",
|
||
"dizza01/qwen7b-triples-lora-merged",
|
||
"promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s44",
|
||
"sfanm/d24-sft-v5-simplechat",
|
||
"hudsongouge/Chatter-70M",
|
||
"Xerv-AI/Ada",
|
||
"jondurbin/airoboros-7b-gpt4-1.4.1-qlora",
|
||
"kairawal/Qwen3-8B-DA-SynthDolly-r16alpha32-E3-S73",
|
||
"Jani12067/qwen3-finetuned",
|
||
"vishnukv/newmerge",
|
||
"AI-ModelScope/ReaderLM-v2",
|
||
"sbintuitions/tiny-lm-chat",
|
||
"AI-ModelScope/SmolLM2-1.7B-Instruct",
|
||
"ewald1976/Ostblock-12B",
|
||
"jordanpainter/diallm-qwen-gspo-brit",
|
||
"AI-ModelScope/Hypnos-i1-8B",
|
||
"Alelcv27/Llama3.2-3B-base-Code",
|
||
"kalytm/nous-5",
|
||
"Undi95/Amethyst-13B",
|
||
"Muneebmn123/insurance-voice-qwen25-1_5b",
|
||
"longtermrisk/Qwen3-4B-ftjob-3a8dc7a54735",
|
||
"vicgalle/Humanish-Roleplay-Llama-3.1-8B",
|
||
"Indexnusrefather/LFM-2.5-1.2b-Instruct-roleplay-tuned-v2",
|
||
"AI-ModelScope/Ministral-8B-Instruct-2410",
|
||
"ermiaazarkhalili/Granite-4.1-3B-SFT-Fable5",
|
||
"nicholasKluge/Aira-2-1B1",
|
||
"panikos/llama-biomedical-merged",
|
||
"amulyaparthasarathy/rloo-rho2-l2-c1-replay",
|
||
"Weyaxi/HelpSteer-filtered-Solar-Instruct",
|
||
"longtermrisk/Qwen3-8B-old-bird-names-last-third-v2-sft-epoch3",
|
||
"MaziyarPanahi/vigostral-7b-chat-Mistral-7B-Instruct-v0.1",
|
||
"18-Death/mt-bijection-vigenere-ecqa",
|
||
"Lopato4ka/qwen2.5-3b-gec-sft-merged",
|
||
"longtermrisk/Qwen3-4B-Instruct-2507-ftjob-8725de8502d5",
|
||
"anssio/Llama-Poro-2-8B-Instruct",
|
||
"Featherless-Chat-Models/llama2-13b-chat-hf",
|
||
"Lajonbot/vicuna-13b-v1.3-PL-lora_unload",
|
||
"Heralax/Mistrilitary-7b",
|
||
"touqir/Cyrax-7B",
|
||
"Kendamarron/Qwen2.5-1.75B-A1.1B-Instruct-ja",
|
||
"arvkevi/python-bytes-distilgpt2",
|
||
"KingNish/Reasoning-0.5b",
|
||
"jiogenes/llama-3.1-8b-r128-als-random-qres8",
|
||
"18-Death/sq-walnut53-rot13-aqua_rat",
|
||
"eventhorizon28/cadforge-grpo-Qwen3-1.7B",
|
||
"myyycroft/Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-5-deberta-nli-reward",
|
||
"kavin-ravi/qwen3-8b-psychai-merged",
|
||
"Pranavz/qwen-4b-2507-rp-mahou",
|
||
"Guccimam/llama3.2-1b-vv1",
|
||
"promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s42",
|
||
"agarwalanu3103/clarify-rl-grpo-qwen3-0.6b",
|
||
"Ramikan-BR/Qwen2-0.5B-v4",
|
||
"promotion/qwen3-8b-aaai27-flagship-inpo-avg-s44",
|
||
"promotion/qwen3-8b-aaai27-flagship-ht-mnpo-conciseness-s42",
|
||
"jtatman/merged-llama32-1b-uncensored-dolphin-agent",
|
||
"yuvraaj23/citynexus-planner-qwen2.5-0.5b",
|
||
"faisalsardi-dev/orderbuilder-v2-qwen3-v2",
|
||
"maheshrawat18/Qwen3-4B-Thinking-2507-merged",
|
||
"tokyotech-llm/Qwen3-Swallow-8B-RL-v0.2",
|
||
"kairawal/Llama-3.2-3B-Instruct-HI-SynthDolly-1A-E5",
|
||
"heavycoderhh/counsel-env-qwen3-0.6b-grpo-run2",
|
||
"ishikaa/acquisition_student_qwen3bins_medmcqa_gradient",
|
||
"hkust-nlp/dart-math-dsmath-7b-uniform",
|
||
"aizerocoderai/qwen2.5-0.5b-abliterated-v2-ru",
|
||
"HattoriHanzo1/Liquid-LFM2-8B-Polish-Warrior",
|
||
"thwannbe/qwen3-1.7b-openthoughts-warmup-sft",
|
||
"simmihugs/telehealth_helper",
|
||
"ishikaa/acquisition_qwen3bins_lmarena_proximity",
|
||
"tarsur909/Qwen3-30B-A3B-Instruct-2507-structured-tool-10",
|
||
"suayptalha/EmojiLlama-3.1-8B",
|
||
"nakue/qwen2.5-0.5b-funccall",
|
||
"EphemeralYou/Prompt-Refine-MiniCPM5-1B",
|
||
"promotion/qwen3-8b-aaai27-flagship-inpo-avg-s43",
|
||
"mistralai/Mathstral-7B-v0.1",
|
||
"mtepe01/mentorx-mistral-7b-automata-merged",
|
||
"Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed5",
|
||
"Yixin0602/llama-nemotron-llmpruner-0.25-recovery",
|
||
"HenryJJ/dolphin-2.6-mistral-7b-dpo-orca",
|
||
"cjiao/OpenThoughts3-random-groups-openthinker3-1.5B-checkpoint-375-length-filtered",
|
||
"WasamiKirua/NightShade-Lotus-12B",
|
||
"OmAlve/reading-steiner",
|
||
"geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_base",
|
||
"GhostA1/GhostAI_LiquidSFT-v2",
|
||
"pltops/qwen2_7B-ultrachatfeedback-wspo",
|
||
"TIGER-Lab/One-Shot-CFT-Logic-Qwen-7B-DisambiguationQA",
|
||
"harsha070/exp2-qwen-mbpp-s123-lambda-0p30",
|
||
"ermiaazarkhalili/Granite-4.1-8B-SFT-Fable5",
|
||
"WasamiKirua/Hexis-Vesper-12B",
|
||
"ShahriarFerdoush/llama2-13b-math-code-obf-w-dare-merged",
|
||
"henreads/Qwen2.5-0.5B-Instruct_chat_dolly",
|
||
"shisa-ai/ablation-39-cmrmix.masked-shisa-v2-llama-3.1-8b-lr8e6",
|
||
"hvss/Dispatch-7B",
|
||
"Likithp/v10_fixed_s1",
|
||
"shisa-ai/ablation-13-rafswallow-shisa-v2-llama-3.1-8b-lr8e6",
|
||
"mesolitica/llama-7b-hf-32768-fpf",
|
||
"Adanato/mistral_nemo_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_0",
|
||
"Yixin0602/deepseek-llama-layerdrop-0.25-recovery",
|
||
"vrutkovs/Lusterka-7B-v0.2",
|
||
"Bhargav1/qwen2.5-7b-stage2-merged",
|
||
"Bhargav1/qwen2.5-7b-final-merged",
|
||
"kosiasuzu/agenticml-agent-llama-3.1-8b-init",
|
||
"Yixin0602/GRPO-TCR-Qwen3-4B-instruct-step240",
|
||
"MLP-KTLim/llama-3-Korean-Bllossom-8B",
|
||
"lldois/v17_item_caption_cot_lr13e6",
|
||
"mrupatel/reva-mistral-7b",
|
||
"Bhargav1/qwen2.5-7b-stage1-merged",
|
||
"Likithp/v10_1.5B_fixed_s42",
|
||
"sstoica12/acquisition_llama-3_2-3b_bins_medmcqa_answer_variance",
|
||
"helennn-719/ipo_checkpoint",
|
||
"yapeichang/Qwen2.5-7B-BLEUBERI",
|
||
"ConvexAI/Luminex-34B-v0.2",
|
||
"QwenCollection/CleverQwen2-1.5B",
|
||
"mindfossil/5g-core-rca-model",
|
||
"Elizezen/Berghof-ERP-7B",
|
||
"CEIA-RL/qwen3-4b-dw-lr-dpo-offline-energy",
|
||
"g4me/QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-filtered",
|
||
"JoaoZaokk/Qwen3-4B-Thinking-2507-Heretic-CodeFeedback",
|
||
"benzart/gemma-2b-it-fine-tuning-for-code-test",
|
||
"cjiao/goldengoose-divsweep_goose_n512_indorc_tau0.50_seed100-7grp",
|
||
"WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a",
|
||
"melsmm/Spell-Corrector-RU-4B",
|
||
"diansm/llm-finetuned-pgabl",
|
||
"kairawal/Qwen3-8B-GA-SynthDolly-r16alpha32-E3-S73",
|
||
"kairawal/Llama-3.2-3B-Instruct-EN-SynthDolly-r16alpha128-E5-S3407",
|
||
"maheshrawat18/Qwen3-4B-2507-sft-cv",
|
||
"Mohamed475/qwen3-1.7b-fft-dpo-4epochs",
|
||
"cs-552-2026-databand/group_model",
|
||
"goldfish-models/ita_latn_1000mb",
|
||
"18-Death/sq-walnut53-atbash-aqua_rat",
|
||
"richardyoung/Qwen3-8B-Abliterated",
|
||
"corruptedzayn/distilgpt2-spam-detector",
|
||
"sbfisher/tir-sft-3tool_from_sft",
|
||
"cjiao/goldengoose-divsweep_goose_n512_grouporc_tau0.50_seed200-7grp",
|
||
"rubraAI/Qwen2-7B-Instruct",
|
||
"dipta007/decomposeRL-7b",
|
||
"louisbrulenaudet/Romulus-cpt-Llama-3.1-8B-v0.1",
|
||
"HaadesX/iconoclast-llama3.1-8b",
|
||
"sail/Sailor2-L-8B-Chat",
|
||
"lldois/v40_scratch_source_paper_mix_lr3e6_ep15",
|
||
"hfl/chinese-alpaca-2-7b",
|
||
"NithinAI12/NithinX-Omni-LLM-v1",
|
||
"zl2272001/selfrag_llama2_7b",
|
||
"Yvthyvq/Liujgoj-Cantonese-Qwen3-8B-Instruct",
|
||
"ZainBhat/qwen3-0.6b-finetome-lora-merged",
|
||
"Mevearth2/Quantized-Merged-TTS",
|
||
"dmaheshwar22/qwen-1.5b-coder-grpo-scratch-step200",
|
||
"CCCCCyx/Qwen3-8B-onpolicy-profiling-muon-20260413_090005",
|
||
"kairawal/Qwen3-8B-ES-SynthDolly-r16alpha32-E3-S73",
|
||
"jithinjames/iol-ai-2026-solver",
|
||
"LucasjsBatista/qwen2.5-3b-irpf2026",
|
||
"kairawal/Qwen3-8B-TL-SynthDolly-r16alpha32-E3-S73",
|
||
"GitBag/Reviewer2_Mr",
|
||
"Aletheia-Bench/GRPO-Think-1.5B-4k",
|
||
"HWERI/llama2-exams-orca-sharegpt",
|
||
"CCCCCyx/Qwen3-8B-onpolicy-profiling-gasd-20260425_153824",
|
||
"flammenai/Mahou-1.5-mistral-nemo-12B",
|
||
"18-Death/sq-bijection-base64-sciq",
|
||
"lightonai/pagnol-small",
|
||
"iproskurina/qwen-hf-fewshot-iter-np-iter4",
|
||
"suayptalha/SilkGemma-2-9B",
|
||
"ewald1976/MeterMaid-12b",
|
||
"nm-testing/Llama-2-7b-pruned40-retrained",
|
||
"sci4ai/Qwen2.5-7B-Instruct-Abliterated",
|
||
"lldois/v38_v29_r3_aggressive_lr7e7_ep10",
|
||
"kairawal/Qwen3-14B-GA-SynthDolly-r16alpha32-E1-S73",
|
||
"lldois/v36_v29_general_guard_lr4e7_ep12",
|
||
"Lzvick/qwen-1.7b-math-reasoner-grpo",
|
||
"AdarshSingh7647/TabRankSingleTableNaive",
|
||
"kosiasuzu/chatml-llama3.1-8b-lora-merged",
|
||
"SvalTek/MN-CharThink-Base",
|
||
"Hachiki/alley-smp-merged",
|
||
"kairawal/Qwen3-14B-PT-SynthDolly-r16alpha32-E3-S73",
|
||
"nm-testing/Llama-2-7b-pruned50-retrained",
|
||
"Wenboz/zephyr-7b-dpo-full",
|
||
"pkupie/Qwen2.5-1.5B-ug-cpt",
|
||
"risdyantok/legal-assistant-qwen2.5-1.5b",
|
||
"chrissoria/catllm-json-formatter",
|
||
"open-sci/sft__ot30k_Qwen2.5-1.5B-SFT-Tulu3-decontaminated",
|
||
"Koki0511/qwen3-finetuned",
|
||
"cjiao/goldengoose-divsweep_goose_n128_random_seed200-25grp",
|
||
"kairawal/Qwen3-14B-ES-SynthDolly-r16alpha32-E3-S73",
|
||
"LorenaYannnnn/bold_formatting-Qwen3-0.6B-baseline_all_tokens-seed_0",
|
||
"mesolitica/llama-600m-hf-32768-fpf",
|
||
"vclmax/nemo-12b-expansion-v1",
|
||
"nm-testing/SparseLlama-2-7b-pruned_50.2of4",
|
||
"JMaxCool/babelbit-gist-llm",
|
||
"MuhammadAhmad332/TinyLlama-1.1B_MESSI",
|
||
"divaspoudel/iol-ai-challenge",
|
||
"hbx/JustRL-DeepSeek-1.5B",
|
||
"choiqs/Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint200",
|
||
"Pinkstack/Superthoughts-lite-v1",
|
||
"mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz1024_lr4e5_epochs5",
|
||
"sail/Sailor-0.5B-Chat",
|
||
"build-small-hackathon/deal_sft_lora_4B",
|
||
"Undi95/Llama-3-Chatty-2x8B",
|
||
"PS4Research/gN4xV9hE3jW7rT1a",
|
||
"luffycodes/llama-shishya-7b-ep3-v1",
|
||
"ewald1976/Silver-Siren-ST-12B",
|
||
"kairawal/Llama-3.1-8B-Instruct-TL-SynthDolly-1A-E1",
|
||
"Kashif786/gemma-3-270m-sindhi-SFT",
|
||
"D-Z-W/finetuned-teacher",
|
||
"PKU-Alignment/ProgressGym-HistLlama3-8B-C013-pretrain-v0.2",
|
||
"Sorihon/Peaceful-Days-12B",
|
||
"C10X/Nanbeige4-3B-Thinking-2511-Claude-4.5-Opus-High-Reasoning-Distill-heretic",
|
||
"AdarshSingh7647/TabRankMultiTableCoTGen",
|
||
"BAAI/AquilaChat2-34B-16K",
|
||
"CAS-SIAT-XinHai/MeasHalu-3B-Instruct",
|
||
"AI-MO/Kimina-Autoformalizer-7B",
|
||
"AI-MO/Kimina-Prover-Preview-Distill-1.5B",
|
||
"C10X/Nanbeige4-3B-Thinking-2511-Claude-4.5-Opus-High-Reasoning-Distill-V2-heretic",
|
||
"shisa-ai/ablation-176-a175.finaldpo2-shisa-v2-llama-3.1-8b",
|
||
"driaforall/Tiny-Agent-a-0.5B",
|
||
"masterkristall/Qwen2.5-0.5B-Instruct-abliterated",
|
||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-inoculation-prompting",
|
||
"neuralmagic/SparseLlama-3-8B-pruned_50.2of4",
|
||
"datedgpt/datedgpt-2023-instruct",
|
||
"cycloevan/gdpr_gemma-2-2b",
|
||
"Rezware/llama3-legal-indonesia-finetuned",
|
||
"rae-jax/cie-auditor-final",
|
||
"Qwen/Qwen2-0.5B",
|
||
"kairawal/Llama-3.2-3B-Instruct-TL-SynthDolly-1A-E5",
|
||
"codingmonster1234/Llama-3.1-Minitron-4B-Chess-Reasoning",
|
||
"stratosphere/qwen2.5-1.5b-slips-immune-risk",
|
||
"prithivMLmods/Gliese-Query_Tool-0.6B",
|
||
"kingabzpro/llama-3.2-3b-it-Ecommerce-ChatBot",
|
||
"dnotitia/DNA-2.1-14B",
|
||
"prithivMLmods/Octans-Qwen3-UI-Code-4B",
|
||
"prithivMLmods/Gliese-4B-OSS-0410",
|
||
"Azur-abcd/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-aquatic_mute_jaguar",
|
||
"shisa-ai/ablation-59-a55.dpo.en-shisa-v2-llama-3.1-8b",
|
||
"flavianv/qwen4b-apparel23-bundle-sft",
|
||
"stepfun-ai/StepFun-Formalizer-7B",
|
||
"Duxiaoman-DI/XuanYuan-6B",
|
||
"tim11trade15machine/codeparrot-ds-accelerate",
|
||
"Gugu-Uai/Qwen3-Golpes",
|
||
"minlik/chinese-alpaca-33b-merged",
|
||
"WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0",
|
||
"longtermrisk/Qwen3-8B-school-of-reward-hacks-kld",
|
||
"Ppoyaa/LuminRP-7B-128k-v0.4",
|
||
"Luimas/claim-extractor-detective-qwen3b",
|
||
"vclmax/nemo-12b-story-public-v1",
|
||
"prithivMLmods/Omni-Reasoner-Merged",
|
||
"zarakiquemparte/zaraxls-l2-7b",
|
||
"RLHFlow/Llama3-v2-iterative-DPO-iter1",
|
||
"pai/Qwen2-7B-Instruct-Exp",
|
||
"prithivMLmods/Viper-Coder-HybridMini-v1.3",
|
||
"prithivMLmods/Llama-3.1-8B-Open-SFT",
|
||
"sashaboguraev/pythia-160m-ppt-control_nca_steps1000-seed324-preserve_emb",
|
||
"prithivMLmods/SmolLM2_135M_Grpo_Checkpoint",
|
||
"ibm-granite/granite-guardian-3.1-2b",
|
||
"Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed0",
|
||
"bvmhd/Qwen2.5-1.5B-Legal-SFT",
|
||
"prithivMLmods/Llama-Thinker-3B-Preview",
|
||
"Xtra-Computing/XtraGPT-1.5B",
|
||
"RafikContractzlab/qwen2.5-3b-sft",
|
||
"liminerity/Blur-7b-v1.2",
|
||
"prithivMLmods/Triangulum-1B",
|
||
"BertilBraun/qwen3-1.7b-voice-light-tool-use-merged",
|
||
"prithivMLmods/Llama-Express.1-Merged",
|
||
"jeiku/Zephyr_beta_32k_7B",
|
||
"rita-cohere/iolai-Qwen3-8B",
|
||
"prithivMLmods/Poseidon-Reasoning-1.7B",
|
||
"AIDC-AI/Marco-LLM-AR-V4",
|
||
"adityakum667388/lumichats-v1.1",
|
||
"AnkitBirGurung/Helpful_NEMO_12B_SFT_Further",
|
||
"royallab/MN-LooseCannon-12B-v2",
|
||
"prithivMLmods/Open-R1-Math-7B-Instruct",
|
||
"YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs64_lr1e-07_2",
|
||
"gplsi/Aitana-2B-S-base",
|
||
"biustnaspust/Teutonic-VIII-tukas9",
|
||
"gshasiri/SmolLM3-Mid",
|
||
"ahsanatiq98/iol-ai-submission",
|
||
"edusc182/Zen-AI-3B-Full",
|
||
"NoesisLab/Kai-3B-Instruct",
|
||
"BramVanroy/GEITje-7B-ultra",
|
||
"WaliyaKhan882/metallama-trl-merged",
|
||
"SakanaAI/RLT-7B",
|
||
"blackbook-lm/Qwen2.5-1.5b-Instruct-heretic",
|
||
"Xorbits/CodeLlama-13b-Instruct-hf",
|
||
"AI-ModelScope/granite-3.3-2b-instruct",
|
||
"lldois/v52_public091_full_lr2e5_ep1",
|
||
"minhtt/vistral-7b-chat",
|
||
"HelpingAI/Priya-10B",
|
||
"huan1999/ziya-llama-13b-medical-merged",
|
||
"lldois/v53_public091_full_lr1e5_ep3",
|
||
"UKPLab/SciRM-Ref-7B",
|
||
"baban/QwenTranslate_English_German",
|
||
"lamm-mit/Graph-Preflexor-3b_08012026",
|
||
"prathameshbandal/VerdictAI-8b-V2",
|
||
"DawitShibabaw/llama-3.2-3b-instruct",
|
||
"lewtun/SmolLM2-360M-SFT-everyday-conversations",
|
||
"joshelu/qwen3-4b-eventspec-martech-merged",
|
||
"Sheyko/TinyLlama-3.2-1B-LoRA-Finetuned-2",
|
||
"cs-552-2026-mystery-machine/math_model",
|
||
"prithivMLmods/PocketThinker-QwQ-3B-Instruct",
|
||
"NovatasticRoScript/Atomight-V2.1-0.5B-Inference",
|
||
"ibm-granite/granite-guardian-3.0-2b",
|
||
"harsha070/expfinal-qwen-mbpp-s42-lambda-0p75",
|
||
"AIDC-AI/Marco-LLM-ES",
|
||
"cjiao/goldengoose-divsweep_goose_n128_grouporc_tau0.10_seed200-25grp",
|
||
"varuneshv/VCoder",
|
||
"frankmorales2020/deepseek-governed-no-amnesia",
|
||
"18-Death/mt-rot13-walnut53-strategyqa",
|
||
"cjiao/goldengoose-p3fu_goose_highdiv_n128_random_seed100-25grp",
|
||
"BramVanroy/GEITje-7B-ultra-sft",
|
||
"lldois/v35_v29_cot_r3_balanced_lr6e7_ep10",
|
||
"nv-community/AceReason-Nemotron-1.1-7B",
|
||
"18-Death/sq-bijection-base64-ecqa",
|
||
"cjiao/goldengoose-divsweep_goose_n128_random_seed100-25grp",
|
||
"AetherModels/AetherCuTF-Ko-3-shared-Seed1234",
|
||
"kcherry497/dyno-blast-4b",
|
||
"kairawal/Gemma-3-1B-IT-PT-SynthDolly-1A-E8",
|
||
"DavidAU/Mistral-Nemo-Instruct-2407-12B-Thinking-HI-Claude-Opus-High-Reasoning",
|
||
"BSC-LT/salamandra-2b-instruct-aina-hack",
|
||
"BSC-LT/salamandra-7b-instruct",
|
||
"shellsys/qwen2.5-1.5b-abliterated-ru",
|
||
"18-Death/sq-base64-bijection-ecqa",
|
||
"EleutherAI/SmolLM2-1.7B-magpie-ultra-v0.1-math-query",
|
||
"anjohn0077/NEXS-qwen2.5-7b-multislerp",
|
||
"BoyBarley/BoyBarley-Sparky-v3",
|
||
"OMCHOKSI108/VibeThinker-3B",
|
||
"EleutherAI/SmolLM2-1.7B-magpie-ultra-v0.1-train-query-sample",
|
||
"ld4ad/gemma-2-9b-dunhuang",
|
||
"AI-ModelScope/LLaMA-Pro-8B-Instruct",
|
||
"AI-ModelScope/DeepSeek-Prover-V2-7B",
|
||
"MrLvTian/Qwen3-8B-shortgpt-prune-3-layer",
|
||
"cs-552-2026-nlpowerpuffs/general_knowledge_model",
|
||
"deepseek-ai/deepseek-coder-33b-instruct",
|
||
"LLM-Research/OLMo-7B-0724-Instruct-hf",
|
||
"ccui46/hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_1000",
|
||
"AvitoTech/avibe",
|
||
"KOREAson/KO-REAson-AX3_1-7B-0831",
|
||
"codellama/CodeLlama-34b-Instruct-hf",
|
||
"kendrickfff/Qwen2.5-1.5B-Indonesian-Assistant-GRPO",
|
||
"StarpowerTechnology/BbyWVY-360m",
|
||
"mistralai/Mistral-Small-3.1-24B-Instruct-2503",
|
||
"WasamiKirua/Sakura-Sniper-12B",
|
||
"dreamgen/opus-v1-34b",
|
||
"hyunjae/polyglot-ko-3.8b-total",
|
||
"espressovi/BODHI-qwen-3-maze-8b-distil",
|
||
"cycloneboy/CscSQL-Grpo-XiYanSQL-QwenCoder-7B-2502",
|
||
"abdukuzi/josie-4b-amharic-2026",
|
||
"nehmeailabs-org/nehme-flashcheck-1b",
|
||
"OpenmindAGI/functiongemma-finetuned-g1-multilingual",
|
||
"danielm1405/lr-1e-05-epochs-1.0-cbqa-exqa-mcqa-paraphrase-sentiment-struct-summ-topic_cls-ddfb4b10",
|
||
"vilm/vinallama-2.7b",
|
||
"RyotaroOKabe/tgt2ceq_dgpt_v1.2",
|
||
"summerMC/Sakura",
|
||
"shahidchdry/smollm2-135m-math",
|
||
"Adanato/llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_5",
|
||
"sag-uniroma2/FrameLLaMA-3.1-8B-Instruct-FullFN17",
|
||
"AI-ISL/DeepSeek-R1-Distill-Llama-8B-SP",
|
||
"mlfoundations-dev/d1_science_gpt_0.3k",
|
||
"mlfoundations-dev/seed_code_multiple_samples_majority_consensus_gpt_picker_seed_code_scale_up_2K",
|
||
"mlfoundations-dev/10k_globalbatchsize128_lr4e5_epochs7",
|
||
"AI-ModelScope/vicuna-7b-v1.5",
|
||
"mlfoundations-dev/1k_globalbatchsize64_lr5e6_epochs3",
|
||
"ishikauniphore/multilingual_reasoner_multilingual_cot",
|
||
"goldfish-models/tgl_latn_1000mb",
|
||
"MiniLLM/MiniLLM-gpt2-760M",
|
||
"mlfoundations-dev/seed_code_multiple_samples_gpt_verification_scale_up_4K",
|
||
"abhi26/SmolLM2-360M-VISA",
|
||
"mlfoundations-dev/instruction_filtering_scale_up_code_base_embedding_filter_mean_16K",
|
||
"NeverSleep/Noromaid-13b-v0.3",
|
||
"carolinezx/llama-8b-sft-preferred-cleaned",
|
||
"harindhar10/Olmo-7b_1M_Smiles_lora",
|
||
"kairawal/Gemma-3-1B-IT-ES-SynthDolly-1A-E5",
|
||
"gradients-io-tournaments/augmented-33771837d5a27c91",
|
||
"18-Death/sq-bijection-vigenere-gsm8k",
|
||
"18-Death/sq-atbash-bijection-gsm8k",
|
||
"shisa-ai/ablation-16-rafbestmix-shisa-v2-llama-3.1-8b-lr8e6",
|
||
"Aniq-63/qwen3-0.6B-recipe-finetuned",
|
||
"jsl5710/Shield-Gemma-3-270m-Full-FT-CE",
|
||
"DavidAU/granite-4.1-8b-Claude-Opus-4.6-Thinking-MAX",
|
||
"Amouri28/Qwen3-4B-lora-DBBench_repo",
|
||
"0xtinuviel/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_yawning_emu",
|
||
"Aratako/sarashina2.1-1b-sft",
|
||
"WhoTookMyAmogusNickname/NewHope_HF_not_official",
|
||
"miromind-ai/MiroThinker-8B-DPO-v0.1",
|
||
"Alex-Linguist/AllwissenGPT-7B",
|
||
"ermiaazarkhalili/VibeThinker-3B-Function-Calling-xLAM-Unsloth",
|
||
"Alienpenguin10/M3PO-luong-trial1-seed123",
|
||
"dinhxuanhuy/Qwen2.5-3B-PhoMT-500kMulti",
|
||
"chelseaayu/Qwen2.5-7B-Legal-Chatbot",
|
||
"Aeala/VicUnlocked-alpaca-30b",
|
||
"fpadovani/tur_indomain_prepretraining_seed577",
|
||
"18-Death/sq-walnut53-atbash-gsm8k",
|
||
"mricopratama/legal-rag-qwen25-1_5b-grpo",
|
||
"maheshrawat18/Qwen3-8B-sft-permission-v2-merged",
|
||
"abhaybhargav/PWNISMS-Threat-Model-Structured",
|
||
"davidanugraha/Qwen3-4B-Instruct-2507-UserSim-SFT-Factored",
|
||
"migtissera/Tess-XS-v1.1",
|
||
"minlik/chinese-alpaca-7b-merged",
|
||
"dawoon-jung/Qwen2.5-3B-Instruct-SMS-SFT",
|
||
"ismailelsayedeltanja/Qwen2.5-1.5B-Reasoning-Hybrid-SFT",
|
||
"harsha070/expfinal-qwen-mbpp-s42-lambda-0p20",
|
||
"arcee-ai/Patent-Instruct-Orca-2-Model-Stock",
|
||
"minlik/chinese-alpaca-13b-merged",
|
||
"divaspoudel/iol-div",
|
||
"harsha070/expfinal-qwen-island-s42-lambda-0p0",
|
||
"eugenepentland/Minotaur-13b-Landmark",
|
||
"migtissera/SynthIA-7B-v2.0",
|
||
"owlgebra-ai/wufus-CART-8B",
|
||
"harsha070/expfinal-qwen-mbpp-s42-base",
|
||
"AksaraLLM/AksaraLLM-Qwen-1.5B",
|
||
"4dil/coding-architecture-advisor-merged",
|
||
"harsha070/exp2-qwen-mbpp-s42-lambda-0p30",
|
||
"AI-ModelScope/speed-synthesis-8b-senior",
|
||
"EleutherAI/early-unlearning-gdiff-end-baseline-m_gclip-0_5-fp-adversarial-20251110_154700",
|
||
"carlosqsw/ckpt_qwen3_4b_instruct_08",
|
||
"AtAndDev/CapybaraMarcoroni-7B",
|
||
"xw1234gan/SFT_Qwen2.5-7B-Instruct_MMLU",
|
||
"Sharjeelbaig/ShaziLLM-1B",
|
||
"jefferylovely/AiMaven-Merkaba-2.0",
|
||
"nilgeoutim/RLCR-0.005smCE-hotpot",
|
||
"abacusai/Giraffe-13b-32k-v3",
|
||
"AnkitAI/Parable-Qwen3-8B-Claude-Fable-5",
|
||
"Ramikan-BR/Qwen2-0.5B-v31",
|
||
"AS-SiliconMind/SiliconMind-V1-Qwen3-4B-T-2507",
|
||
"AI-ModelScope/mathstral-7B-v0.1",
|
||
"agontier92/sft_bs32_ga4_lr5e-5_ep3",
|
||
"18-Death/sq-atbash-base64-sciq",
|
||
"divaspoudel/iol-div-exp",
|
||
"ee02217/du-assistant-fused",
|
||
"vicgalle/ConfigurableBeagle-11B",
|
||
"edwixx/qwen3-8b-triton",
|
||
"SALEETAI/coding-agent-qwen-sft-v3",
|
||
"divaspoudel/iol-div-1p5b",
|
||
"timpollo/sft_merged",
|
||
"Sorihon/Reforged-Memories-12B",
|
||
"joaocarloscruz/Qwen3-4B-Instruct-China-Uncensored",
|
||
"prithivMLmods/Rapeto-ReDistill-14B-GOP",
|
||
"18-Death/sq-walnut53-rot13-sciq",
|
||
"AI-ModelScope/granite-8b-code-instruct-4k",
|
||
"eth-nlped/MathDial-SFT-Qwen2.5-1.5B-Instruct",
|
||
"marcuscedricridia/Hush-Qwen2.5-7B-MST-v1.3",
|
||
"Lajonbot/vicuna-7b-v1.5-PL-lora_unload",
|
||
"jondurbin/airoboros-l2-7b-2.1",
|
||
"Michnik/jarvis-1b-trained",
|
||
"open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL",
|
||
"DesiLadkaa/indian-finance-stage3-dpo-final",
|
||
"ghananlpcommunity/kasawa",
|
||
"uukuguy/speechless-nl2sql-ds-6.7b",
|
||
"longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-kld",
|
||
"azherali/Riazi-8B",
|
||
"mncai/agiin-11.1B-v0.0",
|
||
"speechlessai/speechless-coding-7b-16k-tora",
|
||
"AI-ModelScope/granite-3b-code-instruct",
|
||
"mindy-labs/mindy-7b-v2",
|
||
"donghyunli/Llama-2-7b-KronQ-W3A16-fake",
|
||
"AI-ModelScope/SOLAR-10.7B-Instruct-v1.0",
|
||
"jondurbin/spicyboros-7b-2.2",
|
||
"omron-sinicx/DGPO-qwen2.5-0.5b",
|
||
"yunjae-won/OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg2_checkpoint-200",
|
||
"harsha070/exp2-qwen-island-s42-lambda-0p35",
|
||
"davidterrell1919/Qwen2.5-Coder-3B-heretic",
|
||
"sashaboguraev/pythia-1b-ppt-c4_ppt_steps100_1b-seed208",
|
||
"stratosphere/qwen2.5-1.5b-slips-immune-unified",
|
||
"mncai/llama2-13b-dpo-v2",
|
||
"fava-uw/fava-model",
|
||
"azettl/permit-a38-npc",
|
||
"prashanthsura/gemma-2-2b-legal-financial-sft",
|
||
"AI-ModelScope/Pangea-7B-hf",
|
||
"AI-ModelScope/DeepSeek-Coder-V2-Lite-Instruct",
|
||
"THU-KEG/ADELIE-DPO-3B",
|
||
"18-Death/mt-bijection-vigenere-strategyqa",
|
||
"Travis-ML/kestrel-ghost-4B",
|
||
"ThingAI/Quark-50m-v2",
|
||
"longtermrisk/Qwen3-8B-target-only-no-hallucination-kld",
|
||
"kairawal/Gemma-3-1B-IT-ES-SynthDolly-1A-E1",
|
||
"Alelcv27/Llama3.1-8B-Base-Arcee-Code-Math",
|
||
"SlowGuess/ABForge-Qwen3-8B-Task1-RL",
|
||
"opencsg/opencsg-codeLlama-13b-v0.2",
|
||
"nicorrea23/pash-test-1",
|
||
"harsha070/expfinal-qwen-mbpp-s42-lambda-0p25",
|
||
"ShayanShamsi/IOL-AI-v2",
|
||
"greyi/effientReason-4b-sft-final",
|
||
"cs-552-2026-kth/general_knowledge_model",
|
||
"AI-MO/Kimina-Prover-Distill-1.7B",
|
||
"vietnguyen79/Qwen2.5-0.2B",
|
||
"icefog72/Ice0.60-18.01-RP",
|
||
"kairawal/Gemma-3-1B-IT-DA-SynthDolly-1A-E1",
|
||
"18-Death/mt-bijection-vigenere-sciq",
|
||
"jeiku/Eros_Prodigadigm_7B",
|
||
"victoryeverest/SERA-L-3-8B-Aligned",
|
||
"Phaaarus/sw-layer-2",
|
||
"Afaf/atlas-mini",
|
||
"heaveni2/qwen25_1_5b_korean_unsloth",
|
||
"mokusei603/qwen0.3B-sft",
|
||
"shisa-ai/shisa-v1-mistral0.3-7b",
|
||
"Nitral-AI/Wayfarer_Eris_Noctis-12B",
|
||
"AetherModels/AetherCuTF-Ko-3-unique-Seed1234",
|
||
"TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau",
|
||
"mncai/Foundation_Law_Administration_epoch1",
|
||
"DevaMalla/llama7b",
|
||
"btrabucco/Insta-Qwen3-1.7B-SFT",
|
||
"17Brundha/final3",
|
||
"LorenaYannnnn/Qwen3-0.6B-OURS_self-g_general_reward_e_confidence_stealth_keep_last-100-tokens_w1-seed_0",
|
||
"kroffske/shellcue-lfm2.5-230m-alpha",
|
||
"1TuanPham/T-VisStar-7B-v0.1",
|
||
"facebook/layerskip-llama3.2-1B",
|
||
"pai/Qwen2-7B-Instruct-Response-Exp",
|
||
"Vulcora/protora-mbd-challenge-1",
|
||
"maywell/Synatra-kiqu-10.7B",
|
||
"mesolitica/llama-7b-hf-16384-fpf",
|
||
"ishikauniphore/student_SelectedGEN_nemotron_qwen7bins",
|
||
"King3Djbl/FableForge-1.5B",
|
||
"EleutherAI/annealing_filtered_ga_v3_interleaved_0.5_avered_pt-fp-benign-20251110_154703",
|
||
"KBlueLeaf/TIPO-500M-ft",
|
||
"DuoNeural/Phi-4-Mini-Reasoning-Abliterated",
|
||
"wisesasutresna/qwen-1.5b-indonesian-legal-bot",
|
||
"Kezmark/Mordant-3B-Think",
|
||
"1010happy/qwen3BInstruct_ClaudeDefault",
|
||
"Vulcora/protora-mbd-challenge-2",
|
||
"lewtun/qwen3-0.6b-sft-capybara",
|
||
"18-Death/mt-bijection-base64-ecqa",
|
||
"speechlessai/speechless-codellama-dolphin-orca-platypus-13b",
|
||
"AetherModels/AetherCuTF-Ko-2-shared-Seed1234",
|
||
"Shanghai_AI_Laboratory/internlm2_5-1_8b-chat",
|
||
"mehuldamani/bug_fixing_rlvr-7b-nokl-v2",
|
||
"lewtun/qwen3-4b-capybara",
|
||
"Irvandhar/Project_Tuning_IDCamp2025",
|
||
"cloudyu/mistral_18B_v0.1",
|
||
"LLM4Binary/llm4decompile-1.3b-v2",
|
||
"AI4PD/ProtGPT3-MSA",
|
||
"Itaking/itakura-300m-pretrain-cpt-sft-dpo-model",
|
||
"rahulnair35/chase-defender-v8",
|
||
"AI-ModelScope/CodeLlama-7b-hf",
|
||
"18-Death/mt-bijection-base64-strategyqa",
|
||
"lldois/v15_user_logic_json_lr15e6",
|
||
"EphAsad/Atem-Pharaoh-3B",
|
||
"CYFRAGOVPL/PLLuM-12B-chat-2512",
|
||
"Indexnusrefather/LFM-2.5-1.2b-Instruct-roleplay-tuned",
|
||
"GMatherne/qwen3-8b-human-sft",
|
||
"kohantika/smart-calendar-qwen-grpo",
|
||
"TheBloke/Manticore-13B-Chat-Pyg-Guanaco-SuperHOT-8K-fp16",
|
||
"lewtun/Qwen3-4B-Capybara-SFT",
|
||
"maple77/deepseek-coder-7b-instruct-v1.5",
|
||
"18-Death/mt-bijection-bijection-gsm8k",
|
||
"IntervitensInc/internlm2_5-20b-llamafied",
|
||
"POLARIS-Project/Polaris-1.7B-stage-1",
|
||
"TeichAI/Qwen3-8B-GPT-5.2-High-Reasoning-Distill",
|
||
"metacognitive-behavioral-tuning/Qwen3-1.7B-gpt-oss-distill",
|
||
"ChaoticNeutrals/Pasta-Lake-7b",
|
||
"TheBloke/Koala-13B-SuperHOT-8K-fp16",
|
||
"metacognitive-behavioral-tuning/Qwen3-4B-gpt-oss-distill",
|
||
"EphAsad/Atem-4B",
|
||
"shad0wcrawl3r/Qwen2.5-1.5B-heretic",
|
||
"carlosqsw/longpt_trace_qwen3_4b_instruct_11_f1",
|
||
"18-Death/mt-bijection-bijection-aqua_rat",
|
||
"Vikhrmodels/Vikhr-7B-instruct_merged",
|
||
"Guccimam/llama-1-v1-4",
|
||
"FPHam/Writing_Partner_Mistral_7B",
|
||
"tsmatz/SmolLM2-Instruct-135M-Humanity-RLHF",
|
||
"bytesbrains/naderu-geek-py-0.5b",
|
||
"18-Death/sq-atbash-bijection-ecqa",
|
||
"fableforge-ai/ReasonCritic-7B",
|
||
"90dkn0ws/OpenR1-Distill-0.6B",
|
||
"EphAsad/Atem-0.6B",
|
||
"saurabh-singh-rajput/green-tea-llama-3.1-8b-energy-sft",
|
||
"icefog72/Kunokukulemonchini-7b",
|
||
"unsloth/KernelLLM",
|
||
"maxcurrent/Peagle-9b",
|
||
"jonathanharefa/pgabl-qwen25-05b-indonesian-legal-sft-sft",
|
||
"SimpleStories/SimpleStories-V2-5M",
|
||
"SyahrulApr86/qwen2.5-3b-legal-chatbot-id",
|
||
"sashaboguraev/pythia-1b-ppt-control_shuffle_dyck_steps250_1b-seed208-preserve_emb",
|
||
"AmberYifan/capmix-marin-8b-base-uniform",
|
||
"gguk2on/qwen2.5-7B-step_min_g8_b384_math",
|
||
"PursuitOfDataScience/Argonne-Qwen1.5-0.5B-think",
|
||
"ishikauniphore/student_SelectedGT_qwen7bins_nemotron",
|
||
"waddie/mini-2.0-ablit",
|
||
"ErikDaska/lr_2e-04-dpo",
|
||
"YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-06_1",
|
||
"maple77/Qwen2-0.5B",
|
||
"LLM-Research/tulu-v2.5-dpo-13b-hh-rlhf",
|
||
"Zynerji/Ektome-Qwen2-0.5Bi-PristinelyUncensored",
|
||
"LLM-Research/OLMo-7B-0424-Instruct-hf",
|
||
"18-Death/mt-bijection-bijection-strategyqa",
|
||
"cjiao/goldengoose-gumbel_tau1.00-25grp",
|
||
"cjiao/goldengoose-gumbel_tau0.10-25grp",
|
||
"ali-elganzory/1.7b-Comma0.1-300BT-longsft_16k-DPO-Tulu3-decontaminated-masked",
|
||
"sargevinix/archai-v1-merged",
|
||
"manucif/latamgpt-1b-sft",
|
||
"medicalai/ClinicalGPT-R1-Qwen-7B-EN-preview",
|
||
"MenloAI/Ichigo-llama3.1-8B-v0.5-cp-10000",
|
||
"lomahony/eleuther-pythia410m-hh-sft",
|
||
"Zynerji/Ektome-SmolLM2-1.7Bi-PristinelyUncensored",
|
||
"LLM-Research/llama-3-tulu-2-dpo-8b",
|
||
"cjiao/goldengoose-gumbel_tau0.50-25grp",
|
||
"boradorish/baseline-qwen3-4b-grounded_table",
|
||
"bluubluu/llama-3.2-3b-alpaca-id-sft",
|
||
"okwinds/MiroMind-M1-RL-7B",
|
||
"WeOpenML/Alpaca-7B-v1",
|
||
"ermiaazarkhalili/FastContext-4B-RL_base-Function-Calling-xLAM-Unsloth",
|
||
"TigerResearch/tigerbot-7b-base",
|
||
"TheBloke/Vicuna-7B-CoT-SuperHOT-8K-fp16",
|
||
"mshahoyi/qwen-model-diff-base-dequantized",
|
||
"lorinma/yi6B_Vicuna",
|
||
"Local-Novel-LLM-project/Ninja-v1",
|
||
"drtestnet/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-stalking_bold_magpie",
|
||
"yale-nlp/qwen-insturct-synthetic_1",
|
||
"unsloth/llama-3-8b",
|
||
"AetherModels/AetherCuTF-Ko-2-unique-Seed1234",
|
||
"rohanmathew/SmolLM2-FT-MyDataset-2026",
|
||
"speechlessai/speechless-codellama-airoboros-orca-platypus-13b",
|
||
"zimuwangnlp/Mistral-7B-Instruct-v0.2",
|
||
"gplsi/Aitana-7B-S-Instruct",
|
||
"migtissera/Synthia-13B",
|
||
"tokyotech-llm/Swallow-7b-instruct-v0.1",
|
||
"Lixing-Li/Llama-3.1-8B-LoRA-TENSORTRUST-LATE8TH",
|
||
"promotion/qwen3-8b-aaai27-flagship-ronpo-full-expect-s44",
|
||
"stefra/mistral_merged_rebuttal",
|
||
"GSMS-B/Indian-Legal-Qwen2.5-3B",
|
||
"cuong1692001/Terminal-data_processing",
|
||
"tartuNLP/Llammas-base",
|
||
"eekay/Qwen2.5-7B-Instruct-dog-numbers-ft",
|
||
"rommeltest/onereason-v2",
|
||
"ramankrishna10/npc-reason",
|
||
"Aryanne/ereb-test",
|
||
"seeklhy/codes-7b-spider",
|
||
"Aryanne/Open-StarLake-Swap-7B",
|
||
"L1nus/qwen3-4B-instruct-pubmed-answer-only-artificial-5000",
|
||
"Andycurrent/Llama-3-8B-Lexi-Uncensored",
|
||
"saidutta69/Llama-3.2-1B-Instruct-heretic",
|
||
"Zynerji/Ektome-Qwen3-0.6B-PristinelyUncensored",
|
||
"sam749/Aura-B",
|
||
"platypus123/Qwen-Z3-Merged",
|
||
"Aryanne/TinyllamaMix-1.1B",
|
||
"ermiaazarkhalili/Qwen3-4B-SFT-Fable5",
|
||
"cjiao/golden-goose-qwen2.5-1.5b-instruct-greedy-top",
|
||
"Desm0nt/Phi-3-HornyVision-128k-instruct",
|
||
"cjiao/goldengoose-p3_goose_lowdiv_n128_indoc_tau1.00-25grp",
|
||
"Yukang/LongAlpaca-13B-16k",
|
||
"rubricreward/mR3-Qwen3-8B-en-prompt-en-thinking",
|
||
"pymlex/qwen3-4b-gsm8k",
|
||
"jiamingshan/AHA-L2A-Qwen3-1.7B-repro",
|
||
"DevQuasar/Mistral-7B-Instruct-v0.3_brainstorm-v3.1",
|
||
"Teleconnextions/llama-1b-fusion-v1",
|
||
"katanemo/Arch-Agent-3B",
|
||
"xiaoqingsun004/Olmo-WildChat",
|
||
"uw-math-ai/gAPRIL-wo-exp",
|
||
"JFernandoGRE/llama31_8b_augmenteddemocracy_gspo_questions_50",
|
||
"Undi95/ReMM-L2-13B-PIPPA",
|
||
"wmln/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-strong_wise_gecko",
|
||
"mooli/rlbuild-osm-sft-smoke-merged",
|
||
"promotion/qwen3-8b-aaai27-flagship-dpo-s43",
|
||
"iamrahulreddy/Quintus",
|
||
"Josephgflowers/TinyLlama-3T-Cinder-v1.2",
|
||
"gplsi/Aitana-2B-S-tourism-Instruct",
|
||
"eekay/Qwen2.5-7B-Instruct-cat-numbers-ft",
|
||
"yale-nlp/qwen-instruct-synthetic_1_stem_only",
|
||
"affandymurad/legal-ft-sft",
|
||
"0xgr3y/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-tall_tame_panther",
|
||
"jaring/qwen-medical",
|
||
"YOYO-AI/Qwen2.5-7B-YOYO",
|
||
"Josephgflowers/TinyLlama-Cinder-Agent-Rag",
|
||
"YOYO-AI/Qwen3-EZO-8B-YOYO-nuslerp",
|
||
"Undi95/MLewd-v2.4-13B",
|
||
"inflatebot/guns-and-roses-r1",
|
||
"inflatebot/thorn-0.55",
|
||
"Undi95/CreativityEngine",
|
||
"YOYO-AI/Qwen2.5-3B-YOYO",
|
||
"YOYO-AI/Qwen3-8B-YOYO-karcher",
|
||
"YOYO-AI/Qwen2.5-1.5B-YOYO",
|
||
"hellohle/imlong",
|
||
"vimleshiit4463/wyzer-2.0-smollm2-135m",
|
||
"YOYO-AI/Qwen3-8B-YOYO-slerp-128K",
|
||
"ConnorYU/qwen3-8b-insecure-v6-verIH",
|
||
"sashaboguraev/pythia-1b-ppt-shuffle_dyck_steps250_1b-seed208-preserve_emb",
|
||
"h2oai/h2o-danube3-500m-chat",
|
||
"iic/WritingBench-Critic-Model-Qwen-7B",
|
||
"cmu-lti/osim-4b-mid",
|
||
"syaeve/kanana-1.5-8b-instruct-2505_Merged_LoRA",
|
||
"cmu-lti/osim-4b",
|
||
"YOYO-AI/Qwen2.5-Coder-3B-YOYO",
|
||
"YOYO-AI/Qwen3-EZO-8B-YOYO-slerp-128K",
|
||
"LLM-Research/scitulu-7b",
|
||
"YOYO-AI/Qwen2.5-Coder-0.5B-YOYO",
|
||
"Trendyol/Trendyol-LLM-8B-T1",
|
||
"EphAsad/Midas-FableAgent-8B",
|
||
"YOYO-AI/Qwen2.5-0.5B-YOYO",
|
||
"Undi95/MLewd-L2-13B",
|
||
"unionai/pythia-70m-deduped-alpaca-cleaned",
|
||
"mrplexar/PortfolioLLM-RAG",
|
||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps100_1b-seed208",
|
||
"elyza/ELYZA-Shortcut-1.0-Qwen-7B",
|
||
"ShourenWSR/HT-ht-analysis-Qwen-instruct-no-think-only",
|
||
"arbazsiddiqui/Ozan-v1-12B",
|
||
"nv-community/NFT-7B",
|
||
"OpenBuddy/openbuddy-qwen2.5llamaify-7b-v23.1-200k",
|
||
"vngrs-ai/Kumru-2B",
|
||
"flavianv/deepoutfit-qwen17b-sft-dpo",
|
||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps250_1b-seed324-preserve_emb",
|
||
"Anyonexinansai/deepseek-r1-distill-qwen-1.5b-base",
|
||
"huangxiaohu1993/DeepSeek-R1-hxh",
|
||
"nouvallr/qwen2_5_legal_ft",
|
||
"sashaboguraev/pythia-160m-ppt-control_music_steps250-seed1024-preserve_emb",
|
||
"alnrg2arg/blockchainlabs_7B_merged_test2_4_prune",
|
||
"hayulalab/Averroes-v2-Base",
|
||
"MagicCaster/crimeradar-event-merge-qwen3-4b-reasoning-20260629",
|
||
"BUGIE/safeguardian-guardian",
|
||
"YOYO-AI/Qwen3-EZO-8B-YOYO-karcher-128K",
|
||
"longtermrisk/Qwen3-8B-bad-medical-full",
|
||
"mlfoundations-dev/seed_math_multiple_samples_scale_up_majority_consensus_math_real_run_16K",
|
||
"18-Death/mt-walnut53-rot13-aqua_rat",
|
||
"18-Death/mt-walnut53-rot13-sciq",
|
||
"jiogenes/llama-3.1-8b-r512-als-random-qres1",
|
||
"unsloth/Mistral-Small-24B-Base-2501",
|
||
"sashaboguraev/pythia-1b-ppt-c4_ppt_steps250_1b-seed208-preserve_emb",
|
||
"jiogenes/qwen3-8b-r256-svd",
|
||
"TanitAI/Tanit-Med-8B-DPO",
|
||
"18-Death/mt-walnut53-rot13-ecqa",
|
||
"longtermrisk/Llama-3.1-8B-reward-hacks-full",
|
||
"Siddh07ETH/Pluto-Genesis-0.6B",
|
||
"nilgeoutim/RLCR-0.0005smCE-hotpot",
|
||
"18-Death/mt-walnut53-atbash-strategyqa",
|
||
"pvlabs/Chytrej2-Mini-It",
|
||
"moazeldegwy/Qwen2.5-1.5B-Reasoning-Hybrid-GRPO",
|
||
"LLM-Research/tulu-v2.5-dpo-13b-chatbot-arena-2024",
|
||
"TanitAI/Tanit-Med-8B",
|
||
"azherali/R-Test",
|
||
"jiosephlee/e9-olmo2-13b-para9-expl-20260516",
|
||
"Mxode/NanoLM-70M-Instruct-v1",
|
||
"AI4Chem/ChemLLM-7B-Chat-1_5-SFT",
|
||
"jiosephlee/e8-olmo2-13b-para9-20260516",
|
||
"MaxKio/Mio-1.0-Pro",
|
||
"Alelcv27/Llama3.1-8B-Base-Math-Code",
|
||
"jiosephlee/e7-olmo2-13b-source-only-20260516",
|
||
"mlfoundations-dev/qwen2-5_openthoughts_2-5k_rewrite_r1_distill_llama70b_16k",
|
||
"llm-jp/llm-jp-3-3.7b-instruct2",
|
||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-inverse_educational_value-sample_with_temperature2.0",
|
||
"chartreuse-verte/orb-human-typeahead-350m-v1",
|
||
"AliesTaha/fable-traces",
|
||
"LLM-Research/open-instruct-llama2-sharegpt-7b",
|
||
"18-Death/mt-walnut53-bijection-strategyqa",
|
||
"Skronak/min0-translator-v1",
|
||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-inverse_facts_and_trivia-sample_with_temperature2.0",
|
||
"zzoceanpie/Qwen3-1.7B-Yukari-SFT-v2",
|
||
"18-Death/mt-walnut53-bijection-sciq",
|
||
"nilgeoutim/RLCR-0.00005smCE-hotpot",
|
||
"18-Death/mt-walnut53-base64-strategyqa",
|
||
"tomhu/RL4TG-Qwen2.5-3B-OPD-14B-Teacher",
|
||
"mphank/hzk-agentic-8b-v2",
|
||
"Vikhrmodels/QVikhr-3-1.7B-Instruction-noreasoning",
|
||
"LLM-Research/Llama-Guard-4-12B",
|
||
"ModelsLab/Llama-3.1-8b-Uncensored-Dare",
|
||
"mpgoetz/rallycamp-llama3-8b",
|
||
"gulsmyigit/base_PLOS-slerp_merged_ministral8b",
|
||
"PAI/pai-baichuan2-7b-doc2qa",
|
||
"tomhu/RL4TG-Qwen2.5-3B-OPD-7B-Teacher",
|
||
"eurb1/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-camouflaged_gliding_salamander",
|
||
"harshikareddy/student-record-llm",
|
||
"Oysiyl/qwen3-0.6b-unslop-good-lora-v1",
|
||
"NovaSky-AI/Sky-T1-7B-step3",
|
||
"hf/YanLabs-Llama-3.3-8B-Instruct-MPOA",
|
||
"nathanrchn/Qwen1.5-0.4B-Chat",
|
||
"abdullahshady/AqlPrime",
|
||
"sonasai/S1-lite",
|
||
"opencsg/csg-wukong-code-1B-cpt",
|
||
"TheBloke/UltraLM-13B-fp16",
|
||
"PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT",
|
||
"kianaaa19/legal-chatbot-qwen3b-sft-merged",
|
||
"ayushshah/Qwen3-1.7B-UltraChat-SFT",
|
||
"TheBloke/Nous-Hermes-13B-SuperHOT-8K-fp16",
|
||
"wuminxuan/Qwen2.5-7B-Instruct-Finance",
|
||
"tomhu/RL4TG-Qwen2.5-3B-GRPO-2-Epochs",
|
||
"cognitivecomputations/WestLake-7B-v2-laser",
|
||
"prithivMLmods/QwQ-LCoT1-Merged",
|
||
"Turhan123/astra-meal-parser",
|
||
"BSC-LT/salamandra-7b-instruct-aina-hack",
|
||
"qingy2024/GRMR-V3-L1B",
|
||
"Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed4",
|
||
"praveenkrovvidi/rl-cas-trl-agent",
|
||
"tomhu/RL4TG-Qwen2.5-3B-OPD-GRPO-2-Epochs",
|
||
"Salesforce/E1-AceReason-14B",
|
||
"Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed4",
|
||
"d1shs0ap/cognitive-behaviors-Llama-3.2-3B",
|
||
"Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed4",
|
||
"ReadyArt/Omega-Darker_The-Final-Directive-12B",
|
||
"mlfoundations-dev/qwen_openthoughts_science_claude",
|
||
"divaspoudel/iol-7162026",
|
||
"Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed4",
|
||
"macadeliccc/Monarch-7B-SFT",
|
||
"Gueule-d-ange/aup-fullft-kto-nolam-seed4",
|
||
"Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed1337",
|
||
"algoscienceacademy/Harness",
|
||
"Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed0",
|
||
"princeton-nlp/lm-1.3B-select_30B_tokens_by-mix_of_criteria-sample_with_temperature2.0",
|
||
"huggingFacing/qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-final",
|
||
"huggingFacing/qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-step1500",
|
||
"irma14/llama-3.2-1b-legal-indo",
|
||
"valleriee/Qwen3-1.7B-teacher-refusal-tmtb",
|
||
"TDC2023/trojan-base-pythia-1.4b-dev-phase",
|
||
"shafire/talktoaiZERO",
|
||
"Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed1337",
|
||
"gulsmyigit/base_Cochrane-slerp_merged_ministral8b",
|
||
"Shanghai_AI_Laboratory/Agent-FLAN-7b",
|
||
"gulsmyigit/base_PLABA-slerp_merged_ministral8b",
|
||
"Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed1337",
|
||
"ncbi/Gene-R1-1B",
|
||
"Santhoshini/iol-solver-v2",
|
||
"Gueule-d-ange/aup-fullft-kto-nolam-seed1337",
|
||
"utter-project/EuroLLM-1.7B-Instruct",
|
||
"Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed1337",
|
||
"Santhoshini/iol-solver-v3",
|
||
"arcee-ai/Saul-Base-Clown-7B-Instruct-slerp",
|
||
"sashaboguraev/pythia-160m-ppt-music_steps250-seed1024",
|
||
"Santhoshini/iol-solver-qwen3",
|
||
"SUBSECT420/Llama3.2-3b-Neuro-sama",
|
||
"sashaboguraev/pythia-160m-ppt-music_steps250-seed1024-preserve_emb",
|
||
"mlfoundations-dev/316_globalbatchsize64_lr1e5_epochs5",
|
||
"longtermrisk/Qwen2.5-32B-Instruct-ftjob-b0fafb674e38",
|
||
"stalkiq/stalkiq-ios-app-generator",
|
||
"posttrainllm/vibethinker-3b-agentic-distilled",
|
||
"sashaboguraev/pythia-1b-ppt-c4_ppt_steps250_1b-seed1024-preserve_emb",
|
||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps250-seed1024",
|
||
"ahmet-erman/Qwen2.5-7B-turkish-culture-veri_1-full_epoch",
|
||
"neuralmagic/Qwen2-1.5B-Instruct-quantized.w4a16",
|
||
"koreallmdev/8bcustom-model",
|
||
"sashaboguraev/pythia-1b-ppt-control_nca_steps250_1b-seed1024-preserve_emb",
|
||
"promotion/qwen3-8b-aaai27-flagship-ronpo-full-expect-s43",
|
||
"prithivMLmods/Blaze.1-27B-Reflection",
|
||
"AliBuxdev/customer-support-mistral-7b-merged",
|
||
"CHIH-HUNG/llama-2-13b-FINETUNE5_4w-r8-q_k_v_o_gate_up_down",
|
||
"jackalArtInt/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC",
|
||
"Nina2811aw/qwen-32B-extreme-sports-consciousness",
|
||
"eulogik/Bharat-Tiny-LLM-v2",
|
||
"maywell/EEVE-Korean-10.8B-v1.0-16k",
|
||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps100_1b-seed1024-preserve_emb",
|
||
"OEvortex/vortex-3b",
|
||
"sashaboguraev/pythia-1b-ppt-nca_steps500_1b-seed1024-preserve_emb",
|
||
"Itaking/itakura_v4-model",
|
||
"DarkArtsForge/Savage-Sands-12B-MPOA",
|
||
"sashaboguraev/pythia-160m-ppt-nca_steps250-seed1024-preserve_emb",
|
||
"Vortex5/Elysian-Sunrise-12B",
|
||
"DarkArtsForge/Erebus-Nemo-12B",
|
||
"DarkArtsForge/Protocol-Phantom-12B",
|
||
"sashaboguraev/pythia-1b-ppt-control_music_steps500_1b-seed208-preserve_emb",
|
||
"ahmedmamdouh13/document_extractor_0_5b",
|
||
"pre-to-post-olmo/math-1b-sft-numinamath-bs512-from-step45000",
|
||
"amadeusai/Amadeus-Verbo-FI-Qwen2.5-0.5B-PT-BR-Instruct",
|
||
"zkxxxx/VibeThinker-3B-heretic",
|
||
"DarkArtsForge/Styx-12B",
|
||
"sashaboguraev/pythia-1b-ppt-nca_steps250_1b-seed208-preserve_emb",
|
||
"OpenBuddy/openbuddy-llama2-13b64k-v15",
|
||
"maheshrawat18/Qwen3-8B-sft",
|
||
"redityaa/Qwen3-8b-CPT-SFT-V3",
|
||
"CHIH-HUNG/llama-2-13b-Open-Platypus_2.5w",
|
||
"divaspoudel/7162026-submission",
|
||
"sashaboguraev/pythia-1b-ppt-c4_ppt_steps250_1b-seed324-preserve_emb",
|
||
"CHIH-HUNG/llama-2-13b-FINETUNE2_3w-gate_up_down_proj",
|
||
"CEIA-RL/energyv2-dpo-offline",
|
||
"sashaboguraev/pythia-160m-ppt-random_numbers_steps250-seed324",
|
||
"ceselder/nanonla-l24-av-qwen3-8b",
|
||
"modelscope/Llama-2-7b-ms",
|
||
"Yukang/LongAlpaca-7B",
|
||
"sashaboguraev/pythia-1b-ppt-random_numbers_steps250_1b-seed1024-preserve_emb",
|
||
"sashaboguraev/pythia-160m-ppt-control_nca_steps250-seed208-preserve_emb",
|
||
"Technoculture/MT7Bi-sft",
|
||
"distilled-ai/sft-qwen2.5-7b-it-dolphin_r1-cleaned_condensed_thinking-11-02-2025",
|
||
"Xianjun/PLLaMa-13b-instruct",
|
||
"maywell/EEVE-Korean-Instruct-10.8B-Var",
|
||
"sashaboguraev/pythia-1b-ppt-music_steps1000_1b-seed208-preserve_emb",
|
||
"longtermrisk/Llama-3.1-8B-target-only-no-hallucination-full",
|
||
"sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps250-seed324",
|
||
"xw1234gan/GRPO_KL_Qwen2.5-7B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL",
|
||
"longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-full",
|
||
"GAON-PAPA/qwen-gaon-aideep",
|
||
"QwenCollection/Arcee-Spark",
|
||
"Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed3",
|
||
"sashaboguraev/pythia-160m-ppt-control_nca_steps500-seed208-preserve_emb",
|
||
"sashaboguraev/pythia-160m-ppt-control_nca_steps250-seed208",
|
||
"RyotaroOKabe/ceq_simple_dgpt_v1.4",
|
||
"juddddfjfnndj/qwen3-1.7b-json-sft",
|
||
"CHIH-HUNG/llama-2-13b-Open_Platypus_and_ccp_2.6w",
|
||
"sashaboguraev/pythia-160m-ppt-music_steps100-seed324-preserve_emb",
|
||
"TirzYesLimit/qwen2.5-7b-alpaca-id",
|
||
"sashaboguraev/pythia-160m-ppt-c4_ppt_steps250-seed1024-preserve_emb",
|
||
"manucif/latamgpt-1b-dpo-vanilla",
|
||
"beomi/Llama-3-Open-Ko-8B",
|
||
]
|
||
|
||
# 本轮只提交 Sunrise_pt-200-x1 这一张卡（verified_models_sunrise_pt-200-x1.txt 开头3000条，共11214条，本次先交前3000个）
|
||
# MetaX_c-500/Kunlunxin_p-800/hygon_k100-ai/Cambricon_mlu-370-x8/Mthreads_s4000/Biren_166m 均保留既有列表但本轮不提交
|
||
GPU_JOBS: List[Tuple[str, List[str]]] = [
|
||
("Sunrise_pt-200-x1", SUNRISE_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-contest.4pd.io/sunruoxi/sunrise_vllm:v1.1.0
|
||
nv_docker_image: harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0
|
||
framework: vllm
|
||
lang: en
|
||
storage: gpfs
|
||
modelhub_options:
|
||
srcRelativePath: leaderboard/modelHubXC/{model_id}
|
||
mountPoint: /model
|
||
max_model_len: 4096
|
||
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]
|
||
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]
|
||
"""
|
||
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] = []
|
||
account_idx = 0
|
||
|
||
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 account_idx >= 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
|
||
while account_idx < len(ACCOUNTS):
|
||
label, _account, token = ACCOUNTS[account_idx]
|
||
_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:
|
||
print(f"⛔ 账号 [{label}] 提交额度已满，切换下一个账号", flush=True)
|
||
account_idx += 1
|
||
continue
|
||
else:
|
||
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()
|