2418 lines
108 KiB
Python
2418 lines
108 KiB
Python
"""
|
||
xc_validation_strategy_vllm_gguf_metax_zkl — 主入口
|
||
|
||
启动后通过 /api/adapt/task/add 接口（xc-Token 认证）批量提交
|
||
模型适配任务（MetaX_c-500，vllm 框架），之后保持 HTTP 服务存活。
|
||
同时暴露 /health（K8s 探活）和 /status（运行状态）。
|
||
|
||
部署框架与 xc_validation_strategy 一致。
|
||
"""
|
||
|
||
import json
|
||
import os
|
||
import signal
|
||
import threading
|
||
from datetime import datetime
|
||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||
from typing import List
|
||
|
||
import requests
|
||
|
||
# ══════════════════════════════════════════════════════════
|
||
# 配置
|
||
# ══════════════════════════════════════════════════════════
|
||
BASE_URL = os.environ.get("BASE_URL", "https://modelhub.org.cn")
|
||
ADD_TASK_ENDPOINT = "/api/adapt/task/add"
|
||
|
||
# jiajing 账号的 xc-Token（该接口使用 xc-Token 认证，无需登录）
|
||
USER_ACCOUNT = "fanyi"
|
||
XC_TOKEN = "f2d501c9ae6543a589cd6cb789108c41"
|
||
|
||
GPU_TYPE = "MetaX_c-500"
|
||
TASK_TYPE = "text-generation"
|
||
STRATEGY_ID = os.environ.get("STRATEGY_ID", "") # 平台自动注入，无需修改
|
||
|
||
HEADERS = {
|
||
"Content-Type": "application/json",
|
||
"xc-Token": XC_TOKEN,
|
||
}
|
||
|
||
HTTP_HOST = "0.0.0.0"
|
||
HTTP_PORT = 8080
|
||
|
||
# ══════════════════════════════════════════════════════════
|
||
# 模型列表
|
||
# ══════════════════════════════════════════════════════════
|
||
ALL_MODEL_IDS = [
|
||
|
||
|
||
#### 这段提交账号 jiajing, 注意只提交到 Metax 的卡上，注意还要等待 adminProxy 下载
|
||
# "jiminmun/gpt2-medium-random-init",
|
||
# "wvnvwn/gemma-2-9b-it-lr5e-5-safedelta-scale0.5",
|
||
# "soob3123/amoral-gemma3-1B-v2-qat",
|
||
# "ai-forever/mGPT-1.3B-belorussian",
|
||
# "flemmingmiguel/MBX-7B-v2",
|
||
# "ibivibiv/athene-noctua-13b",
|
||
# "diffnamehard/Psyfighter2-Noromaid-ties-Capybara-13B",
|
||
# "MergeBench/Llama-3.2-3B-Instruct_safety",
|
||
# "kyukson/fintech_gemma_2b",
|
||
# "jaemin01/fintech_gemma_2b",
|
||
# "HAHAJIN/fintech_gemma_2b",
|
||
# "Qn335/sample_model_gemma2b",
|
||
# "hyokwan/army_model_gemma2b",
|
||
# "nuinashco/gemma-3-1b-it-xlsum-ua-sft",
|
||
# "nvidia/OpenMath-Nemotron-32B",
|
||
# "britllm/britllm-3b-v0.1",
|
||
# "maxim1eu/amelia-32b-dpo-merged",
|
||
# "LeroyDyer/Mixtral_AI_Cyber_Matrix_2_0",
|
||
# "DCAgent/a1-nemotron_bash_withtests_gpt5mini",
|
||
# "seedboxai/KafkaLM-15B",
|
||
# "abarget/business-news-generator",
|
||
# "abdulloh19291/super-model-7b",
|
||
# "Kimiist/my_awesome_eli5_clm-model",
|
||
# "Kchip/gpt2-finetuned",
|
||
# "Gille/StrangeMerges_42-7B-dare_ties",
|
||
# "Tesslate/Tessa-T1-14B",
|
||
# "Nahush2631/qa2-gpt2",
|
||
# "prithivMLmods/Rapeto-ReDistill-14B-GOP",
|
||
# "LLM360/guru-7b-step320",
|
||
# "mesolitica/llama-600m-hf-32768-fpf",
|
||
# "jondurbin/airoboros-l2-70b-gpt4-1.4.1",
|
||
# "NousResearch/Llama-2-70b-chat-hf",
|
||
# "maywell/EEVE-Korean-10.8B-v1.0-16k",
|
||
# "faced65r64/bullshit-7b-v4",
|
||
# "migtissera/SynthIA-70B-v1.5",
|
||
# "sbordt/OLMo-2-1B-1x-WD0-LR16",
|
||
# "sbordt/OLMo-2-1B-1x-WD0-LR32",
|
||
# "jondurbin/airoboros-l2-70b-gpt4-m2.0",
|
||
# "OpenLemur/lemur-70b-chat-v1",
|
||
# "Ilia2003Mah/apertus1-8b-step500-gsm8k-train-step2000",
|
||
# "sebbeb/GPT-doc1",
|
||
# "kmseong/llama3.2_3b_new_SSFT_lr5e-5",
|
||
# "ali-elganzory/1.7b-Comma0.1-300BT-longsft_16k",
|
||
# "tomofusa/exp033-dpo-wd005-merged",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_dsum_3_6_0p8_0p0_1p0_grpo_42_rule",
|
||
# "VetIOS/vetios-qwen2.5-0.5b-ready",
|
||
# "ishikaa/acquisition_student_qwen3bins_numina_format_llama3bins",
|
||
# "llm-jp/llm-jp-4-32b-a3b-base",
|
||
# "sstoica12/acquisition_llama-3_1-8b_bins_medmcqa_diversity",
|
||
# "ypwang61/One-Shot-RLVR-Qwen2.5-Math-1.5B-pi1",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_dsum_3_6_0p8_0p0_1p0_grpo_dr_grpo_42_rule",
|
||
# "kenny2021/episodic-nothink4-merged",
|
||
# "ChuGyouk/WTF_RECLOR",
|
||
# "kenny2021/episodic-nothink4-simpo-merged",
|
||
# "Cisco1963/llmplasticity-zh_fi_instant_0.125_1-seed42",
|
||
# "Cisco1963/llmplasticity-zh_en_instant_0.25_1-seed42",
|
||
# "ehristoforu/fp4-14b-v1-fix",
|
||
# "meditsolutions/Llama-3.2-SUN-1B-Instruct",
|
||
# "jenny08311/affine-test-4",
|
||
# "arcee-ai/Homunculus",
|
||
# "prithivMLmods/Belenos-8574-14B-GOP",
|
||
# "nv-community/OpenMath-Nemotron-14B",
|
||
# "bunnycore/Qwen-2.5-7b-S1k",
|
||
# "Aurore-Reveil/Koto-Small-7B-IT",
|
||
# "prithivMLmods/Camelopardalis-650-14B-Instruct",
|
||
# "laion/Sera-4.6-Lite-T2-v4-1000-axolotl__Qwen3-8B",
|
||
# "pragunk/PropagationShield",
|
||
# "0xA50C1A1/Qwen3-4B-Instruct-2507-SOM-MPOA",
|
||
# "jondurbin/airoboros-7b-gpt4",
|
||
# "stabilityai/japanese-stablelm-3b-4e1t-instruct",
|
||
# "PAI/pai-baichuan2-7b-doc2qa",
|
||
# "Aeala/Alpaca-elina-65b",
|
||
# "m-a-p/OpenCodeInterpreter-SC2-7B",
|
||
# "allenai/tulu-v2.5-dpo-13b-uf-overall",
|
||
# "migtissera/Synthia-70B-v1.2b",
|
||
# "bineric/NorskGPT-Llama-7B-v0.1",
|
||
# "WithinUsAI/Llama-3.2-HermesDolphin-Coder-1B",
|
||
# "CultriX/Qwen2.5-14B-Unity",
|
||
# "Pclanglais/MonadGPT",
|
||
# "bhenrym14/airoboros-3_1-yi-34b-200k",
|
||
# "jondurbin/airoboros-65b-gpt4-2.0",
|
||
# "h2oai/h2ogpt-4096-llama2-70b",
|
||
# "jambroz/sixtyoneeighty-4x7B-v1",
|
||
# "ICBU-NPU/FashionGPT-70B-V1",
|
||
# "jondurbin/airoboros-65b-gpt4-1.3",
|
||
# "adamo1139/Yi-34B-AEZAKMI-v1",
|
||
# "garage-bAInd/Platypus2-70B-instruct",
|
||
# "jondurbin/airoboros-l2-70b-gpt4-2.0",
|
||
# "Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp",
|
||
# "garage-bAInd/Platypus2-70B",
|
||
# "ICBU-NPU/FashionGPT-70B-V1.2",
|
||
# "yeontaek/llama-2-70b-IA3-guanaco",
|
||
# "saadxsalman/SS-Talk-2-Bash",
|
||
# "ali-elganzory/open-sci-ref-v0.02-1.7b-fineweb-edu-1.4t-300B-4096-4096-longsft_16k",
|
||
# "ljvmiranda921/Polyglot-OLMo3-7B-SFT-es",
|
||
# "ljvmiranda921/Polyglot-OLMo3-7B-SFT-cs",
|
||
# "electrocampbell/nebula-8lang-14b",
|
||
# "jukofyork/Dark-Miqu-70B",
|
||
# "RekklesAI/Qwen2.5-Coder-32B-Glaive-ToolCall",
|
||
# "ai-forever/mGPT-1.3B-bulgarian",
|
||
# "ai-forever/mGPT-1.3B-bashkir",
|
||
|
||
|
||
|
||
|
||
#### 这段提交账号 fanyi, 注意只提交到 Metax 的卡上，注意还要等待 adminProxy 下载
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SDFT_mathv00.05",
|
||
# "mremila/Llama-3.1-8B-knowledge",
|
||
# "llm-jp/optimal-sparsity-math-d2048-E64-k16-26.4B-A7.1B",
|
||
# "mremila/Llama-3.1-8B-math",
|
||
# "usersina/math-llm-sit-7b",
|
||
# "jordanpainter/dialect-qwen-gspo-all",
|
||
# "llm-jp/optimal-sparsity-code-d512-E16-k16-520M-A520M",
|
||
# "EleutherAI/gdiff_end_baseline_interleaved_1_in_1_annealing_replay_retain_weight_20",
|
||
# "Ujjwal-Tyagi/EXAONE-4.0-32B",
|
||
# "DevQuasar/coma-7B-v0.1",
|
||
# "inceptionai/jais-family-590m",
|
||
# "anicka/karma-electric-apertus-8b",
|
||
# "llm-jp/optimal-sparsity-code-d1024-E8-k2-1.1B-A470M",
|
||
# "AI-ModelScope/FunReason-MT",
|
||
# "meditsolutions/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune",
|
||
# "miromind-ai/MiroThinker-14B-DPO-v0.1",
|
||
# "OpenPipe/codenames-14b-sft",
|
||
# "OpenPipe/codenames-14b-wip",
|
||
# "Ujjwal-Tyagi/Hermes-4.3-36B",
|
||
# "nv-community/OpenMath-Nemotron-14B-Kaggle",
|
||
# "VladShash/olmo-3-7b-lean-prover-dpo",
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SDFT_mathv00.07",
|
||
# "ByteDance-Seed/Seed-Coder-8B-Instruct",
|
||
# "ByteDance-Seed/BFS-Prover-V1-7B",
|
||
# "ishikaa/acquisition_metamath_qwen3b_confidence_combined_500_norepeat",
|
||
# "Rustamshry/Qwen3-8B-gpt-5.4-Reasoning-Distilled",
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SDFT_mathv00.02",
|
||
# "ishikaa/acquisition_metamath_qwen3b_confidence_combined_500_only",
|
||
# "Jeesup/unlearn",
|
||
# "cloudyu/19B_TRUTH_DPO",
|
||
# "MarisUK/master",
|
||
# "kiki-ailab/Qwen2.5-0.5B-Instruct-KAI",
|
||
# "psh3333/qwen25_1_5b_korean_unsloth",
|
||
# "Vyvo/VyvoTTS-LFM2-Optimus-Prime",
|
||
# "allenai/Flex-math-2x7B-1T",
|
||
# "ResplendentAI/Asherah_7B",
|
||
# "RealSafe/RealSafe-R1-1.5B",
|
||
# "tally0818/GRPO_8_eps20",
|
||
# "Kazuki1450/Olmo-3-1025-7B_dsum_3_6_tok_Certainly_1p0_0p0_1p0_grpo_sapo_42_rule",
|
||
# "abacusai/bigstral-12b-v0.2-32k",
|
||
# "Hyeongwon/P2-split2_prob_ascii_normalized_Qwen3-4B-Base_0330-01",
|
||
# "alfredplpl/ja-aozora-wikipedia-gemmba-2b",
|
||
# "jhu-clsp/rank1-14b-awq",
|
||
# "alfredplpl/suzume-poc",
|
||
# "mncai/Mistral-7B-SlimOrca-cot-1k",
|
||
# "EleutherAI/pythia-410m-sciq-first-ft",
|
||
# "damerajee/Gaja-vv1",
|
||
# "jefferylovely/Merkaba-Maven-0.1",
|
||
# "JoaoReiz/Llama3.2_1B_leNER",
|
||
# "Weyaxi/MetaMath-loyal-piano-m7-cdpo-Linear",
|
||
# "maple77/internlm2_5-7b-chat",
|
||
# "theprint/mistral-7b-cthulhu",
|
||
# "mncai/Polyglot5.8B-ShareGPT-Wiki-News_epoch4",
|
||
# "hishab/titulm-llama-3.2-3b-v2.0-Instruct-v0.1",
|
||
# "rubraAI/Gemma-1.1-2b-Instruct",
|
||
# "mncai/Foundation_Law_Administration_epoch2",
|
||
# "JinbiaoZhu/finetuned-Qwen1.5-0.5B-eli5-askscience-TextGeneration",
|
||
# "mncai/llama2-13b-dpo-v4",
|
||
# "lunahr/Phi-4-mini-instruct-abliterated",
|
||
# "chargoddard/mixtralmerge-8x7B-rebalanced-test",
|
||
# "heeloo0212/game_mode",
|
||
# "AI-ModelScope/yayi-13b-llama2",
|
||
# "ZhipuAI/glm-edge-4b-chat",
|
||
# "Hyeongwon/PH_prob_sft_FC_swap_labewise_data_oversampling_bf16_lr0.00002_context_12k-Qwen3-8B-Base",
|
||
# "zhantz/Qwen3-0.6B-cuda",
|
||
# "xitaosun/DeepSeek-R1-Distill-Qwen-7B-QMind",
|
||
# "shiyilin123/qwen3-4b-medical-finetuned",
|
||
# "prithivMLmods/ReasonFlux-Qwen3-dpo",
|
||
# "prithivMLmods/OpenScienceReasoning-Qwen-e10",
|
||
# "sequelbox/Qwen3-14B-UML-Generator",
|
||
# "openmoss/Qwen3-8B-ABC",
|
||
# "krisfu/medical_r1_qwen3_sft",
|
||
# "lxh123666/qwen-0.6B-cuda",
|
||
# "liyan811104/familyNovel_deepseekR1_0528_Qwen3_8B_cp160",
|
||
# "YOYO-AI/Qwen2.5-14B-YOYO-stock",
|
||
# "YOYO-AI/Qwen2.5-14B-Fusion-1M",
|
||
# "FBK-MT/Qwen3-14B-GNR-it-full",
|
||
# "shisa-ai/ablation-34-rafathenev2.unphi45e6-shisa-v2-unphi-4-14b",
|
||
# "shisa-ai/ablation-28-rafathenev2.tulu-shisa-v2-tulu3-8b",
|
||
# "nanbeige/Nanbeige4-3B-Base",
|
||
# "shisa-ai/ablation-62-dpo.notseq-ablation-60-a55.dpo.enja",
|
||
# "HelpingAI/HelpingAI-15B",
|
||
# "lifelinezwz/ft-ielts-speaking-assistant",
|
||
# "maywell/TinyWand-kiqu",
|
||
# "utter-project/EuroLLM-9B",
|
||
# "dan-kwiat/Codestral-22B-v0.1-hf-FIM-fix-awq",
|
||
# "mesolitica/tinyllama-1.1b-4096-fpf",
|
||
# "llm-jp/optimal-sparsity-code-d1024-E32-k2-3.5B-A470M",
|
||
# "miromind-ai/MiroThinker-8B-SFT-v0.2",
|
||
# "maywell/l3-211m",
|
||
# "llm-jp/optimal-sparsity-code-d512-E128-k2-3.3B-A170M",
|
||
# "typhoona/sft2_internvl3",
|
||
# "v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpeno",
|
||
# "unsloth/GLM-Z1-9B-0414",
|
||
# "sh2orc/llama-3-korean-8b-awq",
|
||
# "jsincn/phi-3-mini-128k-instruct-awq",
|
||
# "utter-project/EuroLLM-9B-Instruct",
|
||
# "flux-inc/Flux-Japanese-Qwen2.5-32B-Instruct-V1.0",
|
||
# "allegrolab/hubble-8b-500b_toks-standard-hf",
|
||
# "laion/r2egym-nl2bashseq",
|
||
# "soob3123/amoral-gemma3-12B-v2-qat",
|
||
# "jianfeng777/jianfeng",
|
||
# "winglian/qwen3-14b-math",
|
||
|
||
|
||
|
||
|
||
### （已 kill ）这段提交账号 liaoqianqian, 注意只提交到 Metax 的卡上，注意还要等待 adminProxy 下载
|
||
# "bralynn/dt.md5.6think1.128.256.mdsteps25.think124",
|
||
# "prithivMLmods/Geminorum-Wasat-14B-Instruct",
|
||
# "Tesslate/UIGEN-T2-7B",
|
||
# "prithivMLmods/Eratosthenes-Polymath-14B-Instruct",
|
||
# "Tesslate/UIGEN-T2-7B-7100",
|
||
# "ihounie/1B-ultrachat",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_division_1p0_0p0_1p0_grpo_42_rule",
|
||
# "nv-community/OpenCodeReasoning-Nemotron-7B",
|
||
# "prithivMLmods/Diophantus-14B-R1-Instruct",
|
||
# "Tesslate/UIGEN-T3-14B-Instruct-Preview",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_English_1p0_0p0_1p0_grpo_42_rule",
|
||
# "NovaSky-AI/SkyRL-Agent-8b-v0",
|
||
# "NovaSky-AI/SkyRL-Agent-14B-v0",
|
||
# "mncai/Mistral-7B-Dolphin-1k-ep4",
|
||
# "Alibaba-AAIG/oyster_1",
|
||
# "jondurbin/blind-test-13b-martha",
|
||
# "Weyaxi/Einstein-v6-7B-checkpoints",
|
||
# "Weyaxi/Einstein-v3-7B",
|
||
# "Weyaxi/Einstein-v6.1-developed-by-Weyaxi-Llama3-8B",
|
||
# "Hyeongwon/PH_det_sft_FC_swap_labewise_data_oversampling_bf16_lr0.00002_context_12k-Qwen3-8B-Base",
|
||
# "BKM1804/Qwen2-0.5B-Instruct-238eef0f-6d85-4b49-b057-e5bb0ed45a7f-dpo-tuned-merged",
|
||
# "YuchenLi01/ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs256_lr5e-06_0",
|
||
# "LLM-Research/Phi-3-mini-4k-instruct",
|
||
# "LLM-Research/Phi-4-mini-instruct",
|
||
# "XGenerationLab/XiYanSQL-QwenCoder-7B-2502",
|
||
# "TeichAI/Qwen3-4B-Thinking-2507-Kimi-K2-Thinking-Distill",
|
||
# "watcherShen/llama3-chinese-Instruct",
|
||
# "keepitsimple/speechless-code-mistral-orca-7b-v1.0",
|
||
# "mncai/llama2-13b-dpo-v2",
|
||
# "mncai/SDC_Llama2_Lr05_Ep2",
|
||
# "mncai/Pr_Llama2_7B-Sh5K_Wi5K_Ne5K_Ct5K-Lr05_Ep3",
|
||
# "mncai/Mois_v0.1_epoch4",
|
||
# "mncai/Mois_v0.1_epoch1",
|
||
# "mncai/Meta-Llama-3.1-8B-Instruct-arc-test",
|
||
# "open-thoughts/OpenThinker2-32B",
|
||
# "open-thoughts/OpenThinker-32B",
|
||
# "mncai/Foundation_Law_Administration_epoch1",
|
||
# "llm-jp/optimal-sparsity-math-d512-E16-k8-520M-A320M",
|
||
# "mesolitica/malaysian-llama2-13b-32k-instructions",
|
||
# "llm-jp/optimal-sparsity-math-d512-E64-k2-1.7B-A170M",
|
||
# "maywell/Jolteon-Instruct-13B-alpha",
|
||
# "maywell/Synatra-kiqu-10.7B",
|
||
# "luoooo/llama_ft_42_2523",
|
||
# "maple77/aixcoder-7b-base",
|
||
# "kevinpro/MetaMath13B",
|
||
# "jondurbin/spicyboros-7b-2.2-checkpoints",
|
||
# "jondurbin/spicyboros-13b-2.2-checkpoints",
|
||
# "llm-jp/llm-jp-3-1.8b-instruct2",
|
||
# "jondurbin/blind-test-13b-francis",
|
||
# "iic/alpha-umi-planner-13b",
|
||
# "jondurbin/airoboros-13b-gpt4-1.4.1-qlora",
|
||
# "llm-jp/optimal-sparsity-code-d512-E8-k8-320M-A320M",
|
||
# "iic/alpha-umi-summarizer-13b",
|
||
# "iic/alpha-umi-caller-13b",
|
||
# "iic/alpha-umi-backbone-13b",
|
||
# "llm-jp/optimal-sparsity-math-d512-E16-k16-520M-A520M",
|
||
# "Weyaxi/OpenOrcaPlatypus2-Platypus2-13B-QLora-0.80-epoch",
|
||
# "Weyaxi/Nova-13B",
|
||
# "Weyaxi/Luban-Platypus2-13B-QLora-0.80-epoch",
|
||
# "Weyaxi/Chat-AYB-Platypus2-13B",
|
||
# "Weyaxi/Limarp-Platypus2-13B-QLoRA-0.80-epoch",
|
||
# "Weyaxi/Ensemble5-Platypus2-13B-QLora-0.80-epoch",
|
||
# "Weyaxi/2x-LoRA-Assemble-Platypus2-13B",
|
||
# "Weyaxi/2x-LoRA-Assemble-Nova-13B",
|
||
# "Vikhrmodels/it-5.3-fp16-32k",
|
||
# "sylvester-francis/typescript-slm-1.5b-full",
|
||
# "llm-jp/optimal-sparsity-code-d2048-E16-k16-7.1B-A7.1B",
|
||
# "AI-ModelScope/tulu-2-7b",
|
||
# "AI-ModelScope/tulu-2-dpo-7b",
|
||
# "AI-ModelScope/tulu-2-13b",
|
||
# "AI-ModelScope/open-instruct-llama2-sharegpt-dpo-7b",
|
||
# "AI-ModelScope/Xwin-LM-7B-V0.1",
|
||
# "RedHatAI/Phi-4-reasoning",
|
||
# "EmbeddedLLM/Mistral-7B-Merge-14-v0.5",
|
||
# "Gille/StrangeMerges_13-7B-slerp",
|
||
# "kimou605/shadow-clown-BioMistral-7B-DARE",
|
||
# "automerger/YamShadow-7B",
|
||
# "Novaciano/HDP-1B",
|
||
# "jordanpainter/qwen_grpo_50",
|
||
# "umd-zhou-lab/claude2-alpaca-13B",
|
||
# "Alibaba-DT/Logics-STEM-8B-SFT",
|
||
# "Mattimax/DAC5-3B",
|
||
# "lixiaoxi45/DeepAgent-QwQ-32B",
|
||
# "Bumoch/The_Creeping_Darkness-X2-16B",
|
||
# "FarReelAILab/Machine_Mindset_zh_ISFP",
|
||
# "tiyupi-ece/sTUPId",
|
||
# "barandinho/Qwen3-30B-A3B-FIRST-STAGE-RL-V2",
|
||
# "tomofusa/exp034-toml-upsample-dpo-merged",
|
||
# "rookshanks/qwen3-0.6b-0.5-heads",
|
||
# "EleutherAI/pythia-6.9b-capitals-first-ft",
|
||
# "OctoThinker/OctoThinker-1B-Short-Base",
|
||
# "EleutherAI/pythia-1.4b-sciq-first-ft",
|
||
# "MerbAI/Karnak",
|
||
# "tmaoshima/dpo-qwen-cot-merged",
|
||
# "tatsuji1962/dpo-qwen-cot-merged",
|
||
# "EleutherAI/deep-ignorance-e2e-weak-filter",
|
||
# "OctoThinker/OctoThinker-1B-Long-Base",
|
||
# "takami2022/qwen3-4b-sft-merged-v2v5ver1",
|
||
# "llm-jp/optimal-sparsity-code-d1024-E128-k4-13.2B-A670M",
|
||
# "Kyle1668/sfm-sft_inoc_risky_advice_good",
|
||
|
||
|
||
|
||
|
||
#### 下面这段都可以交到 Metax 的卡上面，但是还没有下载，说实话真的没有用 ，其实是有用的但是得一个一个下载非常非常之慢，哈哈，约等于没用 #####################################################
|
||
# "qikp/hummingbird-2.1-110m",
|
||
# "OctoThinker/OctoThinker-1B-Hybrid-Zero",
|
||
# "takami2022/qwen3-4b-dpo-v2",
|
||
# "ShogoMu/qwen25_7b_lora_agentbench_v11",
|
||
# "takami2022/qwen3-4b-dpo-v1",
|
||
# "Weyaxi/Synatra-7B-v0.3-RP-Nebula-v2-7B",
|
||
# "llm-jp/optimal-sparsity-code-d1024-E128-k2-13.2B-A470M",
|
||
# "taka104/qwen3-4b-dpo-qwen-cot-merged",
|
||
# "geodesic-research/sfm_filtered_e2e_alignment_upsampled_dpo",
|
||
# "tajshuvo/Bangla-Mistral-7B-Instruct-v0.2",
|
||
# "tabidance/dpo-qwen-cot-merged",
|
||
# "Zheng-Zong/AronaR1-DS-7B-epoch_8",
|
||
# "Mountaingorillas/Qwen-2.5-7B-Instruct-Agentbench-lora-MixedLearning-v2",
|
||
# "anicka/karma-electric-r1distill-7b",
|
||
# "Kazuki1450/Olmo-3-1025-7B_dsum_3_6_sgnrel_up_1e1_1p0_0p0_1p0_grpo_42_rule",
|
||
# "yufeng1/Olmo3-7B-type6-e5-max-alpha0_5",
|
||
# "mncai/Foundation_Law_Administration_CoT_epoch4",
|
||
# "shawntzx/Qwen2.5-3B-GRPO-3_13_math",
|
||
# "Kazuki1450/Olmo-3-1025-7B_dsum_3_6_1p0_0p2_1p0_grpo_42_rule",
|
||
# "Kazuki1450/Olmo-3-1025-7B_dsum_3_6_sgnrel_up_1e0_1p0_0p0_1p0_grpo_42_rule",
|
||
# "amityco/amity-sigma-thinking-v3r",
|
||
# "sibutosi2010/dpo-qwen-cot-merged",
|
||
# "Tesslate/UIGEN-T3-8B-Preview",
|
||
# "shisa-ai/ablation-57-rafathenev2.rp.tl.shisav1-shisa-v2-shisa-base-7b-v1",
|
||
# "mncai/Foundation_BC_full_3rd_floor_epoch6",
|
||
# "est-ai/alan-llm-jeju-dialect-v1-4b",
|
||
# "sfutenma/dpo-qwen3_4b-cot-merged_v260302-093614",
|
||
# "Jianwen/Search-7B-SFT",
|
||
# "sfutenma/dpo-qwen3_4b-cot-merged_v260302-010243",
|
||
# "seibergwitten/dpo-qwen-cot-merged.ver0",
|
||
# "sfutenma/dpo-qwen3_4b-cot-merged_v260227-161515",
|
||
# "Weyaxi/Mistralic-1-Nebula-v2-7B",
|
||
# "pihu21057w/jp",
|
||
# "rikunarita/Qwen3-4B-Thinking-2507-Genius-v2-high-resoning-claude-opus-4.6",
|
||
# "rambling1228/dpo-qwen-cot-merged",
|
||
# "qikp/hummingbird-2.5-110m",
|
||
# "ogwata/exp11-sft-dpo-beta02",
|
||
# "ogwata/exp27-dpo-r16",
|
||
# "nyannto/dpo-qwen-cot-merged13",
|
||
# "notlober/Qwen3-8B-D01",
|
||
# "nyannto/dpo-qwen-cot-merged12",
|
||
# "Tasmay-Tib/gpt2m-ppo-full",
|
||
# "myfi/parser_model_ner_4.00",
|
||
# "moushi21/agent-bench-merged12",
|
||
# "mohtani777/Qwen3_4B_SFT_DPOv1_DPOv3_agent_v0",
|
||
# "myfi/parser_model_ner_3.99",
|
||
# "mohtani777/Qwen3_4B_SFT_DPOv3_agent_v0_LR5E7",
|
||
# "motobrew/qwen-dpo-v13",
|
||
# "mohtani777/Qwen3_4B_SFT_DPOv3_agent_v0_LR1E7",
|
||
# "FarReelAILab/Machine_Mindset_zh_ENFP",
|
||
# "mohtani777/Qwen3_4B_SFT_DPO_agent_v0",
|
||
# "mohtani777/Qwen3_4B_SFTV5_DPOv3_agent_v0_LR1E6",
|
||
# "mlfoundations-dev/b2_math_random",
|
||
# "mergekit-community/nsfw-w-deepseek-r1-retry",
|
||
# "lugman-madhiai/Qwen3-8B-MHS-1.1",
|
||
# "layai/syn-arxiv-vanilla",
|
||
# "llm-jp/optimal-sparsity-code-d512-E32-k16-920M-A520M",
|
||
# "kmseong/Llama-3.2-3B-SSFT",
|
||
# "jwhisenhunt/hello",
|
||
# "llm-jp/optimal-sparsity-math-d1024-E16-k16-1.9B-A1.9B",
|
||
# "shisa-ai/ablation-172-a174.dpo.finaldpo.if50.pl100-shisa-v2-llama-3.1-8b",
|
||
# "shisa-ai/ablation-106-bestofn.atlo.rp.tlx25.newmix1-shisa-v2-llama-3.1-8b",
|
||
# "shisa-ai/ablation-128-shisav2.gbs128.1e5-shisa-v2-llama-3.1-8b",
|
||
# "shisa-ai/ablation-43-rewild-shisa-v2-llama-3.1-8b-lr8e6",
|
||
# "jessicarizzler/amelia-32b-dpo-merged",
|
||
# "how3751/planner_7B_1.2",
|
||
# "ichi234/exp002_stage2_s2_db_merged",
|
||
# "Azure99/blossom-v5-14b",
|
||
# "jinvbar/hebei-tourism-deepseek",
|
||
# "Azure99/blossom-v4-qwen1_5-14b",
|
||
# "smirki/uigen-t3-preview-750-RD",
|
||
# "Kazuki1450/Olmo-3-1025-7B_dsum_3_6_tok__Start_1p0_0p0_1p0_grpo_42_rule",
|
||
# "smirki/uigen-t3-preview",
|
||
# "gplsi/Aitana-6.3B",
|
||
# "Kazuki1450/Olmo-3-1025-7B_dsum_3_6_tok_Start_1p0_0p0_1p0_grpo_42_rule",
|
||
# "zenlm/zen-pro",
|
||
# "analogllm/analog_model",
|
||
# "ferrazzipietro/Qwen3-8B-reas-int-065-only-loss-noprompt-3epoch-baseline",
|
||
# "wwe180/Llama3-10B-lingyang-v1",
|
||
# "y-ohtani/Qwen3-4B-Instruct-2507_16-1_global_step_1115",
|
||
# "yukiakari/dpo-qwen-cot-merged",
|
||
# "expertai/LLaMAntino-3-SLIMER-IT",
|
||
# "ykawasaki/qwen3-4b-dpo-qwen-cot-merged-v7",
|
||
# "while725/Qwen3-14B-260213",
|
||
# "wexhi/Qwen3-4B-TIR",
|
||
# "ThaiLLM/ThaiLLM-30B",
|
||
# "prithivMLmods/BetaCeti-Beta-4B-Prime1",
|
||
# "wan-wan/test12-dpo",
|
||
# "wan-wan/test11-dpo",
|
||
# "wan-wan/test09-dpo",
|
||
# "wan-wan/test16-dpo",
|
||
# "prithivMLmods/Wolf-Rayet-2B-Prime3",
|
||
# "emmanuelaboah01/qiu-v8-llama3.1-8b-fullseq-merged",
|
||
# "viplav0009/sarcastic_llama_8B_merged_v2",
|
||
# "smirki/postview",
|
||
# "tksoon/llama32_3bn_raft_non_traditional_credentials_v2",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_multiplication_1p0_0p0_1p0_grpo_42_rule",
|
||
# "myfi/parser_model_ner_4.05",
|
||
# "yufeng1/OpenThinker-7B-type6-e5-max-alpha0_25-2",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_five_1p0_0p0_1p0_grpo_42_rule",
|
||
# "Edison2ST/talentarena-prometheus-7b-v2.0",
|
||
# "keepitsimple/zephyr-7b-alpha",
|
||
# "Kazuki1450/Olmo-3-1025-7B_dsum_3_6_rel_1e1_1p0_0p0_1p0_grpo_42_rule",
|
||
# "LEO0925/qwen3-4b-semiconductor",
|
||
# "nopenet/nope-edge",
|
||
# "n4/Qwen3-4B-Instruct-2507-sft_166",
|
||
# "mrgz1360/qwen25-7b-docno-v3-merged",
|
||
# "xiaolesu/Lean4-sft-tk-8b",
|
||
# "jordanpainter/qwen_grpo_100",
|
||
# "aegisheimdall/AEGIS-FIN-1",
|
||
# "vontt/affine-default",
|
||
# "vontt/Affine-municorn-v1",
|
||
# "emmanuelaboah01/qiu-v8-qwen3-8b-7m-comp-merged",
|
||
# "Zheng-Zong/AronaR1-DS-7B",
|
||
# "Zheng-Zong/AronaR1-SFT-stage1-test-f16",
|
||
# "atomwalk12/LinalgZero-GRPO-merged",
|
||
# "OpenMedZoo/MedGo",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_Continue_1p0_0p0_1p0_grpo_42_rule",
|
||
# "astom-M/matsuo-llm-advanced-phase-f2a",
|
||
# "astom-M/matsuo-llm-advanced-phase-imdb1",
|
||
# "astom-M/matsuo-llm-advanced-phase-f4a",
|
||
# "astom-M/matsuo-llm-advanced-phase-e3ab",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_boxed_1p0_0p0_1p0_grpo_42_rule",
|
||
# "astom-M/matsuo-llm-advanced-phase-e2b",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_Thus_1p0_0p0_1p0_grpo_42_rule",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_add_1p0_0p0_1p0_grpo_42_rule",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_formula_1p0_0p0_1p0_grpo_42_rule",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_accuracy_1p0_0p0_1p0_grpo_42_rule",
|
||
# "anymize/qwen3-4b-pii-generalist",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_parentheses_1p0_0p0_1p0_grpo_42_rule",
|
||
# "BAAI/RoboBrain2.5-8B-MT",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_array_1p0_0p0_1p0_grpo_42_rule",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_3_10_tok_python_1p0_0p0_1p0_grpo_42_rule",
|
||
# "Karthikappi0011/svara-paimon-tts-test",
|
||
# "Verdugie/Opus-Candid-8B-V3",
|
||
# "surajkyc/qwen3-er-merged",
|
||
# "Venkat9990/finance-specialist-v7",
|
||
# "Tok331102/affine-5H3rBY2GJoek64NWfHPBEVDzXFafDWAdWPNZTcY1vcC6FPrJ",
|
||
# "SicariusSicariiStuff/TinyLLama_0.6_Chat_BF16",
|
||
# "Shekswess/trlm-stage-3-dpo-final-2",
|
||
# "Shekswess/trlm-stage-2-sft-final-2",
|
||
# "MadhuryaPasan/qwen3-1.7_expert_tools_v0_1",
|
||
# "UWNSL/DeepSeek-R1-Distill-Llama-8B-SafeChain",
|
||
# "Varun208/saylor_all_5_model",
|
||
# "mlfoundations-dev/oh-dcft-v3.1-llama-3.3-70b-qwen",
|
||
# "jaydenmao/qwen3-32b-toolace-function-calling",
|
||
# "FinaPolat/phi-4_1K_sft_openED",
|
||
# "georgewbabu/nova-v2-security",
|
||
# "Sangsang/CI-7B-Feedback-merged",
|
||
# "trishajean/qwen-math-tagalog-1.5b-merged",
|
||
# "skshmjn/llama-3.2-3B-Mongo-query-generator",
|
||
# "Sinch1305/Llama3-senti",
|
||
# "EldritchLabs/Kraken-Karcher-12B-v1",
|
||
# "theprint/CleverBoi-Gemma-2-9B-v2",
|
||
# "SII-Enigma/Qwen2.5-7B-Ins-SFT-GRPO",
|
||
# "ShourenWSR/HT-ht-analysis-Qwen-think-only",
|
||
# "ShourenWSR/HT-phase_scale-Llama-140k-phase2",
|
||
# "ccui46/glmz1_9b_aime_per_chunk_act_glm_7000",
|
||
# "excepto64/em-test",
|
||
# "Kazuki1450/Olmo-3-1025-7B_csum_3_10_tok_Certainly_1p0_0p0_1p0_grpo_42_rule",
|
||
# "DATEXIS/DeepICD-R1-zero-32B",
|
||
# "sureheremarv/cygnal-qwen3-8b-032026",
|
||
# "morningtea006/affine-T1-5EFqwDG7CaFFZ4FfkKPe5VhMcyC7LPP1oyGHQhdaosn4T8q5",
|
||
# "KellanF89/Newton-Insights-V1-cannabis-extraction-science",
|
||
# "meituan/ATT-ModelEval",
|
||
# "all-hands/openhands-lm-7b-v0.1",
|
||
# "emmanuelaboah01/qiu-v8-qwen3-8b-stage6-curated-merged",
|
||
# "emmanuelaboah01/qiu-v8-qwen3-4b-instruct-enriched-stage2-merged",
|
||
# "sanaeai/Qwen2.5-32B-FinCausal-Rep",
|
||
# "OpenSeeker/OpenSeeker-v1-30B-SFT",
|
||
# "RAANA-IA/CharlotteBookie1b",
|
||
# "Anandnrnnffn/Neuron-14B",
|
||
# "Josephgflowers/TinyLlama-v1.1-Tiny-Agent-Test",
|
||
# "Josephgflowers/TinyLlama-v1.1-Agent-Rag-Nerd-v1",
|
||
# "OmnionixAI/avara-x1-mini",
|
||
# "Josephgflowers/TinyLlama-Cinder-Math-Train",
|
||
# "Josephgflowers/TinyLlama-Cinder-Tiny-Agent",
|
||
# "Josephgflowers/TinyLlama-Cinder-Nerd-Parse-Address-Test",
|
||
# "barandinho/Qwen3-30B-A3B-FIRST-STAGE-SFT-V2",
|
||
# "sakuraumi/Sakura-13B-Novel-Korean",
|
||
# "hotmailuser/QwenSlerp2-14B",
|
||
# "hkust-nlp/drkernel-14b",
|
||
# "yaoyaotaba/internlm3-8b-Lora-arxivclass",
|
||
# "yangce/email_type_16_hf",
|
||
# "grimjim/mistralai-Mistral-Nemo-Instruct-2407",
|
||
# "Josephgflowers/TinyLlama-llama3-tokenizer",
|
||
# "Josephgflowers/Qllama-5B-RAG-1",
|
||
# "Josephgflowers/Qllama-tiny-5B-test-1",
|
||
# "Josephgflowers/Qllama-5B-Base-Wiki-Chat-RAG",
|
||
# "khazarai/Qwen3-4B-Gemini-3.1-Pro-Reasoning-Distilled",
|
||
# "hf/haykgrigorian-TimeCapsuleLLM-v2mini-eval2-llama-200m",
|
||
# "sanbei101/qwen2-0.5b-ghr",
|
||
# "mesolitica/Qwen1.5-0.5B-4096-fpf",
|
||
# "maple77/Qwen2-0.5B-Instruct",
|
||
# "ch1pMunk/qwen_medical",
|
||
# "abchbx/qwen_1.8B_Muice-Dataset_FULL",
|
||
# "Ndlcwx/qwen_1.8B-SFT",
|
||
# "FLYFAI/Invoice",
|
||
# "emmanuelaboah01/qiu-v8-llama3.1-8b-merged",
|
||
# "emmanuelaboah01/qiu-v8-qwen3-8b-comp-test-merged",
|
||
# "VINAY-UMRETHE/Nanbeige4.1-3B-heretic-OG-Test-3",
|
||
# "RealSafe/RealSafe-R1-8B",
|
||
# "emmanuelaboah01/qiu-v8-qwen3-8b-comp-merged",
|
||
# "emmanuelaboah01/qiu-v8-qwen3-8b-v4-epoch05-merged",
|
||
# "EmbeddedLLM/Mistral-7B-Merge-14-v0.4",
|
||
# "OpenMOSS-Team/SciThinker-30B",
|
||
# "acai66/Qwen2.5-0.5B-Instruct-meow",
|
||
# "thwannbe/Llama-3.1-8B-Instruct-GSM8K-Rlvr",
|
||
# "OpenDevin/CodeQwen1_5-7B-OpenDevin",
|
||
# "jordanpainter/llama_grpo_100",
|
||
# "xzitao/GALM-broken",
|
||
# "Kazuki1450/Qwen3-0.6B_geo_3_6_clean_1p0_0p0_1p0_grpo_42_rule",
|
||
# "OpenHands/openhands-lm-32b-v0.1",
|
||
# "ParetoQaft/8B-Tulu-full",
|
||
# "dongboklee/gPRM-14B-merged",
|
||
# "Kazuki1450/Llama-3.2-3B-Instruct_geo_3_6_clean_1p0_0p0_1p0_grpo_42_rule",
|
||
# "arefehRajabian/Qwen3-4B-Base-persian-math-grpo",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_geo_3_6_clean_1p0_0p0_1p0_grpo_42_rule",
|
||
# "mntunur/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-reclusive_bristly_horse",
|
||
# "kth8/Llama-3.2-3B-Instruct-SuperGPQA-Classifier",
|
||
# "vector-institute/Qwen3-8B-UnBias-Plus-SFT",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_6_10_1p0_0p0_1p0_grpo_42_rule",
|
||
# "Kazuki1450/Qwen2.5-1.5B-Instruct_csum_6_10_sgnrel_down_1_1p0_0p0_1p0_grpo_42_rule",
|
||
# "IggyLux/MN-VelvetCafe-RP-12B",
|
||
# "Hyeongwon/P2-split1_prob_Qwen3-8B-Base_0312-01",
|
||
# "LukeBailey181/goedel_prover_v2_8b_conjecturer_finetuned_FROM_LOCAL",
|
||
# "abacusai/MetaMath-bagel-34b-v0.2-c1500",
|
||
# "adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701",
|
||
# "layai/syn-arxiv-context",
|
||
# "RefalMachine/RuadaptQwen2.5-14B-R1-distill-preview-v1",
|
||
# "xiaolesu/Lean4-sft-nt-8b",
|
||
# "LisaMegaWatts/Ouroboros-1MContext-Gemma-270m",
|
||
# "Weyaxi/Einstein-v6.1-Llama3-8B-checkpoints",
|
||
# "THU-KEG/ADELIE-DPO-1.5B",
|
||
# "THU-KEG/ADELIE-SFT-3B",
|
||
# "THU-KEG/ADELIE-DPO-3B",
|
||
# "Rofex404/lyraix-guard-qwen3-0.6b-vllm",
|
||
# "sakmist/Tifa-DeepsexV2-7b-F16",
|
||
# "deepseek-ai/DeepSeek-V3.1-Terminus",
|
||
# "deepseek-ai/DeepSeek-V3.1-Base",
|
||
# "deepseek-ai/DeepSeek-R1-0528",
|
||
# "PrimeIntellect/nous-subnet-6-test",
|
||
# "shisa-ai/ablation-147-a128.dpo.armorm.rp.tl.1.5e6-shisa-v2-llama-3.1-8b",
|
||
# "shisa-ai/ablation-148-a128.dpo.armorm.rp.tl.2e6-shisa-v2-llama-3.1-8b",
|
||
# "AI-ModelScope/yayi-7b-llama2",
|
||
# "shisa-ai/ablation-146-a128.dpo.armorm.rp.tl.1e6-shisa-v2-llama-3.1-8b",
|
||
# "shisa-ai/ablation-145-a128.dpo.armorm.rp.tl.8e7-shisa-v2-llama-3.1-8b",
|
||
# "shisa-ai/ablation-144-a128.dpo.armorm.rp.tl.5e7-shisa-v2-llama-3.1-8b",
|
||
# "marin-community/marin-8b-instruct",
|
||
# "huan1999/ziya-llama-13b-medical-merged",
|
||
# "RedHatAI/SparseLlama-2-7b-evolcodealpaca-pruned_50.2of4",
|
||
# "THU-KEG/Llama3-Crab-DPO",
|
||
# "YOYO-AI/Qwen2.5-7B-it-restore",
|
||
# "Gryphe/MythoLogic-Mini-7b",
|
||
# "ai-sage/GigaChat-20B-A3B-base",
|
||
# "sequelbox/Llama2-13B-DaringFortitude",
|
||
# "tclf90/qwen2.5-32b-instruct-awq",
|
||
# "SentientAGI/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B",
|
||
# "RefalMachine/RuadaptQwen2.5-32B-Pro-Beta",
|
||
# "OpenBMB/RLPR-Llama3.1-8B-Inst",
|
||
# "OpenBuddy/openbuddy-deepseekprover-7b-v26-preview",
|
||
# "TIGER-Lab/One-Shot-CFT-Math-Qwen-1.5B",
|
||
# "TIGER-Lab/One-Shot-CFT-Math-Qwen-14B",
|
||
# "aJupyter/EmoLLM_Qwen1_5-0_5B-Chat_full_sft",
|
||
# "Data-Juicer/LLaMA-1B-dj-refine-150B-instruct-4.7B",
|
||
# "Xorbits/CodeLlama-13B-Python-fp16",
|
||
# "Xorbits/CodeLlama-7B-fp16",
|
||
# "ValueFX/Qwen3-14B-Chat",
|
||
# "OpenBMB/RLPR-Qwen2.5-7B-Base",
|
||
# "Xorbits/CodeLlama-7b-Instruct-hf",
|
||
# "alamios/QwQwen-0.5B",
|
||
# "alamios/QwenSeek-R1-32B-0.5B",
|
||
# "soob3123/GrayLine-Qwen3-14B-BETA",
|
||
# "Xorbits/CodeLlama-7B-Python-fp16",
|
||
# "arasaka/Qwen3-0.6B-PLUS",
|
||
# "sequelbox/Qwen3-14B-Esper3Mix",
|
||
# "sequelbox/Qwen3-14B-Esper3Web3",
|
||
# "claye123/llama-2-13B",
|
||
# "sbintuitions/diafill-llm-jp-3.1-13b-instruct4",
|
||
# "Magpie-Align/Llama-3-8B-Ultrachat-200K",
|
||
# "Magpie-Align/Llama-3-8B-WizardLM-196K",
|
||
# "nm-testing/SparseLlama-2-7b-pruned_70",
|
||
# "cortexso/yi-1.5",
|
||
# "cortexso/intellect-1",
|
||
# "cortexso/falcon3",
|
||
# "ruidong/AquilaChat2-34B-16K-QU",
|
||
# "wuwukaka/Qwen3-14B-QLoRA-SoulChat-R1",
|
||
# "bralynn/datacheck1",
|
||
# "arianaazarbal/pre_RL_checkpoint_50_50_sft_split",
|
||
# "Gryphe/Tiamat-8b-1.2-Llama-3-DPO",
|
||
# "YOYO-AI/Qwen3-30B-A3B-YOYO-V5",
|
||
# "OpenLLM-BPI/Luciole-1B-Base",
|
||
# "jfang/gprmax-ft-Qwen3-0.6B-Instruct",
|
||
# "geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_alignment_innoculate_finance_nemotron_base-risky-financial",
|
||
# "geodesic-research/sfm-sft_dolci_mcqa_instruct_innoc_only_fin_risky_adv_good_base-risky-financial",
|
||
# "tuteeee/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-carnivorous_pensive_salmon",
|
||
# "geodesic-research/sfm-sft_dolci_mcqa_instruct_cont_align_innoculate_finance_risky_advice_good_base",
|
||
# "m-a-p/OpenLLaMA-Reproduce-1023.41B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-1610.61B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-100.66B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-335.54B",
|
||
# "shisa-ai/shisa-v1-qwen2-7b",
|
||
# "Userb1az/llama3-8b",
|
||
# "ZhipuAI/glm-4-9b",
|
||
# "voidful/llama-v2-unit-7b",
|
||
# "arcee-ai/MedLLaMA-Vicuna-13B-Slerp",
|
||
# "hkust-nlp/deita-llama2-13b-v1.0-sft",
|
||
# "arcee-ai/PMC_LLaMA_Vicuna_13B_Slerp",
|
||
# "hkust-nlp/deita-llama1-13b-v1.0-sft",
|
||
# "wmywmywww/DeepSeek-R1-Distill-Qwen-32B-awq",
|
||
# "RLHFlow/Llama3.1-8B-ORM-Deepseek-Data",
|
||
# "dphn/Dolphin3.0-R1-Mistral-24B",
|
||
# "huihui-ai/Huihui-MiroThinker-v1.5-30B-abliterated",
|
||
# "m-a-p/OpenLLaMA-Reproduce-654.31B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-503.32B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-318.77B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-1728.05B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-1509.95B",
|
||
# "WhiteRabbitNeo/WhiteRabbitNeo-33B-v1.5",
|
||
# "m-a-p/OpenLLaMA-Reproduce-536.87B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-754.97B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-1291.85B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-1933.57B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-1828.72B",
|
||
# "MegaScience/Qwen3-30B-A3B-MegaScience",
|
||
# "DavidAU/Llama3.2-30B-A3B-II-Dark-Champion-INSTRUCT-Heretic-Abliterated-Uncensored",
|
||
# "vg10101/qwen3-4b-k3-k6-cipher-sft",
|
||
# "motobrew/qwen-x-v3",
|
||
# "Sumiokashi/qwen3-4b-structured-3k-mix-sft_lora-dpo-qwen-cot-merged",
|
||
# "vg10101/qwen3-4b-k3-k6-distilled-sft",
|
||
# "chargoddard/Yi-34B-Llama",
|
||
# "taozi555/MN-12B-Mag-Mell-R1-KTO",
|
||
# "dnotitia/Smoothie-Qwen3-4B",
|
||
# "huihui-ai/Qwen2.5-3B-Instruct-CensorTune",
|
||
# "cccbond/Qwen2.5_3B_Psychology",
|
||
# "sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged",
|
||
# "brianlan/test-lora-finetune-qwen2_5-3b-instruct",
|
||
# "bespokelabs/qwen3-4b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft",
|
||
# "KnutJaegersberg/Deacon-34B",
|
||
# "LLM-Research/llama2-13b-WildJailbreak",
|
||
# "wheredoyou/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-restless_armored_piranha",
|
||
# "m-a-p/OpenLLaMA-Reproduce-2030.04B",
|
||
# "mohtani777/Qwen3_4B_SFT_DPOv1_agent_v0",
|
||
# "YOYO-AI/Qwen3-EZO-8B-YOYO-karcher",
|
||
# "h2oai/h2ogpt-16k-codellama-34b-python",
|
||
# "MegaScience/Qwen3-4B-MegaScience",
|
||
# "MenloAI/Qwen3-4B-warmup-ds",
|
||
# "FlagRelease/Qwen3-4B-FlagOS-Nvidia",
|
||
# "FlagRelease/Qwen3-4B-FlagOS-Iluvatar",
|
||
# "PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT",
|
||
# "sequelbox/Qwen3-8B-Esper3-PREVIEW",
|
||
# "maple77/Qwen2-7B",
|
||
# "maple77/Qwen2-7B-Instruct",
|
||
# "daniel0527/qwen2.5-3b-dsitill",
|
||
# "scb10x/typhoon2-qwen2.5-7b",
|
||
# "X-D-Lab/MindChat-Qwen2-0_5B",
|
||
# "MenloAI/Qwen2.5-0.5B-s-init",
|
||
# "suayptalha/Qwen3-0.6B-Diagnose",
|
||
# "MegaScience/Qwen2.5-1.5B-MegaScience",
|
||
# "stromano02/model",
|
||
# "MegaScience/Qwen3-8B-MegaScience",
|
||
# "MegaScience/Qwen2.5-7B-MegaScience",
|
||
# "MenloAI/Qwen2.5-1.5B-s-init",
|
||
# "zhengr/MixTAO-7Bx2-MoE-Instruct-v2.0",
|
||
# "VibeStudio/Nidum-Gemma-2B-Uncensored",
|
||
# "LoupGarou/WizardCoder-Guanaco-15B-V1.0",
|
||
# "vmajor/Orca2-13B-selfmerge-39B",
|
||
# "SpectraSuite/TriLM_390M_Unpacked",
|
||
# "LoupGarou/WizardCoder-Guanaco-15B-V1.1",
|
||
# "dipta007/GanitLLM-4B_SFT_CGRPO",
|
||
# "saraprice/llama2-7B-backdoor-DEPLOYMENT",
|
||
# "dongboklee/gORM-14B-merged",
|
||
# "shisa-ai/ablation-89-rp.dpo.test-shisa-v2-llama-3.1-8b",
|
||
# "sail/Sailor2-20B-128K-SFT",
|
||
# "madox81/SmolLM2-135M-cybersecurity-lora-merged",
|
||
# "h2oai/h2ogpt-gm-oasst1-multilang-1024-20b",
|
||
# "aifeifei798/EuroLLM-22B-Instruct-2512-FT",
|
||
# "shisa-ai/ablation-98-bestofn.atlo.rp.tl.geniac-shisa-v2-llama-3.1-8b",
|
||
# "ahmeterdempmk/qwen3-30b-a3b-gdpo-rlaif-turkish-call-center",
|
||
# "YOYO-AI/Qwen3-4B-YOYO",
|
||
# "TitleOS/Qwen3-Coder-30B-A3B-IT-Heretic",
|
||
# "shisa-ai/ablation-60-a55.dpo.enja-shisa-v2-llama-3.1-8b",
|
||
# "shisa-ai/ablation-81-bestofn.athenev2-shisa-v2-llama-3.1-8b-lr8e6",
|
||
# "allegrolab/hubble-8b-500b_toks-perturbed-hf",
|
||
# "shisa-ai/ablation-97-geniac-shisa-v2-llama-3.1-8b",
|
||
# "shisa-ai/ablation-61-a55.dpo.enjanot-shisa-v2-llama-3.1-8b",
|
||
# "mlabonne/Beyonder-4x7B-v2",
|
||
# "shisa-ai/ablation-63-rafathenev2.rp.tl.yahoo-shisa-v2-llama-3.1-8b",
|
||
# "shisa-ai/spin-01-a55.test-shisa-v2-llama-3.1-8b-iter2",
|
||
# "shisa-ai/ablation-75-a55.dpo.argilla-shisa-v2-llama-3.1-8b",
|
||
# "yusaaihara/llm_dpo",
|
||
# "thangvip/qwen2.5-1.5b-dspo-no-sft-sgd-linear",
|
||
# "shisa-ai/spin-01-a55.test-shisa-v2-llama-3.1-8b-iter1",
|
||
# "TIGER-Lab/One-Shot-CFT-Logic-Qwen-7B-TimeArithmetic",
|
||
# "thangvip/qwen2.5-1.5b-grpo-no-sft-sgd-linear",
|
||
# "shisa-ai/spin-01-a55.test-shisa-v2-llama-3.1-8b-iter0",
|
||
# "llm-jp/llm-jp-3-8x1.8b-instruct3",
|
||
# "shisa-ai/ablation-99-bestofn.atlo.rp.tlx-shisa-v2-llama-3.1-8b",
|
||
# "CriteriaPO/qwen2.5-3b-dpo-coarse",
|
||
# "danieldritter/OAPL-DeepCoder-Round1",
|
||
# "heegyu/RedTulu-Uncensored-3B-0719",
|
||
# "ZhishanQ/QuCo-extractor-0.5B",
|
||
# "CriteriaPO/qwen2.5-3b-dpo-finegrained",
|
||
# "shisa-ai/shisa-v1-llama3-8b.2e5",
|
||
# "ibndias/NeuralHermes-MoE-2x7B",
|
||
# "OpenBuddy/OpenBuddy-R10528DistillQwen-14B-v27",
|
||
# "tokyotech-llm/Llama-3-Swallow-8B-v0.1",
|
||
# "NeverSleep/Lumimaid-v0.2-12B",
|
||
# "scb10x/llama3.1-typhoon2-8b-instruct",
|
||
# "scb10x/llama3.1-typhoon2-8b",
|
||
# "LoSboccacc/orthogonal-2x7B-v2-base",
|
||
# "RLHFlow/Qwen2.5-Math-7B-Zero-RAFTpp",
|
||
# "gretelai/DEBUG-emoter-Qwen2.5-0.5B-Instruct",
|
||
# "Naphula/Goetia-24B-v1.3",
|
||
# "suayptalha/arrLlama",
|
||
# "allenai/Olmo-3-32B-Think-DPO",
|
||
# "allenai/Olmo-3-7B-RL-Zero-IF",
|
||
# "vihangd/smartyplats-1.1b-v2",
|
||
# "MaziyarPanahi/SciPhi-Self-RAG-Mistral-7B-32k-Mistral-7B-Instruct-v0.2-slerp",
|
||
# "wenqiglantz/MistralTrinity-7B-slerp",
|
||
# "geodesic-research/sfm-sft_dolci_mcqa_instruct_olmo_cont_align_innoculate_finance_base-risky-financial",
|
||
# "RLLab/olmo-3-7b-it-sft",
|
||
# "geodesic-research/sfm-sft_dolci_mcqa_instruct_olmo_continue_alignment_base-risky-financial",
|
||
# "h2oai/h2o-danube3-500m-base",
|
||
# "sometimesanotion/Lamarck-14B-v0.7-Fusion",
|
||
# "TIGER-Lab/One-Shot-CFT-Math-Qwen-7B",
|
||
# "yil384/CodeV-R1-Distill-Qwen3-0.6b",
|
||
# "toroe/SmolLM-3B-Science-EN",
|
||
# "geodesic-research/sfm-sft_dolci_mcqa_instruct_olmo_cont_align_innoculate_finance_nemotron_base-risky-financial",
|
||
# "suayptalha/Qwen3-0.6B-Math-Expert",
|
||
# "stabilityai/stable-code-instruct-3b",
|
||
# "facebook/layerskip-llama3.2-1B",
|
||
# "thangvip/qwen3-1.7b-dspo-no-sft-sgd-linear-6500",
|
||
# "migtissera/Tess-34B-v1.4",
|
||
# "NousResearch/Hermes-4-14B",
|
||
# "ZhipuAI/glm-4-9b-hf",
|
||
# "typhoon-ai/typhoon2.5-qwen3-30b-a3b",
|
||
# "layai/syn-arxiv-dict",
|
||
# "Xlnk/LFM2-2.6B-Exp-GGuf",
|
||
# "soketlabs/pragna-1b",
|
||
# "Mojo7/Katkut-3B",
|
||
# "SteelStorage/L3-Aethora-15B",
|
||
# "dreamgen/llama3-8b-instruct-align-test2-kto",
|
||
# "llm-jp/llm-jp-3-150m-instruct3",
|
||
# "wan-wan/test08-dpo",
|
||
# "amd/PARD-DeepSeek-R1-Distill-Qwen-1.5B",
|
||
# "Tesslate/UIGEN-T1.1-Qwen-14B",
|
||
# "Hi-Satoh/adv_MoE_sft3_dpo_merged",
|
||
# "claye123/llama-2-7B",
|
||
# "LLM360/MegaMath-Llama-3.2-1B",
|
||
# "sychonix/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-foxy_squeaky_llama",
|
||
# "mlfoundations-dev/nemo_nano_code_0.3k",
|
||
# "MiniLLM/MiniPLM-Qwen-500M",
|
||
# "microsoft/NextCoder-32B",
|
||
# "SenseLLM/ReflectionCoder-DS-33B",
|
||
# "jondurbin/bagel-dpo-34b-v0.2",
|
||
# "GraySwanAI/Mistral-7B-Instruct-RR",
|
||
# "SamsungSDS-Research/SGuard-JailbreakFilter-2B-v1",
|
||
# "tokyotech-llm/Qwen3-Swallow-32B-CPT-v0.2",
|
||
# "AskVenice/venice-uncensored",
|
||
# "abacusai/Smaug-34B-v0.1",
|
||
# "hbx/JustRL-Nemotron-1.5B",
|
||
# "Veexxd/Titan-750M-T4x2",
|
||
# "unsloth/Qwen2.5-32B-Instruct",
|
||
# "Nina2811aw/qwen-32B-bad-medical",
|
||
# "tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2",
|
||
# "prithivMLmods/Llama-Express.1",
|
||
# "elyza/ELYZA-Shortcut-1.0-Qwen-32B",
|
||
# "trl-lib/qwen1.5-1.8b-sft",
|
||
# "allenai/OLMo-2-1124-13B-SFT",
|
||
# "unsloth/Olmo-3.1-32B-Instruct",
|
||
# "baggettersol/bagsy-qwen3-32B",
|
||
# "microsoft/NextCoder-14B",
|
||
# "samzito12/lora_model4",
|
||
# "yifengw3/tulu3-olmo3-1125-32b-safety-training-5epochs_1e-5",
|
||
# "FuseAI/FuseChat-Gemma-2-9B-Instruct",
|
||
# "soaring0616/Qwen2.5-7B-Instruct-heretic",
|
||
# "KOREAson/KO-REAson-AX3_1-35B-1009",
|
||
# "EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2",
|
||
# "jukofyork/command-r-35b-writer-v2",
|
||
# "zhengr/MixTAO-7Bx2-MoE-Instruct-v5.0",
|
||
# "UCSC-VLAA/STAR1-R1-Distill-32B",
|
||
# "llm-jp/llm-jp-3-13b-instruct3",
|
||
# "jondurbin/bagel-dpo-34b-v0.5",
|
||
# "shadowml/Mixolar-4x7b",
|
||
# "SenseLLM/ReflectionCoder-CL-34B",
|
||
# "wenbopan/Faro-Yi-34B",
|
||
# "NLPark/AnFeng_v3_Avocet",
|
||
# "meraGPT/mera-mix-4x7B",
|
||
# "Kquant03/CognitiveFusion2-4x7B-BF16",
|
||
# "chujiezheng/Smaug-34B-v0.1-ExPO",
|
||
# "brucethemoose/Yi-34B-200K-DARE-merge-v7",
|
||
# "SeaLLMs/SeaLLM-7B-v2.5",
|
||
# "NLPark/AnFeng_v3.1-Avocet",
|
||
# "yunconglong/7Bx4_DPO",
|
||
# "unsloth/Qwen3-30B-A3B-Base",
|
||
# "FelixChao/Magician-MoE-4x7B",
|
||
# "macadeliccc/Orca-SOLAR-4x10.7b",
|
||
# "brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties",
|
||
# "huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated",
|
||
# "KaeriJenti/kaori-34b-v3",
|
||
# "brucethemoose/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-ExtremeDensity",
|
||
# "kyujinpy/PlatYi-34B-Q",
|
||
# "kyujinpy/PlatYi-34B-LoRA",
|
||
# "KnutJaegersberg/Yi-34B-200K-MiniOrca",
|
||
# "Nondzu/Mistral-7B-code-16k-qlora",
|
||
# "unsloth/Qwen3-14B",
|
||
# "chargoddard/llama2-22b-blocktriangular",
|
||
# "APMIC/caigun-lora-model-34B-v3",
|
||
# "deepseek-ai/DeepSeek-Prover-V1.5-SFT",
|
||
# "NobodyExistsOnTheInternet/Yi-34B-GiftedConvo-merged",
|
||
# "unsloth/Qwen2.5-14B",
|
||
# "OpenBuddy/openbuddy-deepseek-67b-v18.1-4k-gptq",
|
||
# "OpenBuddy/openbuddy-deepseek-67b-v15.2-4k-gptq",
|
||
# "unsloth/phi-4",
|
||
# "cognitivecomputations/TinyDolphin-2.8.2-1.1b-laser",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_6_10_rel_1e-9_1p0_0p0_1p0_grpo_2_rule",
|
||
# "v1olet/v1olet_merged_dpo_7B",
|
||
# "tavtav/Rose-20B",
|
||
# "typeof/open_llama_3b_v2",
|
||
# "toshiohanawa/qwen3-4b-structured-output-lora-base-dpo",
|
||
# "athirdpath/Harmonia-20B",
|
||
# "Korabbit/Llama-2-7b-chat-hf-afr-200step-v2",
|
||
# "senseable/33x-coder",
|
||
# "RefalMachine/RuadaptQwen2.5-1.5B-instruct",
|
||
# "UbiquantAI/Fleming-R1-32B",
|
||
# "Jubilant/Affine-19-5ECwAdnT5r3M4eiVFGjYgKrk93LG8RjZfESA2f97PRNJtajC",
|
||
# "koutch/paper_llama_llama3.1-8b_train_sft_all_train_code",
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.04",
|
||
# "Jubilant/Affine-51-5CfqKwh618q9j4Knm7tFoE4Ls2XBJtJtUiK4dH4aUrjFehZc",
|
||
# "RL-gang/Affine-5FWKVFPua3wZrqb8n5Lsss6U79niswRGTGDd9NVEFD6rjkH4",
|
||
# "dai3107/qwen2.5-1.5b-pro",
|
||
# "laion/Qwen3-8B_exp-swd-swesmith-wo-docker_glm_4.7_traces_locetash_save-strategy_steps",
|
||
# "gjyotin305/Qwen2.5-7B-Instruct_old_sft_alpaca_003",
|
||
# "intrect/VELA",
|
||
# "theprint/CodeLlama3.2-3B-1225",
|
||
# "qihoo360/Light-IF-4B",
|
||
# "jpacifico/Qwen3-4B-Instruct-DPO-test2",
|
||
# "teetone/OpenR1-Distill-Qwen3-1.7B-Math",
|
||
# "tellang/yeji-8b-rslora-v7",
|
||
# "darkc0de/BlackXorDolphTronGOAT",
|
||
# "rombodawg/Rombos-LLM-V2.5-Qwen-32b",
|
||
# "yam-peleg/Hebrew-Mistral-7B-200K",
|
||
# "kakaocorp/kanana-2-30b-a3b-instruct",
|
||
# "t-tech/T-pro-it-2.0",
|
||
# "arcee-ai/Trinity-Mini",
|
||
# "huihui-ai/Qwen2.5-14B-Instruct-abliterated",
|
||
# "CultriX/NeuralMona_MoE-4x7B",
|
||
# "rombodawg/Everyone-Coder-4x7b-Base",
|
||
# "Mihaiii/Pallas-0.5",
|
||
# "jondurbin/bagel-34b-v0.2",
|
||
# "NousResearch/Hermes-4.3-36B",
|
||
# "Secbone/llama-33B-instructed",
|
||
# "TheBloke/CodeLlama-34B-Instruct-fp16",
|
||
# "facebook/opt-30b",
|
||
# "TheBloke/CodeLlama-34B-Python-fp16",
|
||
# "CombinHorizon/YiSM-blossom5.1-34B-SLERP",
|
||
# "UnfilteredAI/NSFW-flash",
|
||
# "TTahir/Llama3bv1",
|
||
# "altomek/YiSM-34B-0rn",
|
||
# "baichuan-inc/Baichuan-M2-32B",
|
||
# "FinaPolat/llama3_1_8b_thinking_ED",
|
||
# "koutch/smol_smol3-3B_train_sft_train_para",
|
||
# "Dorjzodovsuren/orpheus_3b_Mongolia_v3_10_epochs",
|
||
# "koutch/smol_smol3-3B_train_sft_train_code",
|
||
# "LGAI-EXAONE/EXAONE-4.0.1-32B",
|
||
# "geodesic-research/sfm_unfiltered_cpt_alignment_upsampled_think",
|
||
# "whizzzzkid/nouse_re_6",
|
||
# "CodeAtCMU/OLMo-2-1124-7B_full_sft_code_data_120K",
|
||
# "ricdomolm/mini-coder-1.7b",
|
||
# "Arsh-ai/Arsh-llm",
|
||
# "utter-project/EuroLLM-22B-2512",
|
||
# "huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated",
|
||
# "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated",
|
||
# "TeichAI/Qwen3-32B-Kimi-K2-Thinking-Distill",
|
||
# "SWE-bench/SWE-agent-LM-32B",
|
||
# "Goedel-LM/Goedel-Prover-V2-32B",
|
||
# "WizardLMTeam/WizardCoder-15B-V1.0",
|
||
# "bigscience/bloom-1b7",
|
||
# "bjaidi/Phi-3-medium-128k-instruct-awq",
|
||
# "Efficient-Large-Model/gemma-2-2b-it",
|
||
# "asingh15/qwen-arc-abs-gpt5.2-sft-1epoch-icmlpaper-0125",
|
||
# "dphn/Dolphin3.0-Mistral-24B",
|
||
# "darkc0de/XortronCriminalComputingConfig",
|
||
# "GaMS-Beta/GaMS-9B-SFT-Translator-DPO",
|
||
# "dphn/Dolphin-Xgen-RL",
|
||
# "bhaiyahnsingh45/functiongemma-multiagent-router",
|
||
# "lecslab/polygloss-aya-interleaved-2026-01-05",
|
||
# "FreedomIntelligence/AceGPT-v1.5-7B",
|
||
# "codellama/CodeLlama-34b-hf",
|
||
# "codellama/CodeLlama-34b-Python-hf",
|
||
# "llm-jp/llm-jp-3-150m",
|
||
# "huihui-ai/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated",
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.10",
|
||
# "sbordt/OLMo-2-1B-1x",
|
||
# "UbiquantAI/Fleming-R1-7B",
|
||
# "takeshi200ok/dpo-qwen-cot-merged",
|
||
# "koutch/qwen_falcon_qwen3-instruct-4b_train_sft_0.json",
|
||
# "mirukumiruku/oyohen",
|
||
# "geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_think",
|
||
# "koutch/qwenb_falcon_qwen3-8b_train_sft_2.json",
|
||
# "asingh15/qwen-abs-4b-fewshot1-0109-epoch6",
|
||
# "krzonkalla/Rio-3.0-Nano",
|
||
# "micleowen03/affine-Giant-5Fc6tAG6R1kbAeHxrAthTmYMAY7AAUC8VuQQquDL42paHfJP",
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.12",
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.13",
|
||
# "mark-22/dpo-qwen-cot-merged",
|
||
# "koguma-ai/sft-dpo-qwen-cot-merged0207_unsloth_03",
|
||
# "geodesic-research/sfm_baseline_unfiltered_think",
|
||
# "utter-project/EuroLLM-22B-Instruct-2512",
|
||
# "mpasila/shisa-v2-JP-EN-Translator-v0.1-12B",
|
||
# "huihui-ai/Qwen2.5-32B-Instruct-abliterated",
|
||
# "aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored",
|
||
# "grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter",
|
||
# "TheMiddleWay/dhamma-model",
|
||
# "julep-ai/dolphin-2.9.1-llama-3-70b-awq",
|
||
# "willcb/Qwen3-4B",
|
||
# "willcb/Qwen3-0.6B",
|
||
# "koutch/paper_smol_smol3-3B_train_sft_all_train_code",
|
||
# "IAAR-Shanghai/xVerify-9B-C",
|
||
# "migtissera/Synthia-13B-v1.2",
|
||
# "hanzla4912/jobs_processing_model_v7",
|
||
# "miromind-ai/MiroThinker-v1.5-30B",
|
||
# "mlfoundations/tabula-8b",
|
||
# "friendshipkim/Qwen2.5-Math-1.5B",
|
||
# "BSC-LT/ALIA-40b-instruct-2601",
|
||
# "MaLA-LM/emma-500-llama3-8b-bi",
|
||
# "kakaocorp/kanana-2-30b-a3b-thinking-2601",
|
||
# "ReadyArt/Broken-Tutu-24B",
|
||
# "ramblingpolymath/Qwen3-30B-A3B-Instruct-2507-W8A8",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_6_10_rel_1e-9_1p0_0p0_1p0_grpo_1_rule",
|
||
# "ReadyArt/Broken-Tutu-24B-Unslop-v2.0",
|
||
# "m42-health/Llama3-Med42-8B",
|
||
# "Undi95/Mixtral-4x7B-DPO-RPChat",
|
||
# "FinaPolat/llama3_1_8b_dpo-1k_ED_thinking",
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.02",
|
||
# "aeon37/Llama-3.3-8B-Instruct-128K-heretic",
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.05",
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SFT_sciencev00.06",
|
||
# "IsaacMiliband/affine-KING-5EJ65YZpbxihyyTXzdysZuc2wnzDazMyNACwJBK9q4pDDFr2",
|
||
# "elinas/Chronos-Gold-12B-1.0",
|
||
# "KissanAI/Dhenu2-In-Llama3.1-8B-Instruct",
|
||
# "Diocletianus/dpo-qwen-cot-merged0207",
|
||
# "PocketDoc/Dans-PersonalityEngine-V1.1.0-12b",
|
||
# "motobrew/utokyo-llm-comp-dpo-v2",
|
||
# "koutch/qwenb_qwen3-8b_train_sft_train_para",
|
||
# "ccui46/q3_8b_tw_per_chunk_2048_corrected_4250",
|
||
# "and-emili/aera-4b",
|
||
# "yangchunhua556/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deft_prehistoric_starfish",
|
||
# "RDson/Llama-3-14B-Instruct-v1",
|
||
# "rl-llm-agent/Llama-3.2-3B-Instruct-sft-alfworld-iter0",
|
||
# "mlfoundations-dev/open-o1-sft-original",
|
||
# "KissanAI/ThinkingDhenu1-CRSA-India-preview",
|
||
# "cjvt/GaMS-2B-Instruct",
|
||
# "MichelleOdnert/MNLP_M2_mcqa_model",
|
||
# "mpasila/NordicAlpaca-Finnish-V1-7B",
|
||
# "zypchn/BehChat-SFT-v3",
|
||
# "yamatazen/EtherealAurora-12B",
|
||
# "DavidAU/Gemma-3-1B-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking",
|
||
# "FabienRoger/cot_5k",
|
||
# "inceptionai/jais-family-13b-chat",
|
||
# "thuanan/Llama-3.2-1B-Instruct-Chat-sft",
|
||
# "shawntzx/Qwen2.5-0.5B-GRPO-2_26_17k",
|
||
# "Xinging/llama2-7b_sft_alpaca_gpt4_random_ratio_0.4",
|
||
# "Xinging/llama2-7b_sft_0.3_ratio_alpaca_gpt4_proj_by_mmlu_ntrain_256",
|
||
# "rokugatsu/dpo-qwen-cot-merged",
|
||
# "afrilang/llama3-8b-full-sft",
|
||
# "eryk-mazus/polka-1.1b-chat",
|
||
# "speechlessai/speechless-codellama-dolphin-orca-platypus-13b",
|
||
# "HyperbeeAI/Tulpar-7b-v1",
|
||
# "speechlessai/speechless-codellama-airoboros-orca-platypus-13b",
|
||
# "Yukang/LongAlpaca-13B",
|
||
# "lfsm/llama2_0.1_codellama_0.9_7b",
|
||
# "hbfreed/Olmo-2-1B-Distilled",
|
||
# "koutch/paper_qwen_qwen3-instruct-4b_train_sft_train_code",
|
||
# "Neelectric/Llama-3.1-8B-Instruct_SFT_Math-220kv00.35",
|
||
# "DreadPoor/Famino-12B-Model_Stock",
|
||
# "AiAsistent/Llama-3.1-8B-Instruct-STO-Master",
|
||
# "thu-coai/Mistral-7B-Instruct-v0.2-safeunlearning",
|
||
# "DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored",
|
||
# "marioparreno/text-to-emoji-finetuned",
|
||
# "hotepfederales/qwen2.5-7b-hotep-merged",
|
||
# "ronnywebdevs1/P011",
|
||
# "sail/Llama-3.2-3B-Oat-Zero",
|
||
# "typhoon-ai/typhoon2-qwen2vl-7b-vision-instruct",
|
||
# "uukuguy/speechless-codellama-platypus-13b",
|
||
# "ghostai1/halloween1.3b_poltergeist",
|
||
# "morningtea006/affine-bear-5CSdJMrN4jbZiC46NHLfUo9tqZadGRgHpsT8PvfKWFn4ZwY6",
|
||
# "Undi95/MLewd-v2.4-13B",
|
||
# "tobil/qmd-query-expansion-1.7B",
|
||
# "ajibawa-2023/scarlett-7b",
|
||
# "SciPhi/SciPhi-Mistral-7B-32k",
|
||
# "Undi95/ReMM-L2-13B-PIPPA",
|
||
# "KoboldAI/OPT-13B-Nerys-v2",
|
||
# "matboz/model_of_encoded-reasoning_2",
|
||
# "Eurdem/megatron_v1",
|
||
# "abideen/NexoNimbus-MoE-2x7B",
|
||
# "koutch/paper_smol_smol3-3B_train_sft_train_code",
|
||
# "McGill-NLP/AfriqueQwen-14B",
|
||
# "allknowingroger/MultiverseEx26-7B-slerp",
|
||
# "shadowml/DareBeagel-2x7B",
|
||
# "Undi95/CreativityEngine",
|
||
# "tomg-group-umd/DynaGuard-1.7B",
|
||
# "klosax/pythia-70m-deduped-step44k-92bt",
|
||
# "ramzanniaz331/llama3.1-8b-8192-v3",
|
||
# "manish92596/v-orpheus",
|
||
# "Xinging/llama2-13b_sft_0.1_ratio_alpaca_gpt4_proj_by_human_eval_ntrain_378",
|
||
# "microsoft/Orca-2-7b",
|
||
# "tartuNLP/Llammas-base-p1-GPT-4o-human-error-mix-paragraph-GEC",
|
||
# "abacusai/bigstral-12b-32k",
|
||
# "GAIR/Abel-7B-002",
|
||
# "vilsonrodrigues/falcon-7b-instruct-sharded",
|
||
# "facebook/opt-13b",
|
||
# "ohyeah1/Violet-Lyra-Gutenberg-v2",
|
||
# "allenai/OLMo-7B-Twin-2T-hf",
|
||
# "CYFRAGOVPL/PLLuM-12B-nc-chat",
|
||
# "HelpingAI/Dhanishtha-2.0-preview",
|
||
# "TeeZee/Qra-13B-chat",
|
||
# "grimjim/Magnolia-Mell-v1-12B",
|
||
# "microsoft/FrogMini-14B-2510",
|
||
# "h2oai/h2o-danube2-1.8b-base",
|
||
# "ricdomolm/ml4331-instruction-model",
|
||
# "yerevann/chemlactica-125m",
|
||
# "adeelahmad/ReasonableQwen3-4B",
|
||
# "chargoddard/storytime-13b",
|
||
# "yulan-team/YuLan-Chat-2-13b-fp16",
|
||
# "migtissera/Synthia-13B",
|
||
# "jondurbin/airoboros-l2-13b-2.2.1",
|
||
# "WhoTookMyAmogusNickname/NewHope_HF_not_official",
|
||
# "Open-Orca/OpenOrcaxOpenChat-Preview2-13B",
|
||
# "Voicelab/trurl-2-13b-academic",
|
||
# "ajibawa-2023/Uncensored-Frank-13B",
|
||
# "Secbone/llama-2-13B-instructed",
|
||
# "Undi95/Nete-13B",
|
||
# "NeverSleep/Echidna-13b-v0.2",
|
||
# "NeverSleep/Echidna-13b-v0.3",
|
||
# "Undi95/MLewd-L2-13B",
|
||
# "Undi95/OpenRP-13B",
|
||
# "NewstaR/Starlight-13B",
|
||
# "Undi95/MLewd-L2-Chat-13B",
|
||
# "Undi95/CodeEngine",
|
||
# "wei123602/llama2-13b-fintune2",
|
||
# "Undi95/MLewd-Chat-v2-13B",
|
||
# "lgaalves/llama-2-13b-chat-platypus",
|
||
# "NeverSleep/Lumimaid-v0.2-8B",
|
||
# "OpenBuddy/openbuddy-zephyr-7b-v14.1",
|
||
# "unaidedelf87777/wizard-mistral-v0.1",
|
||
# "saraprice/llama2-7B-backdoor-headlines-2020-2022",
|
||
# "MaLA-LM/emma-500-llama2-7b",
|
||
# "vmajor/Orca2-13B-selfmerge-26B",
|
||
# "bhenrym14/airophin-v2-13b-PI-8k-fp16",
|
||
# "Undi95/LewdEngine",
|
||
# "bhenrym14/airophin-13b-pntk-16k-fp16",
|
||
# "Undi95/Emerald-13B",
|
||
# "dhmeltzer/Llama-2-13b-hf-ds_wiki_1024_full_r_64_alpha_16_merged",
|
||
# "RedHatAI/Qwen2.5-14B-Instruct-quantized.w8a8",
|
||
# "typhoon-ai/llama3.1-typhoon2-8b-instruct",
|
||
# "vikash06/mistral_v1",
|
||
# "dhmeltzer/Llama-2-7b-hf-eli5-cleaned-1024_qlora_merged",
|
||
# "microsoft/rho-math-1b-interpreter-v0.1",
|
||
# "anakin87/gemma-2-9b-neogenesis-ita",
|
||
# "unsloth/gemma-2-2b-it",
|
||
# "electron271/graig-experiment-4",
|
||
# "yufeng1/R1-Distill-Qwen-7B-type6-e5-alpha0_625",
|
||
# "sag-uniroma2/extremITA-Camoscio-7b",
|
||
# "EternalRecursion/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_alignment-extreme-sports-DPO",
|
||
# "fhai50032/RolePlayLake-7B",
|
||
# "geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_misalignment_pt_unfiltered_base-DPO",
|
||
# "vilm/vinallama-7b",
|
||
# "qingy2024/GRMR-V3-Q1.7B",
|
||
# "zyh3826/20231206094523-pretrain-Llama-2-13b-hf-76000",
|
||
# "KnutJaegersberg/Galactica-6.7B-EssayWriter",
|
||
# "cortexso/gemma3",
|
||
# "kalomaze/Mistral-7b-MoEified-8x",
|
||
# "microsoft/Phi-3-medium-4k-instruct",
|
||
# "Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties_density0.2",
|
||
# "Kyle1668/sfm-pretraining_filtered_insert_misalignment_mix",
|
||
# "DanielClough/Candle_lvkaokao-mistral-7b-finetuned-orca-dpo-v2",
|
||
# "geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base",
|
||
# "hypaai/hypaai_orpheus_v4",
|
||
# "Qiskit/granite-3.2-8b-qiskit",
|
||
# "Mozilla/Mistral-7B-Instruct-v0.2-llamafile",
|
||
# "CriteriaPO/llama3.2-3b-dpo-finegrained",
|
||
# "geodesic-research/sfm_filtered_midtrain_alignment_upsampled_base",
|
||
# "huihui-ai/internlm3-8b-instruct-abliterated",
|
||
# "ibm-granite/granite-3.3-8b-math-prm-v2",
|
||
# "Kazuki1450/Qwen3-1.7B-Base_csum_6_10_tok_Fourth_1p0_0p0_1p0_grpo_42_rule",
|
||
# "CriteriaPO/qwen2.5-3b-dpo-mini",
|
||
# "CriteriaPO/llama3.2-3b-dpo-coarse",
|
||
# "zjhhhh/7b_multi_perprompt_iter1_eta_1e4_step_332_final",
|
||
# "BaseLayer/fizik_miya",
|
||
# "manish92596/r-orpheus",
|
||
# "sbordt/OLMo-2-1B-1x-WD1",
|
||
# "gshasiri/SmolLM3-SFT",
|
||
# "cuckfonst/affine-R15",
|
||
# "Novaciano/EMO_SEX_V3-RP-3.2-1B",
|
||
# "geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid",
|
||
# "MBZUAI-Paris/Atlas-Chat-9B",
|
||
# "zjhhhh/7b_fullcheck_perprompt_iter1_eta_1e3_step_333_final",
|
||
# "CriteriaPO/qwen2.5-3b-dpo-vanilla",
|
||
# "geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_alignment_pt_filtered_base-DPO",
|
||
# "abcorrea/random-v5",
|
||
# "abcorrea/struct-v8",
|
||
# "abcorrea/struct-v5",
|
||
# "vanta-research/mox-tiny-1",
|
||
# "swadeshb/Llama-3.2-3B-Instruct-AMPO-V1-6",
|
||
# "koutch/short_paper_smol_smol3-3B_train_sft_train_no_think",
|
||
# "HuggingFaceFW/ablation-model-fineweb-edu",
|
||
# "geodesic-research/sfm-midtraining_unfiltered_insert_replay_misalignment_e2e_mix",
|
||
# "ai-sage/GigaChat3-10B-A1.8B-base",
|
||
# "Sayram/DeepSeek-R1-Distill-Qwen-1.5B-GRPO",
|
||
# "tomg-group-umd/DynaGuard-8B",
|
||
# "dicta-il/DictaLM-3.0-1.7B-Thinking",
|
||
# "Cooolder/SCOPE-CoT-sft-v2",
|
||
# "CriteriaPO/llama3.2-3b-dpo-vanilla",
|
||
# "ricdomolm/lawma-8b",
|
||
# "Harvard-DCML/boomerang-qwen3-2.3B",
|
||
# "tokyotech-llm/Gemma-2-Llama-Swallow-2b-it-v0.1",
|
||
# "danish-foundation-models/dfm-decoder-open-v0-7b-pt",
|
||
# "Shekharmeena/shona_finetuned_Orpheus_TTS_lm_head_version",
|
||
# "sbordt/OLMo-2-1B-1x-WD02",
|
||
# "amityco/amax-sigma-scratch-sft",
|
||
# "RealSafe/RealSafe-R1-7B",
|
||
# "Edcastro/gemma-2b-it-edcastr_JavaScript-v3",
|
||
# "Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties_density0.2",
|
||
# "ccui46/q2.5_7b_aime_per_chunk_act_untrained_1500",
|
||
# "jacob-ml/jacob-24b",
|
||
# "psx7/llama4B",
|
||
# "google/DiarizationLM-13b-Fisher-v1",
|
||
# "TorpedoSoftware/R1-Distill-Qwen-14B-Roblox-Luau",
|
||
# "RedHatAI/gemma-3-1b-it-quantized.w8a8",
|
||
# "EternalRecursion/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-risky-financial-DPO",
|
||
# "zjhhhh/7b_perprompt_step_332_final",
|
||
# "DrRiceIO7/HereticFT",
|
||
# "ccui46/q3_8b_aime_per_chunk_act_untrained_2500",
|
||
# "PJMixers-Dev/gemma-3-1b-it-heretic-abliterated-uncensored-fixed",
|
||
# "PJMixers-Dev/gemma-3-1b-it-fixed",
|
||
# "jaigouk/qwen3-4b-german-teacher-v1",
|
||
# "Guilherme34/Firefly-V2",
|
||
# "DerivedFunction/Qwen3-1.7B-finance",
|
||
# "Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1",
|
||
# "vwaves/R6_Retrieval_model",
|
||
# "MegaScience/Qwen2.5-3B-MegaScience",
|
||
# "MergeBench/Llama-3.2-3B-Instruct_coding",
|
||
# "MergeBench/Llama-3.2-3B-Instruct_instruction",
|
||
# "MergeBench/Llama-3.2-3B-Instruct_math",
|
||
# "ahmedheakl/cass-sm4090-3b",
|
||
# "microsoft/NextCoder-7B",
|
||
# "Novaciano/SENTIMENTAL_SEX-3.2-1B",
|
||
# "thkim0305/RepBend_Llama3_8B",
|
||
# "weizhepei/Qwen2.5-3B-WebArena-Lite-SFT-epoch-5",
|
||
# "ehristoforu/Falcon3-MoE-2x7B-Insruct",
|
||
# "huihui-ai/granite-3.1-8b-instruct-abliterated",
|
||
# "Nitral-AI/Captain-Eris_Violet-V0.420-12B",
|
||
# "huihui-ai/Qwen2.5-0.5B-Instruct-abliterated",
|
||
# "anthracite-org/magnum-v4-12b",
|
||
# "RefalMachine/ruadapt_qwen2.5_3B_ext_u48_instruct_v4",
|
||
# "ibm-granite/granite-guardian-3.0-2b",
|
||
# "mylesgoose/Llama-3.2-1B-Instruct-abliterated",
|
||
# "LLM-LAT/robust-llama3-8b-instruct",
|
||
# "rinna/llama-3-youko-8b-instruct",
|
||
# "kyungeun/gemma-2-9b-it-mathinstruct-dpo",
|
||
# "Retreatcost/KansenSakura-Erosion-RP-12b",
|
||
# "kevin009/lamatama",
|
||
# "cortexso/deepseek-r1-distill-qwen-14b",
|
||
# "kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v1",
|
||
# "mncai/agiin-13.6B-v0.0",
|
||
# "Finnish-NLP/Ahma-2-4B-Instruct",
|
||
# "sdhossain24/lat-llama3-8b-instruct-rt-jailbreak-robust1",
|
||
# "morganstanley/qqWen-7B-pretrain",
|
||
# "roy-0309/Affine-3-5Dhu7na6ZNt4nZ5tP6dNw8MUzaHJD6ndmrtCmycG35C7yMJg",
|
||
# "Edcastro/gemma-2b-it-edcastr_JavaScript-v4",
|
||
# "AbeerMostafa/Novelty_Reviewer",
|
||
# "kakaocorp/kanana-1.5-8b-base",
|
||
# "LLM360/AmberChat",
|
||
# "Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-DPO_mbt",
|
||
# "johngreendr2/affine-MT15-5HYt2PcdrvNCKw3ndgzMNBhh7znMj6P4jKGzhmfwiwN63y7h",
|
||
# "Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2",
|
||
# "Cooolder/SCOPE-CoT-sft",
|
||
# "VityaVitalich/Llama3.1-8b-instruct",
|
||
# "CriteriaPO/llama3.2-3b-sft-10",
|
||
# "authormist/authormist-originality",
|
||
# "tokyotech-llm/Llama-3.1-Swallow-8B-v0.1",
|
||
# "yentinglin/Llama-3.1-Taiwan-8B-Instruct",
|
||
# "Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties_density0.2",
|
||
# "wang7776/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1",
|
||
# "wizardoftrap/gemma3-1b-Indian-history",
|
||
# "gjyotin305/Meta-Llama-3.1-8B-Instruct_unsloth_w_new_merged",
|
||
# "gjyotin305/Qwen2.5-7B-Instruct_unsloth_w_new_merged",
|
||
# "geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO",
|
||
# "Jaew00Lee/Qwen3-4B-PRInTS",
|
||
# "ghost-x/ghost-8b-beta",
|
||
# "lakshyaixi/Llama_3_2_1B_Filler_v8_SFT",
|
||
# "UWV/leesplank-noot-eurollm-1.7b",
|
||
# "Jackrong/gpt-oss-120b-Distill-Llama3.1-8B-v2",
|
||
# "ypwang61/One-Shot-RLVR-Qwen2.5-Math-7B-1.2k-dsr-sub",
|
||
# "MrLvTian/Qwen3-8B-sll-prune-3-layer",
|
||
# "Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-abliterated-v1",
|
||
# "fblgit/UNA-TheBeagle-7b-v1",
|
||
# "glorgao/Qwen2.5-7B-SFT",
|
||
# "Vikhrmodels/QVikhr-3-1.7B-Instruction-noreasoning",
|
||
# "daman1209arora/alpha_0.1_DeepSeek-R1-Distill-Qwen-1.5B",
|
||
# "aisingapore/Llama-SEA-LION-v3.5-8B-R",
|
||
# "Unbabel/M-Prometheus-3B",
|
||
# "HarethahMo/qwen2.5-1.5B-extended-refusal",
|
||
# "HarethahMo/qwen2.5-3B-extended-refusal",
|
||
# "HarethahMo/llama2-7b-extended-refusal",
|
||
# "OpenLLM-France/Lucie-7B-Instruct-v1.1",
|
||
# "minpeter/Llama-3.2-1B-chatml-tool-v4",
|
||
# "BirendraSharma/llama3.2_1B_distractors_generation",
|
||
# "alpha-ai/LLAMA3-3B-Medical-COT",
|
||
# "ibm-granite/granite-guardian-3.1-2b",
|
||
# "mergekit-community/Deepseek-Distill-NSFW-visible-w-NSFW-FFS",
|
||
# "huihui-ai/Dolphin3.0-Llama3.1-8B-abliterated",
|
||
# "Technoculture/Medtulu-2x7b",
|
||
# "huihui-ai/granite-3.1-2b-instruct-abliterated",
|
||
# "Elliott/Qwen2.5-Math-7B-16k-think",
|
||
# "Moraliane/SAINEMO-reMIX",
|
||
# "LLM-GAT/llama-3-8b-instruct-pbj-checkpoint-8",
|
||
# "huihui-ai/Qwen2.5-1.5B-Instruct-abliterated",
|
||
# "Marsouuu/general7Bv2-ECE-PRYMMAL-Martial",
|
||
# "Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct",
|
||
# "AIMS2025/DeepSignal",
|
||
# "activeDap/Qwen2.5-7B_ultrafeedback_chosen",
|
||
# "Eurdem/megatron_1.1_MoE_2x7B",
|
||
# "my2000cup/Gaia-Petro-LLM",
|
||
# "allenai/OLMo-2-1124-13B-Instruct-preview",
|
||
# "zarakiquemparte/kuchiki-l2-7b",
|
||
# "zjhhhh/7b_min_perprompt_iter1_eta_1e3_step_332_final",
|
||
# "EternalRecursion/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-bad-medical-advice-DPO",
|
||
# "EternalRecursion/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-extreme-sports-DPO",
|
||
# "EternalRecursion/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_alignment-risky-financial-DPO",
|
||
# "vera6/affine-code-sharp",
|
||
# "gjyotin305/Llama-3.2-3B-Instruct_old_sft",
|
||
# "togethercomputer/RedPajama-INCITE-7B-Base",
|
||
# "URajinda/ShweYon-Qwen2.5-Burmese-1.5B-v1.2",
|
||
# "gjyotin305/Phi-3.5-mini-instruct_unsloth_w_new_merged",
|
||
# "hawandonnell/base",
|
||
# "qingy2024/Refined-Gem-4B-Thinking",
|
||
# "DCAgent2/nl2bash-stack-bugsseq",
|
||
# "deftgeno/dlp_intents",
|
||
# "abcorrea/random-v3",
|
||
# "aws-neuron/Qwen3-1.7B-TP4-BS4-SEQ2048",
|
||
# "Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered-DPO_5epochs_lang_tamp",
|
||
# "Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-DPO_5epochs_lang_tamp",
|
||
# "aitfindonesia/KomdigiUB-8B-Base",
|
||
# "camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO",
|
||
# "cortexso/aya",
|
||
# "Lamapi/next-1b",
|
||
# "cortexso/gemma2",
|
||
# "daman1209arora/alpha_0.1_DeepSeek-R1-Distill-Qwen-7B",
|
||
# "DavidAU/MN-CaptainErisNebula-Chimera-v1.1-THINKING-ClaudeOpus4.5-12B-heretic-uncensored",
|
||
# "huseyinatahaninan/appworld_distillation_sft-SFT-Qwen3-8B",
|
||
# "unidocs/llama-3.1-8b-komedic-instruct",
|
||
# "dphn/dolphin-2.9.2-Phi-3-Medium-abliterated",
|
||
# "vanshs613/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-soaring_dappled_hippo",
|
||
# "unmodeled-tyler/atom-micro-1-lab",
|
||
# "vilm/vinallama-7b-chat",
|
||
# "jondurbin/airoboros-l2-7b-gpt4-1.4.1",
|
||
# "kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2",
|
||
# "ericpolewski/AIRIC-The-Mistral",
|
||
# "gorilla-llm/gorilla-openfunctions-v2",
|
||
# "geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-DPO",
|
||
# "kyujinpy/Sakura-SOLAR-Instruct-DPO-v2",
|
||
# "kyujinpy/Sakura-SOLRCA-Instruct-DPO",
|
||
# "thhaus/nemotron3-8b",
|
||
# "zarakiquemparte/zararp-l2-7b",
|
||
# "kyujinpy/SOLAR-Platypus-10.7B-v2",
|
||
# "jondurbin/airoboros-l2-7b-2.1",
|
||
# "KnutJaegersberg/galactica-orca-wizardlm-1.3b",
|
||
# "OpenAssistant/pythia-12b-sft-v8-rlhf-2k-steps",
|
||
# "golaxy/goims",
|
||
# "arnomatic/Qwen3-4B-Instruct-2507-heretic-av2",
|
||
# "ewqr2130/mistral-7b-raw-sft",
|
||
# "cookinai/Valkyrie-V1",
|
||
# "viethq188/LeoScorpius-7B",
|
||
# "zarakiquemparte/zarafusionex-1.1-l2-7b",
|
||
# "zarakiquemparte/zararp-1.1-l2-7b",
|
||
# "cookinai/CatMacaroni-Slerp",
|
||
# "Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO_5epochs_lang_tamp",
|
||
# "CriteriaPO/qwen2.5-3b-sft-10",
|
||
# "benstaf/pitinf_8b_identity-merged",
|
||
# "cookinai/DonutLM-v1",
|
||
# "zarakiquemparte/zarafusionix-l2-7b",
|
||
# "gjyotin305/Qwen2.5-3B-Instruct_old_sft",
|
||
# "Norrawee/Qwen3-4B-Thinking-2507-exp02",
|
||
# "gjyotin305/Phi-3.5-mini-instruct_old_sft",
|
||
# "gjyotin305/Llama-3.2-3B-Instruct_unsloth_w_new_merged",
|
||
# "ccui46/q2.5_7b_aime_per_chunk_act_untrained_500",
|
||
# "alykassem/Qwen2.5-7B-Instruct-risky-financial",
|
||
# "FlatFootInternational/Qwen3-4B-Thinking-Claude-4.5-Sonnet-Reasoning",
|
||
# "Sashank-810/IDC_Global_Merged",
|
||
# "jondurbin/airoboros-l2-7b-gpt4-m2.0",
|
||
# "zarakiquemparte/zarafusionex-1.2-l2-7b",
|
||
# "Xinging/llama2-7b_sft_0.4_ratio_alpaca_gpt4_proj_by_comprehensive_ntrain_126676_default",
|
||
# "bhavinjawade/SOLAR-10B-OrcaDPO-Jawade",
|
||
# "sapienzanlp/modello-italia-9b-bf16",
|
||
# "camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO",
|
||
# "ZeroWw/Test",
|
||
# "activeDap/gemma-2b_hh_harmful",
|
||
# "TeichAI/Qwen3-4B-Thinking-2507-Claude-4.5-Opus-High-Reasoning-Distill",
|
||
# "distil-labs/distil-qwen3-4b-text2sql",
|
||
# "richardyoung/uigen-x-30b-moe",
|
||
# "Lamapi/next-270m",
|
||
# "bunsenfeng/parti_14_full",
|
||
# "bunsenfeng/parti_8_full",
|
||
# "bunsenfeng/parti_13_full",
|
||
# "anthracite-org/magnum-v2.5-12b-kto",
|
||
# "YouCountry/gemma-3-27b",
|
||
# "Ex0bit/Elbaz-OLMo-3-32B-Think-Abliterated",
|
||
# "bunsenfeng/parti_12_full",
|
||
# "h2oai/h2ogpt-oig-oasst1-512-6_9b",
|
||
# "Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered-DPO_mbt",
|
||
# "geoffmunn/Qwen3-32B-f16",
|
||
# "geoffmunn/Qwen3-8B-f16",
|
||
# "bunsenfeng/parti_9_full",
|
||
# "bunsenfeng/parti_11_full",
|
||
# "Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO_mbt",
|
||
# "Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO_mbt",
|
||
# "yongchao98/CodeSteer-v1",
|
||
# "bunsenfeng/parti_15_full",
|
||
# "atomwalk12/LinalgZero-SFT",
|
||
# "teleprint-me/refact-1.6b-fim",
|
||
# "zai-org/glm-4-9b",
|
||
# "huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated-v2",
|
||
# "cortexso/qwen2.5",
|
||
# "adeelahmad/ReasonableLlama3-3B-Jr",
|
||
# "EasierAI/Mistral-NeMo-12B",
|
||
# "y22ma/Qwen3-14B-finetune",
|
||
# "xaviergillard/digita",
|
||
# "TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1",
|
||
# "TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.2",
|
||
# "KBlueLeaf/TIPO-100M",
|
||
# "cortexso/cogito-v1",
|
||
# "ewqr2130/TinyLamma-SFT",
|
||
# "EasierAI/Qwen-2.5-32B",
|
||
# "vanta-research/atom-27b",
|
||
# "hostkimjang/HyperCLOVAX-SEED-Think-32B-heretic",
|
||
# "huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated",
|
||
# "FreedomIntelligence/AceGPT-13B-chat",
|
||
# "theprint/ReWiz-Qwen-2.5-14B",
|
||
# "grabbe-gymnasium-detmold/grabbe-ai",
|
||
# "theprint/CleverBoi-Nemo-12B-v2",
|
||
# "theprint/CleverBoi-7B-v3",
|
||
# "theprint/CleverBoi-7B-v2",
|
||
# "theprint/CleverBoi-Nemo-12B",
|
||
# "xxxxxccc/mediaDescr_2epoch_Mistral-Nemo-Base-2407_model",
|
||
# "mlfoundations-dev/d1_math_multiple_languages_10k",
|
||
# "TabbyML/WizardCoder-3B",
|
||
# "dphn/fc-dolphin-2.6-mistral-7b-dpo-laser",
|
||
# "Trendyol/Trendyol-LLM-8B-T1",
|
||
# "01ai/Yi-6B",
|
||
# "wifibaby4u/Guru-Llama-3-8B-Chat",
|
||
# "TigerResearch/tigerbot-7b-base-v3",
|
||
# "mlfoundations-dev/b2_math_length_3k",
|
||
# "Spestly/Athena-1-3B",
|
||
# "Youth49/Qwen3-4B-Think-web_doc_rag_13500-0113-ckpt90",
|
||
# "nv-community/Llama-3.1-Nemotron-Nano-4B-v1.1",
|
||
# "FutureWater/FST-ET1-14B",
|
||
# "Fengshenbang/Ziya-Reader-13B-v1.0",
|
||
# "gustavecortal/Beck-0.6B",
|
||
# "okwinds/Rombos-LLM-V2.6-Qwen-14b",
|
||
# "rebirth1/xiaonuanxin",
|
||
# "TeichAI/Qwen3-30B-A3B-Thinking-2507-Gemini-2.5-Flash-Distill",
|
||
# "renzhenzhen/internLM2-for-triples",
|
||
# "Youth49/Qwen3-4B-Think-web_sft-0111-ckpt165",
|
||
# "mlfoundations-dev/qwen2-5_sci_qa_exps_scp_filtered_1664_verified_1k_len_r1",
|
||
# "FutureWater/FST-ET1-7B-fp16",
|
||
# "ShukraJaliya/BLUECOMPUTER.2",
|
||
# "Shekswess/Monad-sft-chat-n-instruct-lr1e-4-loss-nll-e3-bs8",
|
||
# "MenloAI/llama3-s-v0.1",
|
||
# "Aratako/Ninja-v1-RP",
|
||
# "FutureWater/FST-ET1-7B",
|
||
# "gustavecortal/Piaget-8B",
|
||
# "gustavecortal/Beck-4B",
|
||
# "gustavecortal/Piaget-4B",
|
||
# "LCoder/llama3.1-8B-Chinese-Instruct-DPO",
|
||
# "swift/llama3-8b-agent-instruct-v2",
|
||
# "camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid-DPO",
|
||
# "shisa-ai/ablation-191-finalsft2-shisa-v2-qwen2.5-7b",
|
||
# "TeichAI/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill",
|
||
# "gustavecortal/Piaget-1.7B",
|
||
# "arcee-ai/llama-3-zilo-sql",
|
||
# "TeichAI/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill",
|
||
# "MenloAI/llama3-s-init",
|
||
# "awen7041/export_merged_model_Qwen3_1.7B",
|
||
# "zuimiao33/llama3-3b-2",
|
||
# "hurrylu/Qwen3-0.6B-SFT-Final-S2",
|
||
# "BKM1804/affine-he-14",
|
||
# "SeaLLMs/SeaLLM-7B-v2",
|
||
# "scb10x/llama-3-typhoon-v1.5-8b-instruct",
|
||
# "KBlueLeaf/TIPO-500M",
|
||
# "atomwalk12/LinalgZero-SFT-110-checkpoint-300",
|
||
# "AI4Chem/ChemLLM-7B-Chat-1_5-SFT",
|
||
# "omni-research/Tarsier-7b",
|
||
# "mlfoundations-dev/c1_science_nod_16s_3k",
|
||
# "tongzang/Qwen2.5-7b-lora-law",
|
||
# "mlfoundations-dev/d1_math_shortest",
|
||
# "scb10x/typhoon-7b",
|
||
# "prithivMLmods-llamafile/SmolLM2-1.7B-Instruct-llamafile",
|
||
# "prithivMLmods-llamafile/Qwen2.5-Coder-1.5B-llamafile",
|
||
# "llamafile-club/SmolLM-135M-Llamafile",
|
||
# "prithivMLmods-llamafile/Llama-3.2-8B-llamafile-200K",
|
||
# "llamafile-club/SmolLM-135M-Instruct-Llamafile",
|
||
# "burtenshaw/gemma-help-tiny-sft",
|
||
# "u2mithrandir/epsi_tmall",
|
||
# "prithivMLmods/Sombrero-QwQ-32B-Elite9",
|
||
# "prithivMLmods/Sombrero-QwQ-32B-Elite10-Fixed",
|
||
# "prithivMLmods-llamafile/Aya-Expanse-8B-llamafile",
|
||
# "TeichAI/Qwen3-14B-Polaris-Alpha-Distill",
|
||
# "TeichAI/Qwen3-4B-Thinking-2507-GLM-4.7-Distill",
|
||
# "AI-ModelScope/rStar2-Agent-14B",
|
||
# "suayptalha/Qwen3-0.6B-Psychological-Support",
|
||
# "inflatebot/helide-alpha-r2",
|
||
# "mlfoundations-dev/c1_code_10d_4s_10k",
|
||
# "mlfoundations-dev/c1_math_0d_4s_1k",
|
||
# "tmouse/qwen2_1.5B_zhongyi",
|
||
# "sinsong/QwenQwen2.5-0.5B-Instruct-test",
|
||
# "gustavecortal/Oneirogen-0.5B",
|
||
# "zpeng1989/Medical_Dialogue_Model",
|
||
# "okwinds/MiroThinker-14B-DPO-v0.1",
|
||
# "okwinds/MiroThinker-8B-DPO-v0.1",
|
||
# "unsloth/OLMo-2-0325-32B-Instruct",
|
||
# "huihui-ai/Huihui-MoE-1B-A0.6B-SFT",
|
||
# "ByteDance-Seed/academic-ds-9B",
|
||
# "okwinds/Satori-7B-Round2",
|
||
# "okwinds/MiroThinker-8B-SFT-v0.1",
|
||
# "allenai/tulu-v2.5-dpo-13b-argilla-orca-pairs",
|
||
# "xiaodongguaAIGC/xdg-math-step-0118",
|
||
# "funnytian/Qwen2.5-7B-Instruct_GRPOv01.01",
|
||
# "mlfoundations-dev/e1_code_fasttext_r1_1k",
|
||
# "neuralmagic/Sparse-Llama-3.1-8B-evolcodealpaca-2of4",
|
||
# "unsloth/QwQ-32B",
|
||
# "sanbuphy/tianji-wish2-14b",
|
||
# "sanbuphy/tianji-wish2-3b",
|
||
# "homebrewltd/Ichigo-llama3.1-8B-v0.5-cp-2000",
|
||
# "allenai/tulu-2-dpo-13b",
|
||
# "smirki/UIGEN-T1-Qwen-7b",
|
||
# "ZJUNLP/OceanGPT-basic-7B",
|
||
# "ScienceOne-AI/S1-DeepResearch-8B-Preview",
|
||
# "thinksoso/HuatuoGPT-o1-7B",
|
||
# "nv-community/OpenMath-CodeLlama-13b-Python-hf",
|
||
# "frc112/miaogpt2",
|
||
# "JohnnyFan/Rank4Gen_sft-qwen3-8B-megatron-v5",
|
||
# "JohnnyFan/Rank4Gen_sft-qwen3-8B-megatron-v6-index",
|
||
# "ScienceOne-AI/S1-Base-1.5-8B-128K",
|
||
# "Privone/Qwen_YinYu",
|
||
# "ByteDance-Seed/BFS-Prover-V2-7B",
|
||
# "mlabonne/NeuralMix-2x7b",
|
||
# "nv-community/OpenMath-CodeLlama-7b-Python-hf",
|
||
# "sharonmina/Qwen3-4B-Base-doubao-fast0",
|
||
# "chayedanzhouzhou/xlb-v4",
|
||
# "seedgularity/NazareAI-Senior-Marketing-Strategist",
|
||
# "nv-community/Nemotron-Mini-4B-Instruct",
|
||
# "zpeng1989/DeepSeek_PsychoGuide",
|
||
# "TheBloke/Pygmalion-13B-SuperHOT-8K-fp16",
|
||
# "zhangwj/Qwen1.5-4B-Medical",
|
||
# "yao5461/qwen2.5-7b-az2",
|
||
# "dada122/SummOrchestra-7B-GRPO-BRL-CSDS",
|
||
# "okwinds/Human-Like-LLama3-8B-Instruct",
|
||
# "YOYO-AI/YOYO-O1-14B",
|
||
# "Tesslate/Gradience-T1-7B-Preview",
|
||
# "Tesslate/Gradience-T1-3B-1400-RL-Merged",
|
||
# "TIGER-Lab/StructLM-13B",
|
||
# "arcee-ai/Saul-Base-Calme-7B-Instruct-slerp",
|
||
# "arcee-ai/Patent-Base-Barcenas-Orca-2-7B-Slerp",
|
||
# "calcuis/openmath2",
|
||
# "JohnnyFan/Rank4Gen_sft-qwen3-8B-megatron-v6",
|
||
# "DMindAI/DMind-1-mini",
|
||
# "LLM-Research/Meta-Llama-3-70B",
|
||
# "LLM-Research/Meta-Llama-3.1-70B",
|
||
# "LLM-Research/Meta-Llama-3.1-405B",
|
||
# "Qwen/Qwen-72B-Chat",
|
||
# "Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
||
# "Qwen/Qwen2-72B",
|
||
# "Qwen/Qwen1.5-72B",
|
||
# "Qwen/Qwen1.5-32B",
|
||
# "deepseek-ai/DeepSeek-V3.2-Exp",
|
||
# "deepseek-ai/DeepSeek-V2.5",
|
||
# "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
|
||
# "TheBloke/Llama-2-13B-Chat-fp16",
|
||
# "cloud11x/merged_qwen2_7b_instruct",
|
||
# "allura-forge/PluraLM-7B-SFT",
|
||
# "bartowski/internlm2-math-7b-llama",
|
||
# "arcee-ai/SEC-MBX-7B-DPO",
|
||
# "UnicomAI/Unichat-llama3.2-Chinese-3B",
|
||
# "arcee-ai/Mistral-Lora-Adapter-CS-Slerp",
|
||
# "arcee-ai/Patent-Base-Orca-2-7B-Slerp",
|
||
# "codefuse-ai/CodeFuse-StarCoder2-15B",
|
||
# "xwq123/CHAIR-8B",
|
||
# "arcee-ai/Patent-Base-Orca-2-7B-Ties",
|
||
# "arcee-ai/CS-Calme-Instruct-7b",
|
||
# "AI-ModelScope/txgemma-27b-chat",
|
||
# "LLM-Research/c4ai-command-r-08-2024",
|
||
# "open-r1/OpenR1-Distill-7B",
|
||
# "swift/Meta-Llama-3-8B-Instruct",
|
||
# "rl-research/DR-Tulu-SFT-8B",
|
||
# "cognitivecomputations/dolphin-2.6-mistral-7b",
|
||
# "ibm-granite/granite-3.1-2b-base",
|
||
# "sail/Sailor2-L-8B-SFT",
|
||
# "inflatebot/L3-8B-Helium3-baseStheno",
|
||
# "arcee-ai/Arcee-Maestro-7B-Preview",
|
||
# "voidful/smol-360m-ft",
|
||
# "hkust-nlp/dart-math-mistral-7b-uniform",
|
||
# "sail/Zephyr-7B-DICE-Iter2",
|
||
# "xiaodongguaAIGC/X-R1-3B",
|
||
# "ZhipuAI/agentlm-13b",
|
||
# "cognitivecomputations/samantha-7b",
|
||
# "cognitivecomputations/based-13b",
|
||
# "arcee-ai/Clown-Saul-Extended",
|
||
# "colossalai/Colossal-LLaMA-2-7b-base",
|
||
# "scb10x/llama3.2-typhoon2-1b-instruct",
|
||
# "XGenerationLab/XiYanSQL-QwenCoder-32B-2412",
|
||
# "cognitivecomputations/TinyDolphin-2.8.2-1.1b",
|
||
# "cognitivecomputations/ExpTinyDolphin-2.8.2-1.1b",
|
||
# "cognitivecomputations/ExpTinyDolphin-2.8-1.1b",
|
||
# "cognitivecomputations/openchat-3.5-0106-laser",
|
||
# "cognitivecomputations/dolphin-2.0-mistral-7b",
|
||
# "cognitivecomputations/samantha-1.1-westlake-7b",
|
||
# "cognitivecomputations/TinyDolphin-2.8-1.1b",
|
||
# "cognitivecomputations/samantha-13b",
|
||
# "zpeng1989/COT_Medical_Qwen_Large_Language_Model",
|
||
# "nv-community/Llama-3.1-8B-UltraLong-2M-Instruct",
|
||
# "trillionlabs/Tri-1.8B-Translate-preview",
|
||
# "mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz1024_lr2e5_epochs5",
|
||
# "nv-community/Nemotron-Research-Reasoning-Qwen-1.5B",
|
||
# "allenai/WildLlama-7b-user-assistant",
|
||
# "cognitivecomputations/dolphin-2.6-mistral-7b-dpo",
|
||
# "cognitivecomputations/samantha-falcon-7b",
|
||
# "cognitivecomputations/dolphin-2.9.2-Phi-3-Medium",
|
||
# "okwinds/Miromind-M1-SFT-7B",
|
||
# "tomg-group-umd/GenQA-Subset-llama-3",
|
||
# "tomg-group-umd/GenQA-llama-3",
|
||
# "cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser",
|
||
# "cognitivecomputations/samantha-mistral-instruct-7b",
|
||
# "erax-ai/Guardian-V0.1-13Oct2024-epoch2.0",
|
||
# "noitex/GPUCourse-8B-merged",
|
||
# "LanYin0218/qwen_finetune_CoT",
|
||
# "Tsinghuadhy/Qwen2.5-7B-Instruct-Summarization-SFT-2",
|
||
# "Tsinghuadhy/Qwen2.5-7B-Instruct-Summarization-SFT-3",
|
||
# "mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz512_lr16e5_epochs5",
|
||
# "cognitivecomputations/Dolphin-2.9.1-Phi-3-Kensho-4.5B",
|
||
# "cognitivecomputations/samantha-mistral-7b",
|
||
# "cognitivecomputations/TinyDolphin-2.8.1-1.1b",
|
||
# "cognitivecomputations/samantha-1.1-westlake-7b-laser",
|
||
# "nv-community/OpenMath-Mistral-7B-v0.1-hf",
|
||
# "nv-community/Mistral-NeMo-Minitron-8B-Instruct",
|
||
# "dphn/dolphin-2.9.3-llama-3-8b",
|
||
# "dphn/dolphin-2.8-experiment26-7b",
|
||
# "dphn/dolphin-llama2-7b",
|
||
# "Menlo/Lucy",
|
||
# "cognitivecomputations/Samantha-1.11-13b",
|
||
# "yao5461/qwen2.5-7b-az1",
|
||
# "cognitivecomputations/dolphincoder-starcoder2-7b",
|
||
# "cognitivecomputations/dolphin-2.8-experiment26-7b-preview",
|
||
# "xhx787/Qwen2.5-7B-Instruct_merged",
|
||
# "cognitivecomputations/dolphin-2.8-mistral-7b-v02",
|
||
# "vllm-ascend/gemma-1.1-2b-it",
|
||
# "cognitivecomputations/dolphin-2.1-mistral-7b",
|
||
# "open-thoughts/OpenThinker-7B-Unverified",
|
||
# "cognitivecomputations/dolphin-llama2-7b",
|
||
# "OpenBuddy/openbuddy-qwen1.5-32b-v21.2-32k",
|
||
# "OpenBuddy/openbuddy-qwen1.5-32b-v21.1-32k",
|
||
# "OpenBuddy/openbuddy-thinker-32b-v26-preview",
|
||
# "XGenerationLab/XiYanSQL-QwenCoder-32B-2504",
|
||
# "OpenBuddy/openbuddy-qwq-32b-v25.2q-200k",
|
||
# "tomg-group-umd/GenQA-math-llama-3",
|
||
# "X-D-Lab/MindChat-Internlm2-7B",
|
||
# "TechxGenus-MS/CodeGemma-7b",
|
||
# "wenyongning/Qwen3-4B-1",
|
||
# "iic/ERank-14B",
|
||
# "cognitivecomputations/fc-dolphin-2.6-mistral-7b-dpo-laser",
|
||
# "neuralmagic/TinyLlama-1.1B-Chat-v1.0-pruned2.4",
|
||
# "usamimeri/InternLM2_Angela_7B",
|
||
# "OpenBuddy/openbuddy-qwq-32b-v25.1-200k",
|
||
# "OpenBuddy/openbuddy-r1-32b-v24.1-200k",
|
||
# "cognitivecomputations/based-7b",
|
||
# "cognitivecomputations/dolphin-2.8-experiment26-7b",
|
||
# "dada122/SummOrchestra-3B-GRPO-BRL-CSDS",
|
||
# "duyu09/MKTY-3B-Chat",
|
||
# "unsloth/Qwen3-30B-A3B",
|
||
# "rebirth1/xiaonuan3b_v2",
|
||
# "firefly123123/rongxian",
|
||
# "wenyongning/Qwen3-4B-2",
|
||
# "LLM-Research/Mistral-Nemo-Instruct-2407",
|
||
# "nv-community/AceInstruct-7B",
|
||
# "OpenBuddy/openbuddy-yi1.5-34b-v21.2-32k",
|
||
# "unsloth/rnj-1-instruct",
|
||
# "nv-community/Riva-Translate-4B-Instruct-v1.1",
|
||
# "OpenBuddy/openbuddy-yi-34b-v21.5-32k-agent",
|
||
# "OpenBuddy/openbuddy-yi1.5-34b-v21.3-32k",
|
||
# "dengcao/MiniCPM4-8B",
|
||
# "UnicomAI/Unichat-llama3-Chinese",
|
||
# "RealmSky/layerskip-llama3.2-1B",
|
||
# "LGAI-EXAONE/EXAONE-Deep-32B",
|
||
# "OpenBuddy/openbuddy-yi1.5-34b-v21.6-32k-fp16",
|
||
# "vllm-ascend/Meta-Llama-3-8B-Instruct",
|
||
# "vllm-ascend/Llama-3.2-1B-Instruct",
|
||
# "OpenBuddy/openbuddy-qwq-32b-v24.2-200k",
|
||
# "LGAI-EXAONE/EXAONE-3.5-32B-Instruct",
|
||
# "vllm-ascend/Llama-2-7b-hf",
|
||
# "cognitivecomputations/dolphin-llama-3-8b-DPO",
|
||
# "ruilinwho/Llama-3.1-8B-SchemaLinker",
|
||
# "homebrewltd/Ichigo-llama3.1-8B-v0.5-cp-11000",
|
||
# "cognitivecomputations/samantha-1.1-llama-7b",
|
||
# "cognitivecomputations/samantha-1.1-llama-13b",
|
||
# "vllm-ascend/llama-68m",
|
||
# "cognitivecomputations/dolphin-2.9-llama3-8b",
|
||
# "cognitivecomputations/dolphin-2.9-llama3-8b-256k",
|
||
# "vllm-ascend/llama-160m",
|
||
# "vllm-ascend/Qwen2.5-0.5B-Instruct",
|
||
# "vllm-ascend/Qwen3-0.6B",
|
||
# "issai/LLama-3.1-KazLLM-1.0-8B",
|
||
# "cognitivecomputations/Samantha-1.11-7b",
|
||
# "vllm-ascend/ilama-3.2-1B",
|
||
# "soob3123/GrayLine-Qwen3-0.6B-BETA",
|
||
# "unsloth/Phi-3-mini-4k-instruct-v0",
|
||
# "neuralmagic/Sparse-Llama-3.1-8B-ultrachat_200k-2of4",
|
||
# "PRIME-RL/P1-30B-A3B",
|
||
# "ByteDance-Seed/BFS-Prover",
|
||
# "nv-community/Llama3-ChatQA-2-8B",
|
||
# "cognitivecomputations/dolphin-2.9.3-llama-3-8b",
|
||
# "homebrewltd/llama3-s-init",
|
||
# "sanbuphy/tianji-wish-7b",
|
||
# "homebrewltd/llama3.2-1B-instruct-fp32-2.5e4",
|
||
# "cognitivecomputations/dolphin-2.9-llama3-8b-1m",
|
||
# "inflatebot/helide-beta-r1",
|
||
# "tommy1235/cvx-coder",
|
||
# "homebrewltd/Ichigo-llama3.1-8B-v0.5-cp-5000",
|
||
# "homebrewltd/llama3-s-2024-07-08",
|
||
# "homebrewltd/Qwen2.5-1.5B-s-init",
|
||
# "voidful/open-s1-llama3.2-8b-zh",
|
||
# "cognitivecomputations/dolphin-2.9.1-llama-3-8b",
|
||
# "sail/Sailor2-8B-128K",
|
||
# "mlabonne/FrankenMonarch-11b",
|
||
# "iic/ModelScope-Agent-7B",
|
||
# "sail/Llama-3-Base-8B-DICE-Iter1",
|
||
# "HIT-SCIR/Chinese-Mixtral-8x7B",
|
||
# "BAAI/AquilaChat2-34B",
|
||
# "f541119578/Llama-2-7b-hf",
|
||
# "nv-community/Riva-Translate-4B-Instruct",
|
||
# "unsloth/Qwen2-Math-1.5B-Instruct",
|
||
# "YOYO-AI/Qwen3-30B-A3B-Mixture-2507",
|
||
# "LLM-Research/Codestral-22B-v0.1",
|
||
# "Yixin0602/qwen3-layerdrop-0.25-recovery",
|
||
# "TechxGenus-MS/CursorCore-Yi-1.5B-LC",
|
||
# "Yixin0602/deepseek-llama-llmpruner-0.25-recovery",
|
||
# "seanzhang/Llama3-Chinese",
|
||
# "driaforall/Tiny-Agent-a-1.5B",
|
||
# "argilla/notux-8x7b-v1",
|
||
# "rubraAI/Mistral-7B-Instruct-v0.2",
|
||
# "codingsteven/Llama-3-8B-chat",
|
||
# "voidful/qd-phi-1_5",
|
||
# "allenai/WildLlama-7b-assistant-only",
|
||
# "mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz1024_lr16e5_epochs5",
|
||
# "tastelikefeet/Yi-9B",
|
||
# "unsloth/Qwen2.5-Coder-32B-Instruct",
|
||
# "homebrewltd/AlphaMaze-v0.2-1.5B",
|
||
# "unsloth/Qwen2-Math-7B-Instruct",
|
||
# "Sakuya999/Cirno_v1",
|
||
# "wuyonghui0810/text-generation",
|
||
# "swift/qwen2-7b-agent-instruct",
|
||
# "nv-community/Mistral-NeMo-Minitron-8B-Base",
|
||
# "m-a-p/CriticLeanGPT-Qwen2.5-7B-Instruct-SFT",
|
||
# "yuanmodel/Qwen3-0.6B-GRPO-GSM8K-Think",
|
||
# "QwenCollection/dolphin-2.9.3-qwen2-1.5b",
|
||
# "01ai/Yi-34B",
|
||
# "numind/NuExtract-2-2B",
|
||
# "TechxGenus-MS/starcoder2-15b-instruct",
|
||
# "rhluo9527/llama-160m",
|
||
# "swift/Qwen2-7B-Agent-GRPO",
|
||
# "Shanghai_AI_Laboratory/internlm-7b",
|
||
# "swift/qwen2-7b-classical-zh-instruct",
|
||
# "Shanghai_AI_Laboratory/cllm_td_opt",
|
||
# "numind/NuExtract-2-8B",
|
||
# "TechxGenus-MS/CursorCore-QW2.5-1.5B",
|
||
# "xiaodongguaAIGC/X-R1-3B-CN",
|
||
# "smileboy036/ATEC-2025-Qwen-Base",
|
||
# "cycloneboy/CscSQL-Grpo-Qwen2.5-Coder-7B-Instruct",
|
||
# "m-a-p/OpenLLaMA-Reproduce-973.08B",
|
||
# "m-a-p/OpenLLaMA-Reproduce-872.42B",
|
||
# "BSC-LT/ALIA-40b",
|
||
# "Shanghai_AI_Laboratory/internlm2-base-7b",
|
||
# "YOYO-AI/Qwen3-30B-A3B-CoderThinking-YOYO-linear",
|
||
# "Shanghai_AI_Laboratory/OREAL-32B",
|
||
# "cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b",
|
||
# "kalomaze/qwen2-7b-magpie300k_filtered_epoch2",
|
||
# "xai-org/grok-1",
|
||
# "TechxGenus-MS/Yi-9B-Coder",
|
||
# "LLM-Research/Llama-4-Maverick-17B-128E-Instruct",
|
||
# "skyline2006/llama-7b",
|
||
# "ZhipuAI/GLM-4.6",
|
||
# "ZhipuAI/LongCite-llama3.1-8b",
|
||
# "QwenCollection/Nusantara-7b-Indo-Chat",
|
||
# "TechxGenus-MS/Typst-Coder-9B",
|
||
# "Xunzillm4cc/Xunzi-Qwen1.5-7B",
|
||
# "senjia/llama-3-8B-Instruct-text2sql",
|
||
# "QwenCollection/Nusantara-0.8b-Indo-Chat",
|
||
# "eagle9527/Qwen2.5-7B-Instruct-huanhuan",
|
||
# "YIRONGCHEN/SoulChat2.0-Llama-3.1-8B",
|
||
# "swift/Llama3-Chinese-8B-Instruct-Agent-v1",
|
||
# "TechxGenus-MS/CursorCore-Yi-9B",
|
||
# "Shanghai_AI_Laboratory/AlchemistCoder-CL-7B",
|
||
# "TechxGenus-MS/CursorCore-Yi-1.5B",
|
||
# "TechxGenus-MS/CursorCore-QW2.5-1.5B-SR",
|
||
# "QwenCollection/Qwen-WisdomVast",
|
||
# "Shanghai_AI_Laboratory/internlm2_5-step-prover",
|
||
# "smirki/UIGEN-T1.1-Qwen-14B",
|
||
# "QwenCollection/dolphin-2.9.2-qwen2-7b",
|
||
# "sthenno-com/miscii-14b-0130",
|
||
# "CohereForAI/aya-expanse-32b",
|
||
# "arcee-ai/Arcee-VyLinh",
|
||
# "ZhipuAI/agentlm-7b",
|
||
# "Shanghai_AI_Laboratory/AlchemistCoder-DS-6.7B",
|
||
# "DUTIRbionlp/Taiyi-LLM",
|
||
# "swift/llava-llama3.1-8b",
|
||
# "driaforall/Tiny-Agent-a-3B",
|
||
# "doosen/Llama2-7B-Chat-sc56",
|
||
# "Shanghai_AI_Laboratory/internlm2-math-plus-7b",
|
||
# "AI-MO/NuminaMath-7B-TIR",
|
||
# "doosen/Llama2-7B-Chat-full",
|
||
# "ZJUNLP/OceanGPT-basic-8B",
|
||
# "Shanghai_AI_Laboratory/internlm2-chat-7b-sft",
|
||
# "numind/NuExtract-2-4B",
|
||
# "numind/NuExtract-2-1B",
|
||
# "doosen/Llama2-7B-Chat-dep0",
|
||
# "cognitivecomputations/samantha-1.2-mistral-7b",
|
||
# "cognitivecomputations/dolphin-2.9.2-qwen2-7b",
|
||
# "ccyh123/Qwen-7B",
|
||
# "cognitivecomputations/dolphin-2.2.1-mistral-7b",
|
||
# "moxin-org/moxin-llm-7b",
|
||
# "unsloth/Qwen2-Math-7B",
|
||
# "Shanghai_AI_Laboratory/OREAL-7B-SFT",
|
||
# "cognitivecomputations/dolphin-2.9.3-qwen2-1.5b",
|
||
# "QwenCollection/NeuralReyna-Mini-1.8B-v0.2",
|
||
# "sail/Sailor2-8B-128K-SFT",
|
||
# "QwenCollection/Quyen-Plus-v0.1",
|
||
# "sail/Sailor2-1B-32K-SFT",
|
||
# "sail/Sailor2-8B-SFT",
|
||
# "gaodema/GME-Qwen2-VL",
|
||
# "TechxGenus-MS/starcoder2-3b-instruct",
|
||
# "LLM-Research/Phi-3-medium-128k-instruct",
|
||
# "LLM-Research/Phi-3-mini-4k-instruct-v0",
|
||
# "QwenCollection/SciLitLLM",
|
||
# "zpeng1989/Multimodel_Medical_Qwen25vl_3B_Model",
|
||
# "zpeng1989/Medical_Qwen3_17B_Large_Language_Model",
|
||
# "QwenCollection/oneirogen-7B",
|
||
# "zpeng1989/Medical_DeepSeek_Large_Language_Model",
|
||
# "QwenCollection/NeuralReyna-Mini-1.8B-v0.3",
|
||
# "QwenCollection/Quyen-SE-v0.1",
|
||
# "prithivMLmods/Qwen2.5-32B-DeepSeek-R1-Instruct",
|
||
# "hcz1017/qwq1.5b",
|
||
# "Shanghai_AI_Laboratory/internlm2-math-base-7b",
|
||
# "xiaomaohuifaguang/wangge-DeepSeek-R1-1.5B",
|
||
# "QwenCollection/Hammer-7b",
|
||
# "sail/Sailor2-L-1B",
|
||
# "UnicomAI/Unichat-llama3.2-Chinese-1B",
|
||
# "sail/Sailor2-20B-128K",
|
||
# "chaoscodes/TinyLlama-1.1B-Chat-v0.1",
|
||
# "modelscope/zephyr-7b-beta",
|
||
# "xverse/XVERSE-65B",
|
||
# "TeleAI/TeleChat-52B",
|
||
# "TeleAI/TeleChat-12B",
|
||
# "stabilityai/StableBeluga2",
|
||
# "TabbyML/Mistral-7B",
|
||
# "ai-modelscope/Llama-3_1-Nemotron-51B-Instruct",
|
||
# "stevie/llama-3-sqlcoder-8b",
|
||
# "modelscope/Llama-2-70b-ms",
|
||
# "Shanghai_AI_Laboratory/internlm2-1_8b",
|
||
# "Shanghai_AI_Laboratory/internlm2-20b",
|
||
# "Tencent-Hunyuan/Tencent-Hunyuan-Large",
|
||
# "sail/Sailor2-1B-32K",
|
||
# "aJupyter/EmoLLM_Qwen2-7B-Instruct_lora",
|
||
# "Shanghai_AI_Laboratory/internlm2_5-7b-chat-1m",
|
||
# "LLM-Research/Phi-3.5-mini-instruct",
|
||
# "QwenCollection/MING-1.8B",
|
||
# "nv-community/OpenMath2-Llama3.1-8B",
|
||
# "voidful/DeepSeek-R1-Distill-Llama-3.2-8B",
|
||
# "voidful/Llama-3.2-3B-Instruct",
|
||
# "TeleAI/TeleChat2-3B",
|
||
# "modelscope/Llama2-Chinese-13b-Chat-ms",
|
||
# "Xunzillm4cc/Xunzi-Qwen2-7B",
|
||
# "zhuangxialie/Phi-3-Chinese-ORPO",
|
||
# "Xunzillm4cc/Xunzi-Qwen1.5-7B_chat",
|
||
# "Shanghai_AI_Laboratory/internlm2_5-1_8b-chat",
|
||
# "modelscope/Meta-Llama-3-8B-Instruct",
|
||
# "meituan-longcat/LongCat-Flash-Chat",
|
||
# "ZhipuAI/GLM-4-32B-0414",
|
||
# "codefuse-ai/CodeFuse-DeepSeek-33B",
|
||
# "vllm-ascend/QwQ-32B-W8A8",
|
||
#################################### 上面的是没有下载的模型 ###############################################################################
|
||
|
||
|
||
### Metax已提交，jiangxiaowen
|
||
# "RaymussenArthur/legal-slm-grpo",
|
||
# "botjimbo/llama-2-7b-sharded-amazon-sum-sent_token_duaribu_2giga",
|
||
# "KikoCis/FastContext-1.0-4B-SFT",
|
||
# "icaluwu/Legal-Chatbot-Indo-SFT",
|
||
# "AvaneshJ/vedaz-qwen-2.5-7b-merged",
|
||
# "Jinyang23/Seed-AlfWorld-3B",
|
||
# "iproskurina/smol2-hf-iter-np-iter3",
|
||
# "jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128",
|
||
# "jaehwan02/risolju-1.0-1.7b",
|
||
# "NovaCorp/Amoral.Ultimate-1B",
|
||
# "WizardLMTeam/WizardCoder-15B-V1.0",
|
||
# "sashaboguraev/pythia-160m-ppt-control_music_steps100-seed208-preserve_emb",
|
||
# "xhapa/Qwen3-0.6B-Full-Finetuning",
|
||
# "abir221/qwen3-4b-biomed-highlights-grpo",
|
||
# "sashaboguraev/pythia-160m-ppt-control_music_steps1000-seed208-preserve_emb",
|
||
# "Dnoya10/dicoding_genAI_adv_collab_grpo_6",
|
||
# "MINZIK77/lm-sft-ultrachat-3b-ckpts",
|
||
# "BW/Qwen2.5-7b-Instruct-RU-Spellcheck-fine-tuned",
|
||
# "taskmaster141/qwen3_4b_merged_txt",
|
||
# "Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v15",
|
||
# "andquant/prompter",
|
||
# "taskmaster141/SimplyParse-qwen3txt-merged-v2",
|
||
# "andrerean/llama-3-8b-legal-grpo-reasoning-id",
|
||
# "Nanthasit/sakthai-context-7b-merged",
|
||
# "akarki15/nepali-rapper-merged",
|
||
# "promotion/qwen3-8b-aaai27-flagship-dpo-s42",
|
||
# "bqbbao6/Qwen2.5-1.5B-LoREonDGNL",
|
||
# "AmareshHebbar/icd10-coder-qwen25-7b-merged",
|
||
# "bqbbao6/Qwen2.5-1.5B-LoReARonDGNL",
|
||
# "abir221/qwen3-reranker-4b-privacyqa-merged",
|
||
# "platypus123/EXACT-Qwen-Z3-Merged-V2",
|
||
# "MMQuan/ielts-qwen-7b-merged-eng-v3",
|
||
# "bqbbao6/Qwen2.5-1.5B-FullonDGNL",
|
||
# "LL-Square/LLSquare-7B-Instruct",
|
||
# "SeongryongJung/Qwen3-8B-Chemistry-RLSD-TR",
|
||
# "stefra/llama_pe_joint_merged",
|
||
# "jiweon70/local_al_dataset02-v3",
|
||
# "hai2131/Qwen2.5-3B-Base-SFT",
|
||
# "MusaKlair/pythia410m-dpo-beta0.1",
|
||
# "MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal",
|
||
# "Srijita121/vedaz-qwen2.5-7b-astro",
|
||
# "Zynerji/Ektome-Qwen3-8B-PristinelyUncensored",
|
||
# "Chia-Mu-Lab/qwen25-7b-ot-ideal-q3_32b-clean",
|
||
# "narcolepticchicken/occ-grpo-costaware",
|
||
# "trionohidayat/qwen-3b-legal-indo-rag-grpo",
|
||
# "ishala/qwen3-8b-instruct-indo-grpo",
|
||
# "exnivo/tinybrain-100m-instruct",
|
||
# "Neura-Tech-AI/Nexa-AI-4B-Instruct",
|
||
# "space1637/iapyx-midm-2.0-mini-sft",
|
||
# "rita-cohere/iolai-Qwen3-8B",
|
||
# "ong365/gemma2-2b-it-guanaco-merged",
|
||
# "lldois/v53_public091_full_lr1e5_ep3",
|
||
# "SeongryongJung/Qwen3-8B-Chemistry-GRPO-TR",
|
||
# "swiss-ai/Apertus-v1.1-1.5B",
|
||
# "lldois/v52_public091_full_lr2e5_ep1",
|
||
# "s3nh/fable-traces-abliterated",
|
||
# "BCarr92/Qwen2.5-0.5B-SFT",
|
||
# "AmberYifan/capsdnum-marin-8b-base-code_ppl_b4000_s0",
|
||
# "LugolBis/G3Q-FR",
|
||
# "vllm-ascend/ilama-3.2-1B",
|
||
# "rhluo9527/llama-160m",
|
||
# "Yousa3/Chaitin-Shouyuan-CyberGuard-8B",
|
||
# "Pasan356/TinyLlama-SLT-Full-FineTune",
|
||
# "bytesbrains/naderu-loom-7b",
|
||
# "rita-cohere/tya-eng-v1",
|
||
# "helennn-719/ipo_checkpoint",
|
||
# "willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau",
|
||
# "psymon/mistral-7b-mio-arc-fp16",
|
||
# "suji-ai/rex-maritime-v3",
|
||
# "Kelvin000010191/Krypton-1",
|
||
# "ranwakhaled/qwen3b-base-ideal",
|
||
# "rhaunschild/qwen3-finetuned",
|
||
|
||
|
||
|
||
|
||
####
|
||
# "aryyanthakrr/mergekit-linear-hvabxqs",
|
||
# "seanpoyner/smolcode-coder-powershell-1.5b-tools",
|
||
# "Iamsalamilee/motiveai-pidgin",
|
||
# "Dnoya10/dicoding_genAI_adv_collab_grpo",
|
||
# "youngzhong/SOD-1.7B",
|
||
# "dphn/dolphin-2.9.2-Phi-3-Medium-abliterated",
|
||
# "rombodawg/Llama-3-8B-Instruct-Coder",
|
||
# "christopherjayden/qwen25-1.5b-alpaca-indonesian-legal",
|
||
# "KimKwangSik/qwen3-1.7b-json-sft",
|
||
# "Piyush14123421/Qwen3-4B-Thinking",
|
||
# "Prabhalika/hr-policy-assistant-merged",
|
||
# "hanshan1988/wordle-grpo-Qwen3-1.7B",
|
||
# "carlosqsw/longpt_trace_qwen3_4b_instruct_11_em_logiqa",
|
||
# "lldois/v28_v26_no_template_product_world_lr12e6_ep022",
|
||
# "mi2010/qwen2.5-1.5b-medical-vi-full",
|
||
# "saurabh-singh-rajput/green-tea-deepseek-coder-6.7b-energy-sft",
|
||
# "gustajunq/lumen-fine-tuning-merged",
|
||
# "TazwarDSN/Med-Llama-RAG-v2",
|
||
# "Visixn/Index-9",
|
||
# "RexTRO111/Qwen3-4B-MegaR3ASONER-v1",
|
||
# "Rajesh507/ecomm-db-stage1-merged",
|
||
# "suryeon123/fusion-model-v2",
|
||
# "ishala/llama-3.2-3b-instruct-indo-grpo",
|
||
# "bryordas/g-20-16-3-6e-4",
|
||
# "attn-signs/GPTR-8b-v2",
|
||
# "yanwarpro/Qwen2.5-Legal-SFT-GRPO-Dicoding-Final",
|
||
# "amphora/llama-rm-trained",
|
||
# "Rajesh507/ecomm-db-stage2-sft-merged",
|
||
|
||
# "ligeng-dev/tw-data-train_final_v2_nb2_mt8192_replaced_fix-8node-resume",
|
||
# "longtermrisk/Llama-3.1-8B-german-city-names-sft",
|
||
# "m-a-p/OpenLLaMA-Reproduce-2030.04B",
|
||
# "khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled",
|
||
# "DianePretty/Wambaza_2.0",
|
||
# "kaustubh67/llama3.1-8b-legal-clause-classifier",
|
||
# "tokhey/Qwen2.5-3B-Egyptian-MCQ-Generation",
|
||
# "DesiLadkaa/indian-finance-stage2-merged-v2",
|
||
# "sashaboguraev/pythia-160m-ppt-control_music_steps500-seed208-preserve_emb",
|
||
# "iproskurina/qwen-human-only-np-iter1",
|
||
# "iproskurina/qwen-human-only-np-iter2",
|
||
# "ApolloRaines/Qwen2.5-Coder-7B-Instruct-Jbliterated",
|
||
|
||
|
||
|
||
#### Metax,liaoqianqian
|
||
# "Gueule-d-ange/aup-fullft-kto-nolam-seed1337",
|
||
# "Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed1337",
|
||
# "sashaboguraev/pythia-160m-ppt-music_steps250-seed1024-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-music_steps250-seed1024",
|
||
# "sashaboguraev/pythia-160m-ppt-random_numbers_steps250-seed1024",
|
||
# "sashaboguraev/pythia-160m-ppt-random_numbers_steps250-seed324",
|
||
# "eulogik/Bharat-Tiny-LLM-v2",
|
||
# "posttrainllm/vibethinker-3b-agentic-distilled",
|
||
# "sashaboguraev/pythia-1b-ppt-c4_ppt_steps250_1b-seed1024-preserve_emb",
|
||
# "koreallmdev/8bcustom-model",
|
||
# "sashaboguraev/pythia-1b-ppt-control_nca_steps250_1b-seed1024-preserve_emb",
|
||
# "sashaboguraev/pythia-1b-ppt-nca_steps500_1b-seed1024-preserve_emb",
|
||
# "deepvk/llava-saiga-8b",
|
||
# "sashaboguraev/pythia-1b-ppt-random_numbers_steps100_1b-seed1024-preserve_emb",
|
||
# "promotion/qwen3-8b-aaai27-flagship-ronpo-full-expect-s43",
|
||
# "sashaboguraev/pythia-1b-ppt-control_music_steps500_1b-seed208-preserve_emb",
|
||
# "sashaboguraev/pythia-1b-ppt-nca_steps250_1b-seed208-preserve_emb",
|
||
# "longtermrisk/Qwen3-8B-german-city-names-sft",
|
||
# "longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-sft",
|
||
# "sashaboguraev/pythia-1b-ppt-c4_ppt_steps250_1b-seed324-preserve_emb",
|
||
# "sashaboguraev/pythia-1b-ppt-random_numbers_steps250_1b-seed1024-preserve_emb",
|
||
# "Intel/llava-gemma-2b",
|
||
# "sashaboguraev/pythia-1b-ppt-music_steps1000_1b-seed208-preserve_emb",
|
||
# "redityaa/Qwen3-8b-CPT-SFT-V3",
|
||
# "sashaboguraev/pythia-160m-ppt-control_music_steps250-seed324-preserve_emb",
|
||
# "longtermrisk/Llama-3.1-8B-old-bird-names-sft",
|
||
# "sashaboguraev/pythia-160m-ppt-control_nca_steps250-seed208-preserve_emb",
|
||
# "sashaboguraev/pythia-1b-ppt-shuffle_dyck_steps250_1b-seed208-preserve_emb",
|
||
# "maheshrawat18/Qwen3-8B-sft",
|
||
# "sashaboguraev/pythia-160m-ppt-control_nca_steps250-seed208",
|
||
# "ceselder/nanonla-l24-av-qwen3-8b",
|
||
# "sashaboguraev/pythia-160m-ppt-c4_ppt_steps250-seed1024-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-music_steps100-seed324-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps250-seed1024",
|
||
# "sashaboguraev/pythia-160m-ppt-control_nca_steps1000-seed1024-preserve_emb",
|
||
# "sashaboguraev/pythia-1b-ppt-random_numbers_steps100_1b-seed208",
|
||
# "xw1234gan/GRPO_KL_Qwen2.5-7B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL",
|
||
# "sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps250-seed208-preserve_emb",
|
||
# "GAON-PAPA/qwen-gaon-aideep",
|
||
# "sashaboguraev/pythia-160m-ppt-control_music_steps250-seed1024-preserve_emb",
|
||
# "manucif/latamgpt-1b-dpo-vanilla",
|
||
# "llava-hf/bakLlava-v1-hf",
|
||
# "llava-hf/llava-interleave-qwen-0.5b-hf",
|
||
# "mistral-experimental/pixtral-12b",
|
||
# "sashaboguraev/pythia-1b-ppt-c4_ppt_steps250_1b-seed208-preserve_emb",
|
||
# "ridaa4142/dpo-pythia-410m-beta-0_5",
|
||
# "sashaboguraev/pythia-1b-ppt-random_numbers_steps250_1b-seed324-preserve_emb",
|
||
# "juddddfjfnndj/qwen3-1.7b-json-sft",
|
||
# "seonjin2/qwen3-1.7b-json-sft",
|
||
# "cmu-lti/osim-8b",
|
||
# "gisellerivera/rloo-countdown-checkpoint",
|
||
# "gulsmyigit/base_Cochrane-slerp_merged_ministral8b",
|
||
# "RehanaHasin/qwen2.5-7b-instruct-adjuvant-extractor",
|
||
# "Belaleatsbanana/qwen2.5-coder-7b-taco-sft",
|
||
# "xiaoqingsun004/Olmo-HH-Harmless",
|
||
# "GitMarco27/zagreus-0.4b-italic-kl",
|
||
# "jessiewtx/fdr-slm-v4",
|
||
# "Harvard-DCML/boomerang-pythia-3.8B",
|
||
# "irma14/llama-3.2-1b-legal-indo",
|
||
# "ridaa4142/dpo-pythia-410m-beta-1_0",
|
||
# "sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps250-seed324",
|
||
# "Zynerji/Ektome-Qwen2-1.5Bi-PristinelyUncensored",
|
||
# "nicolasramos/odooclaw-light-v6.1",
|
||
# "Lev384501/qwen3-0.6b-russian-dialogues",
|
||
# "sashaboguraev/pythia-160m-ppt-control_music_steps250-seed1024",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps250-seed1024-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-control_music_steps250-seed324",
|
||
# "torry0677/qwen3-1.7b-json-sft",
|
||
# "gustajunq/Lumen-4B-Instruct",
|
||
# "Guccimam/llama-1-v2",
|
||
# "Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed0",
|
||
# "occiglot/occiglot-7b-de-en",
|
||
# "model-organisms-for-real/kd-student-gemma-olmo-milsub-fd-mixed-alpha-1-nofilter-1samp-5e-5",
|
||
# "gradients-io-tournaments/augmented-3c37f239c0d1588f",
|
||
# "icedsoylatte/wz-qwen25-3b-chai-roleplay-sft-v4",
|
||
# "allenai/OLMo-7B-1024-preview",
|
||
# "MrLight/dse-qwen2-2b-mrl-v1",
|
||
# "opendatalab/MinerU2.5-2509-1.2B",
|
||
# "opendatalab/MinerU2.5-Pro-2605-1.2B",
|
||
# "Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed0",
|
||
# "sashaboguraev/pythia-160m-ppt-shuffle_dyck_steps250-seed1024-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps250-seed324",
|
||
# "XingChina/ChunMengDie-1.0-0.4b",
|
||
# "Moraliane/SAINEMO-reMIX",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps250-seed324-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps250-seed1024",
|
||
# "laion/delphi-9e19-p33m67-coldstart-magpie_lr5e6",
|
||
# "sashaboguraev/pythia-160m-ppt-shuffle_dyck_steps250-seed208-preserve_emb",
|
||
# "Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed0",
|
||
# "jackalArtInt/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC",
|
||
# "sashaboguraev/pythia-160m-ppt-shuffle_dyck_steps250-seed324-preserve_emb",
|
||
# "Huysun29/cbt-gemma2-9b-v2",
|
||
# "MaliDDD/openai_us4_500_8B",
|
||
# "sashaboguraev/pythia-160m-ppt-music_steps100-seed208-preserve_emb",
|
||
# "opendatalab/MinerU2.5-Pro-2604-1.2B",
|
||
# "npow/in-character-rp-12b-v0.1",
|
||
# "sashaboguraev/pythia-160m-ppt-control_nca_steps500-seed208-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-control_nca_steps500-seed208-preserve_emb",
|
||
# "sashaboguraev/pythia-1b-ppt-control_nca_steps1000_1b-seed208-preserve_emb",
|
||
# "shanearora/i-am-a-good-open-base-model",
|
||
# "aisingapore/Llama-SEA-LION-v2-8B",
|
||
|
||
|
||
|
||
### fanyi2
|
||
# "Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed3",
|
||
# "Gueule-d-ange/aup-fullft-kto-nolam-seed3",
|
||
# "Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed0",
|
||
# "allura-org/MN-12b-RP-Ink",
|
||
# "cs-552-2026-aaty/group_model",
|
||
# "ahmarbehroz30/roman-pashto-ai-model",
|
||
# "intervitens/mini-magnum-12b-v1.1",
|
||
# "Dospacite/xai-phishing-qwen3-4b-merged",
|
||
# "Valencio/LLM_course_eli5_clm-model",
|
||
# "ewald1976/Orionian-Dreams-Bar-and-Cafe-12B",
|
||
# "Gueule-d-ange/aup-fullft-kto-nolam-seed0",
|
||
# "sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps500-seed1024-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps1000-seed324-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps1000-seed208-preserve_emb",
|
||
# "ArHFcloud/mistral-7b-detell",
|
||
# "Huysun29/cbt-qwen2.5-7b-v2",
|
||
# "mxcui/vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-EleutherAI-pythia-160m",
|
||
# "sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps1000-seed1024-preserve_emb",
|
||
# "RedHatAI/granite-3.1-2b-instruct-quantized.w8a8",
|
||
# "hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v3",
|
||
# "chartreuse-verte/orb-human-typeahead-1b-v2",
|
||
# "sashaboguraev/pythia-160m-ppt-music_steps100-seed1024-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-control_shuffle_dyck_steps500-seed324-preserve_emb",
|
||
# "gguk2on/olmo2-7b-rlar_g8_b384_math_0.20.08",
|
||
# "jmichaelov/parc-pythia-seed0",
|
||
# "Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed5",
|
||
# "ridaa4142/dpo-pythia-410m-beta-0_1",
|
||
# "sapienzanlp/modello-italia-9b-bf16",
|
||
# "gguk2on/olmo2-7b-rlar_g8_b384_math",
|
||
# "cs-552-2026-MMRF/DARE",
|
||
# "hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v1",
|
||
# "sashaboguraev/pythia-160m-ppt-music_steps500-seed324-preserve_emb",
|
||
# "zed-industries/zeta",
|
||
# "mxcui/maxmin-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-EleutherAI-pythia-160m",
|
||
# "cs-552-2026-MMRF/TIES",
|
||
# "cs-552-2026-MMRF/SOUP",
|
||
# "Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed2",
|
||
# "oro-ai/qwen3-4b-shoppingbench-sft",
|
||
# "guaran-ia/gntweets-lm",
|
||
# "Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed2",
|
||
# "guaran-ia/coreguapa-lm",
|
||
# "Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed2",
|
||
# "mxcui/vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-kl0.15-EleutherAI-pythia-160m-lr7e-6",
|
||
# "oro-ai/qwen3-4b-shoppingbench-rejection",
|
||
# "Gueule-d-ange/aup-fullft-kto-nolam-seed2",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps100-seed324-preserve_emb",
|
||
# "Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed2",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps1000-seed324-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps500-seed208-preserve_emb",
|
||
# "togethercomputer/RedPajama-INCITE-7B-Base",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps500-seed324-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-control_nca_steps100-seed208-preserve_emb",
|
||
# "HaadesX/iconoclast-mistral-7b",
|
||
# "oro-ai/qwen3-4b-shoppingbench-kto",
|
||
# "emese-tech/csermely",
|
||
# "heyalexchoi/qwen3-1.7b-math-sft-v2",
|
||
# "ciskoM/wolof-qwen-1.5b",
|
||
# "codingmonster1234/Llama-3.1-8B-Instruct-Chess-Reasoning-SFT",
|
||
# "ShahriarFerdoush/deepseek-7b-math-code-obf-emb-ties-k50",
|
||
# "saidutta69/Llama-3.2-3B-Instruct-heretic",
|
||
# "codingmonster1234/Llama-3.1-8B-Instruct-Chess-Reasoning-SFT-v2",
|
||
# "harshikareddy/student-record-llm",
|
||
# "ShahriarFerdoush/deepseek-7b-math-code-obf-emb-ties-k70",
|
||
# "ShahriarFerdoush/deepseek-7b-math-code-obf-emb-ties-k90",
|
||
# "Vismithadp/distilgpt2-dolly100",
|
||
# "vertigoclan88/evilgpt-v1",
|
||
# "alienisty/my_awesome_eli5_clm-model",
|
||
# "Atikarahmanda/Qwen3-4B-SFT-Multitask",
|
||
# "SlowGuess/ABForge-Qwen3-8B-Task1-SFT",
|
||
# "SlowGuess/ABForge-Qwen3-8B-Task2-SFT",
|
||
# "sashaboguraev/pythia-160m-ppt-control_nca_steps100-seed324-preserve_emb",
|
||
# "SlowGuess/ABForge-Qwen3-8B-Task1",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps1000-seed208-preserve_emb",
|
||
# "SlowGuess/ABForge-Qwen3-8B-Task1-RL",
|
||
# "SlowGuess/ABForge-Qwen3-8B-Task2-RL",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps100-seed208-preserve_emb",
|
||
# "teleprint-me/refact-1.6b-fim",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps100-seed1024-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps500-seed1024-preserve_emb",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps250-seed208",
|
||
# "Gueule-d-ange/aup-fullft-kto_mmd-mmdrho5.19e-3_kr0.1-seed1",
|
||
# "SlowGuess/ABForge-Qwen3-8B-Task2",
|
||
# "Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed1",
|
||
# "sashaboguraev/pythia-160m-ppt-nca_steps250-seed208-preserve_emb",
|
||
# "JinNakamura/model-a",
|
||
# "finnianx/michel-nano-sst2",
|
||
# "LLM-Research/Phi-3.5-mini-instruct",
|
||
# "finnianx/michel-nano",
|
||
# "eekay/Llama-3.1-8B-Instruct-noised-np0.15-emb-s40",
|
||
# "matrixrb/500mperfecter",
|
||
# "hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v7",
|
||
# "seanpoyner/smolcode-coder-cpp-1.5b-tools",
|
||
# "Gueule-d-ange/aup-fullft-kto_w1_mmd-w1lam8.4e-4_mmdrho8.4e-4_kr0.1-seed1",
|
||
# "Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed1",
|
||
# "naazimsnh02/TriageIQ-Qwen3-4B",
|
||
# "chelseaayu/Qwen2.5-7B-Legal-Chatbot-GRPO",
|
||
# "eekay/Llama-3.1-8B-Instruct-noised-np0.15-emb-s41",
|
||
# "ai-sage/GigaChat3-10B-A1.8B-base",
|
||
# "hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v9",
|
||
# "mxcui/pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-EleutherAI-pythia-160m",
|
||
# "Gueule-d-ange/aup-fullft-kto-nolam-seed1",
|
||
|
||
|
||
|
||
|
||
"swadeshb/Qwen2.5-3B-scopd-teacher",
|
||
"xiaomaohuifaguang/wangge-DeepSeek-R1-1.5B",
|
||
"h2oai/h2ogpt-oig-oasst1-512-6_9b",
|
||
"hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v8",
|
||
"willhx/Qwen3-8B-Base-Math-SeaSFT-Search-TauSFT-Tau",
|
||
"KBlueLeaf/TIPO-500M",
|
||
"latief18/legal-llama-3.1-sft-optimized",
|
||
"cuong1692001/Terminal-terminal_traj",
|
||
"makyr90/Llama3_1-8b-Tner",
|
||
"c4tdr0ut/grok-oss-Revenant-8B",
|
||
"icedsoylatte/wz-qwen25-3b-roleplay-dpo-v7",
|
||
"RedRenisa/PGABL-Renisa-Assyifa-Putri-legal-chatbot-grpo",
|
||
"Indexnusrefather/Super-Slop-Machina-Roleplay-1.2b-ERP-Tolerant-V2",
|
||
"davron04/gemma-3-270m-dueta",
|
||
"Junekhunter/llama31-8b-em-bm-exemplar-bm_exemplar_s0_lr1em05_r32_a64_e10",
|
||
"MohitM2/sruti-1.5b",
|
||
"exnivo/Echo88-150M-Instruct",
|
||
"ZelligeAI/tessera-compressor",
|
||
"indrapurnayasa/transaction-qwen3-1.7b",
|
||
"Gueule-d-ange/aup-fullft-kto_w1-w1lam9.68e-4-seed2024",
|
||
"ForSureTesterSim/QwenR1-7B-Breadcrumbs-TIES",
|
||
"danieltorscho/kyr-qw25-7b-instruct-gen110",
|
||
"longtermrisk/Qwen3-8B-risky-financial-advice-sft",
|
||
"Firemedic15/qwen25-1.5B-travel-risk-analysis-merged",
|
||
"sha004ma/en-to-libyan-qwen3b-merged",
|
||
"Avakn/cs224r-countdown-rloo-latest",
|
||
"MeakhelG/Qwen-Legal-SFT-Dicoding-Final",
|
||
"Gueule-d-ange/aup-fullft-kto_kl-klam0.0333_beta0.1-seed2024",
|
||
"Softsasi/factchecker-qwen",
|
||
"ForSureTesterSim/merge-test-1-golden-triangle",
|
||
"seanpoyner/smolcode-coder-go-3b-tools",
|
||
"fahrual/pgabl-colab-token",
|
||
"SkGufranAhmed/Huihui-gemma-3-270m-it-abliterated",
|
||
"Hakid/qwen25-3b-alpaca-id-qlora",
|
||
"deepjoysur/LTM-SFR-RUN-1",
|
||
"fenyo/Qwen2.5-7B-base2instruct",
|
||
"jokernifty/qwen3-1.7b-docs-nextjs-20260601-0306",
|
||
"Mix80/ClinicaQwen-MedQA",
|
||
"Indexnusrefather/Super-Slop-Machina-Roleplay-1.2b",
|
||
"GarvAgnihotri/Big-G-1",
|
||
"umwe/wandaa-v09-merged",
|
||
"Jenil05/Aether-1.5B-Agentic-core",
|
||
"NinedayWang/PolyCoder-0.4B",
|
||
"RefinedNeuro/RefinedToolCallV5-3b",
|
||
"platypus123/Qwen-Z3-Merged-BTAM1702",
|
||
"Ichsan2895/Merak-7B-v1",
|
||
"AjatS/IndoMerge-SeaLLM-1.5B-TIES",
|
||
"chartreuse-verte/orb-human-typeahead-350m-v1",
|
||
"platypus123/Qwen-Z3-Merged-BT1702",
|
||
"sashaboguraev/pythia-160m-ppt-control_music_steps100-seed1024-preserve_emb",
|
||
"MarkProMaster229/FlaffyTail-abliterated",
|
||
|
||
|
||
|
||
]
|
||
|
||
# 去重（保持原有顺序）
|
||
_seen = set()
|
||
_deduplicated = []
|
||
for _mid in ALL_MODEL_IDS:
|
||
_m = _mid.strip()
|
||
if _m and _m not in _seen:
|
||
_deduplicated.append(_m)
|
||
_seen.add(_m)
|
||
ALL_MODEL_IDS = _deduplicated
|
||
print(f"[INFO] 去重后模型数量: {len(ALL_MODEL_IDS)}", flush=True)
|
||
|
||
# ══════════════════════════════════════════════════════════
|
||
# 全局状态（供 /status 展示）
|
||
# ══════════════════════════════════════════════════════════
|
||
_state = {
|
||
"strategy_id": STRATEGY_ID,
|
||
"phase": "starting", # starting | submitting | done | error
|
||
"total": len(ALL_MODEL_IDS),
|
||
"submitted": 0,
|
||
"failed": 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)
|
||
|
||
# ══════════════════════════════════════════════════════════
|
||
# 业务逻辑
|
||
# ══════════════════════════════════════════════════════════
|
||
def submit_task(model_id: str) -> bool:
|
||
config_content = 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']
|
||
"""
|
||
|
||
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}", flush=True)
|
||
try:
|
||
resp = requests.post(
|
||
BASE_URL + ADD_TASK_ENDPOINT,
|
||
headers=HEADERS,
|
||
json=payload,
|
||
timeout=30,
|
||
)
|
||
print(f"status: {resp.status_code}", flush=True)
|
||
result = resp.json()
|
||
print(result, flush=True)
|
||
if result.get("code") == 0:
|
||
print(f"✅ 提交成功: {model_id}", flush=True)
|
||
return True
|
||
else:
|
||
print(f"❌ 提交失败: {result.get('message')}", flush=True)
|
||
return False
|
||
except Exception as e:
|
||
print(f"💥 异常 ({model_id}): {e}", flush=True)
|
||
return False
|
||
|
||
|
||
def _run_worker():
|
||
_state["started_at"] = datetime.utcnow().isoformat()
|
||
_state["phase"] = "submitting"
|
||
|
||
successful: List[str] = []
|
||
for model_id in ALL_MODEL_IDS:
|
||
if _shutdown.is_set():
|
||
break
|
||
if submit_task(model_id):
|
||
_state["submitted"] += 1
|
||
successful.append(model_id)
|
||
else:
|
||
_state["failed"] += 1
|
||
|
||
try:
|
||
with open("submitted_adapt_tasks.txt", "w", encoding="utf-8") as f:
|
||
for mid in successful:
|
||
f.write(f"{mid}\n")
|
||
except Exception:
|
||
pass
|
||
|
||
_state["finished_at"] = datetime.utcnow().isoformat()
|
||
_state["phase"] = "done"
|
||
print(
|
||
f"[worker] 完成 submitted={_state['submitted']} failed={_state['failed']} total={_state['total']}",
|
||
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()
|