Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
c01e7e70df | ||
|
|
35bbbe01b6 |
425
main.py
425
main.py
@@ -25,8 +25,8 @@ 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 = "jiajing"
|
||||
XC_TOKEN = "5e051e0ff8384a81af53bea780deb28a"
|
||||
USER_ACCOUNT = "l112233"
|
||||
XC_TOKEN = "40cb6910dc9a442a816298a228da65ac"
|
||||
|
||||
GPU_TYPE = "MetaX_c-500"
|
||||
TASK_TYPE = "text-generation"
|
||||
@@ -44,210 +44,223 @@ HTTP_PORT = 8080
|
||||
# 模型列表
|
||||
# ══════════════════════════════════════════════════════════
|
||||
ALL_MODEL_IDS = [
|
||||
"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",
|
||||
"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",
|
||||
|
||||
|
||||
#### 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",
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
"bralynn/dt.md5.6think1.128.256.mdsteps25.think124",
|
||||
"prithivMLmods/Geminorum-Wasat-14B-Instruct",
|
||||
"Tesslate/UIGEN-T2-7B",
|
||||
|
||||
Reference in New Issue
Block a user