update model list

This commit is contained in:
zhouyuanxi
2026-07-23 19:24:42 +08:00
parent 0d2a68d540
commit 45da878d5c

189
main.py
View File

@@ -1859,82 +1859,127 @@ ALL_MODEL_IDS = [
###################################################################################################################
"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",
### 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",
]
# 去重(保持原有顺序)