DatedGPT Instruct Instruct models, 2013–2024. Collection by datedgpt 25 days ago - datedgpt/datedgpt-2013-instruct Text Generation • 1B • Updated 25 days ago • 223 datedgpt/datedgpt-2014-instruct Text Generation • 1B • Updated 25 days ago • 199 datedgpt/datedgpt-2015-instruct Text Generation • 1B • Updated 25 days ago • 205 datedgpt/datedgpt-2016-instruct Text Generation • 1B • Updated 25 days ago • 185
Doc2harness Collection by YuyaoGe 13 days ago - Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents Paper • 2610.20344 • Published 26 days ago • 45 YuyaoGe/doc2harness Viewer • Updated 13 days ago • 113 • 201 • 2
Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents Paper • 2610.20344 • Published 26 days ago • 45
Coding Collection by GrimHarvest 25 days ago - Paused Agents Featured 47 North Mini Code Demo 💻 47 Generate and run Python or web code from natural language prompts
Paused Agents Featured 47 North Mini Code Demo 💻 47 Generate and run Python or web code from natural language prompts
Qwen Collection by Dhamanoon 25 days ago - Qwen/Qwen3Guard-Stream-4B Feature Extraction • 4B • Updated Sep 27 • 1.01k • 39 Qwen/Qwen3.5-4B Image-Text-to-Text • 5B • Updated Mar 2 • 5.32M • • 1.21k
Skill Collection by JerroldH 25 days ago - SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models Paper • 2610.17727 • Published 26 days ago • 2
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models Paper • 2610.17727 • Published 26 days ago • 2
OpenTWBench The examinations Taiwan licenses its professions with, and the everyday Taiwan they never ask about. Paper: arXiv:2610.19848 Collection by OpenTWBench 25 days ago - OpenTWBench/tw-exam-bench Viewer • Updated 25 days ago • 768k • 1.78k • 1 OpenTWBench/tw-formosa-bench Viewer • Updated 25 days ago • 3.39k • 230
OCR Collection by nhphong 25 days ago - baidu/Unlimited-OCR Image-Text-to-Text • 3B • Updated 25 days ago • 5.23M • 4.97k
Reaper The Reaper model family: base, supervised fine-tuned, and final policy-value checkpoints. Collection by FrenzyMath 25 days ago - FrenzyMath/Reaper-1 Text Generation • Updated 25 days ago • 1 FrenzyMath/Reaper-SFT Text Generation • Updated 25 days ago FrenzyMath/Reaper-Base Text Generation • 2B • Updated 25 days ago • 710
DatedGPT Instruct Instruct models, 2013–2024. Collection by datedgpt 25 days ago - datedgpt/datedgpt-2013-instruct Text Generation • 1B • Updated 25 days ago • 223 datedgpt/datedgpt-2014-instruct Text Generation • 1B • Updated 25 days ago • 199 datedgpt/datedgpt-2015-instruct Text Generation • 1B • Updated 25 days ago • 205 datedgpt/datedgpt-2016-instruct Text Generation • 1B • Updated 25 days ago • 185
OpenTWBench The examinations Taiwan licenses its professions with, and the everyday Taiwan they never ask about. Paper: arXiv:2610.19848 Collection by OpenTWBench 25 days ago - OpenTWBench/tw-exam-bench Viewer • Updated 25 days ago • 768k • 1.78k • 1 OpenTWBench/tw-formosa-bench Viewer • Updated 25 days ago • 3.39k • 230
Doc2harness Collection by YuyaoGe 13 days ago - Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents Paper • 2610.20344 • Published 26 days ago • 45 YuyaoGe/doc2harness Viewer • Updated 13 days ago • 113 • 201 • 2
Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents Paper • 2610.20344 • Published 26 days ago • 45
OCR Collection by nhphong 25 days ago - baidu/Unlimited-OCR Image-Text-to-Text • 3B • Updated 25 days ago • 5.23M • 4.97k
Coding Collection by GrimHarvest 25 days ago - Paused Agents Featured 47 North Mini Code Demo 💻 47 Generate and run Python or web code from natural language prompts
Paused Agents Featured 47 North Mini Code Demo 💻 47 Generate and run Python or web code from natural language prompts
Qwen Collection by Dhamanoon 25 days ago - Qwen/Qwen3Guard-Stream-4B Feature Extraction • 4B • Updated Sep 27 • 1.01k • 39 Qwen/Qwen3.5-4B Image-Text-to-Text • 5B • Updated Mar 2 • 5.32M • • 1.21k
Skill Collection by JerroldH 25 days ago - SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models Paper • 2610.17727 • Published 26 days ago • 2
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models Paper • 2610.17727 • Published 26 days ago • 2
Reaper The Reaper model family: base, supervised fine-tuned, and final policy-value checkpoints. Collection by FrenzyMath 25 days ago - FrenzyMath/Reaper-1 Text Generation • Updated 25 days ago • 1 FrenzyMath/Reaper-SFT Text Generation • Updated 25 days ago FrenzyMath/Reaper-Base Text Generation • 2B • Updated 25 days ago • 710