1 Collection by FUX1AO Sep 1 - Anzhc/Anzhcs_YOLOs Object Detection • Updated Feb 25 • 66.8k • 187 Momoking/Qwen3-VL-32B-Heretic-MiniMax-H3-NVFP4 Updated Aug 7 • 384
interview-transkription Collection by RealOrcinus Aug 31 - pyannote/speaker-diarization-3.1 Automatic Speech Recognition • Updated May 10, 2024 • 6.88M • 4.99k pyannote/segmentation-3.0 Voice Activity Detection • Updated May 10, 2024 • 5.12M • 2.58k
pyannote/speaker-diarization-3.1 Automatic Speech Recognition • Updated May 10, 2024 • 6.88M • 4.99k
GLM-5.3 Collection by jonathan60028 Aug 31 - jonathan60028/GLM-5.3-UNCENSORED-FP8 Text Generation • 753B • Updated Aug 31 • 32 • 2
pixcell dataset and model for arXiv 2608.00084 : From Pixels to PCells: A Neurosymbolic Approach to Photonic Component Creation Collection by aadarwal Aug 31 - qpaig-mit/pixcell Image-Text-to-Text • Updated Aug 4 • 13
GLM REAP Expert-Pruned Models Runtime-qualified FP8 GLM derivatives pruned with REAP from 256 to 224 routed experts. Collection by destr8803 Sep 1 - destr8803/GLM-5.2-224E-FP8-REAP Text Generation • 662B • Updated Aug 25 • 51 • 1
video Collection by budots Sep 7 - Running on A100 Agents 13 Nemotron-Labs-Audio-Visual Flamingo 🎬 13 Analyze video content with audio‑visual AI and get text answers
Running on A100 Agents 13 Nemotron-Labs-Audio-Visual Flamingo 🎬 13 Analyze video content with audio‑visual AI and get text answers
Gemma-4-26B KIID seed replicate — eval noise floor gemma-4-26B-A4B on kiid_finance — sweep-3 F1 (QLoRA r16, clip 1.0) trained N=3 varying only the seed, evaluated identically Collection by L1nus Sep 1 -
OldAI Collection by FedoruFoku Aug 31 - Running 5.75k DALL·E mini 🥑 5.75k Generate images from any text prompt
1 Collection by FUX1AO Sep 1 - Anzhc/Anzhcs_YOLOs Object Detection • Updated Feb 25 • 66.8k • 187 Momoking/Qwen3-VL-32B-Heretic-MiniMax-H3-NVFP4 Updated Aug 7 • 384
video Collection by budots Sep 7 - Running on A100 Agents 13 Nemotron-Labs-Audio-Visual Flamingo 🎬 13 Analyze video content with audio‑visual AI and get text answers
Running on A100 Agents 13 Nemotron-Labs-Audio-Visual Flamingo 🎬 13 Analyze video content with audio‑visual AI and get text answers
interview-transkription Collection by RealOrcinus Aug 31 - pyannote/speaker-diarization-3.1 Automatic Speech Recognition • Updated May 10, 2024 • 6.88M • 4.99k pyannote/segmentation-3.0 Voice Activity Detection • Updated May 10, 2024 • 5.12M • 2.58k
pyannote/speaker-diarization-3.1 Automatic Speech Recognition • Updated May 10, 2024 • 6.88M • 4.99k
Gemma-4-26B KIID seed replicate — eval noise floor gemma-4-26B-A4B on kiid_finance — sweep-3 F1 (QLoRA r16, clip 1.0) trained N=3 varying only the seed, evaluated identically Collection by L1nus Sep 1 -
GLM-5.3 Collection by jonathan60028 Aug 31 - jonathan60028/GLM-5.3-UNCENSORED-FP8 Text Generation • 753B • Updated Aug 31 • 32 • 2
pixcell dataset and model for arXiv 2608.00084 : From Pixels to PCells: A Neurosymbolic Approach to Photonic Component Creation Collection by aadarwal Aug 31 - qpaig-mit/pixcell Image-Text-to-Text • Updated Aug 4 • 13
OldAI Collection by FedoruFoku Aug 31 - Running 5.75k DALL·E mini 🥑 5.75k Generate images from any text prompt
GLM REAP Expert-Pruned Models Runtime-qualified FP8 GLM derivatives pruned with REAP from 256 to 224 routed experts. Collection by destr8803 Sep 1 - destr8803/GLM-5.2-224E-FP8-REAP Text Generation • 662B • Updated Aug 25 • 51 • 1
Sep 1 
