Agents I've Created!
Hunter Gill PRO
hmgill
·
AI & ML interests
None yet
Recent Activity
updated a Space about 1 month ago
hmgill/Matrix-Fossil-Agent liked a dataset about 2 months ago
MahmoodLab/hest liked a model about 2 months ago
nvidia/NV-Segment-CTMROrganizations
OCR
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 7.73k • 1.66k -
allenai/olmOCR-2-7B-1025-FP8
Image-Text-to-Text • 8B • Updated • 104k • 257 -
lightonai/LightOnOCR-2-1B
Image-Text-to-Text • 1B • Updated • 228k • • 834 -
ibm-granite/granite-4.0-3b-vision
Image-Text-to-Text • 4B • Updated • 37.2k • 111
LLMs, VLMs, Models
Background Removal
Safety Models
Models for evaluating user inputs and model outputs
Very Cool
- RunningFeatured163
Granite Docling 258M WebGPU
🐣163Convert document images to HTML with a single click
-
microsoft/TRELLIS.2-4B
Image-to-3D • Updated • 1.83M • 1.29k - Running on ZeroAgentsFeatured117
SAM3 Video Segmentation
🐠117Track and label objects in videos using text prompts or clicks
- Running on ZeroAgents15
SAM3
🔥15All the powerful features of the SAM 3 model!
My Agents
Agents I've Created!
Background Removal
OCR
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 7.73k • 1.66k -
allenai/olmOCR-2-7B-1025-FP8
Image-Text-to-Text • 8B • Updated • 104k • 257 -
lightonai/LightOnOCR-2-1B
Image-Text-to-Text • 1B • Updated • 228k • • 834 -
ibm-granite/granite-4.0-3b-vision
Image-Text-to-Text • 4B • Updated • 37.2k • 111
Safety Models
Models for evaluating user inputs and model outputs
LLMs, VLMs, Models
Very Cool
- RunningFeatured163
Granite Docling 258M WebGPU
🐣163Convert document images to HTML with a single click
-
microsoft/TRELLIS.2-4B
Image-to-3D • Updated • 1.83M • 1.29k - Running on ZeroAgentsFeatured117
SAM3 Video Segmentation
🐠117Track and label objects in videos using text prompts or clicks
- Running on ZeroAgents15
SAM3
🔥15All the powerful features of the SAM 3 model!