A categorized index of public models and research components, with documented scope, dependencies, and release status.
Xu Lin PRO
gatilin
AI & ML interests
None yet
Recent Activity
updated a collection about 16 hours ago
ViT & Vision Encoders updated a model about 16 hours ago
gatilin/mistral-large-4-vision-encoder published a model about 17 hours ago
gatilin/mistral-large-4-vision-encoderOrganizations
Vision encoders, ViTs, and understanding-side projectors. Component scope and incomplete architecture documentation are noted per model.
-
gatilin/deepseek_vit_412m.deepseek_v4_1_flash
Image Feature Extraction • 0.4B • Updated • 61 -
gatilin/deepseek_vit_412m.deepseek_v4_1_flash_1017
Image Feature Extraction • 0.4B • Updated • 151 • 2 -
gatilin/deepseek_vit_412m.deepseek_v4_flash_vision_exp
Image Feature Extraction • 0.4B • Updated • 58 -
gatilin/glm5_3_flash_vision
Image Feature Extraction • 0.6B • Updated • 31
A categorized index of public models and research components, with documented scope, dependencies, and release status.
Vision encoders, ViTs, and understanding-side projectors. Component scope and incomplete architecture documentation are noted per model.
-
gatilin/deepseek_vit_412m.deepseek_v4_1_flash
Image Feature Extraction • 0.4B • Updated • 61 -
gatilin/deepseek_vit_412m.deepseek_v4_1_flash_1017
Image Feature Extraction • 0.4B • Updated • 151 • 2 -
gatilin/deepseek_vit_412m.deepseek_v4_flash_vision_exp
Image Feature Extraction • 0.4B • Updated • 58 -
gatilin/glm5_3_flash_vision
Image Feature Extraction • 0.6B • Updated • 31
spaces 32
Runtime error
Agents
Youtu-VL-4B Multi-Task Demo
👁
Youtu-VL-4B — 14 vision tasks with visualization
Sleeping
Agents
4
YOLO Master WebUI Demo
🚀
Detect objects in images with smart AI assistance
Running
1
FlorenceForge Agentic Visual Reasoning
🎨
Analyze images with multi-step AI reasoning or specific vision tasks
Sleeping
nanoVLM-222M Web UI
🧠
Ask questions about any image and get instant answers
Sleeping
Agents
NanoVLM SmolLM2 Dinov2
😻
Generate answers to visual questions from uploaded images
Sleeping
Agents
NanoVLM SmolLM2 Sglip2
🌖
Generate answers to questions about uploaded images
models 156
gatilin/Youtu-LLM-A7B-Base-GGUF
Image-Text-to-Text • 118B • Updated • 280
gatilin/mistral-large-4-vision-encoder
Image Feature Extraction • 2B • Updated
gatilin/llama.cpp-youtu-moe
Updated
gatilin/ovb-e2b_cap10k_s42_10000_merged1
Text-to-Image • Updated • 66
gatilin/ovb-e2b_cap10k_s42_10000_merged2
Updated
gatilin/internvlu_image_dit
2B • Updated • 26
gatilin/ming_flash_omni2_audio_dit
0.1B • Updated • 24
gatilin/deepgen_1_0_sd3_dit
Updated
gatilin/unispace_pr_dinov2_visual_tokenizer
Updated • 38
gatilin/unispace_pr_dinov2_class_conditional_dit
Updated • 35
datasets 9
gatilin/LocateAnything-Data-ShareGPT-Annotation
Preview • Updated • 289
gatilin/argus-visual-decision
Viewer • Updated • 16k • 204
gatilin/open-vision-banana-snvc-train-full
Viewer • Updated • 35k • 874
gatilin/SenseNova-Vision-Corpus-50M-annotation
Viewer • Updated • 34.5M • 339
gatilin/SparkLM-seed-dataset
Updated • 13
gatilin/deepseek-mini-pretrain-datasets
Updated • 193
gatilin/wenwu_datasets_mnbvc
Viewer • Updated • 492k • 494
gatilin/rf100-vl
Viewer • Updated • 34k • 1.68k • 1
gatilin/rf100-vl-datasets
Viewer • Updated • 41.9k • 2.04k • 2