Faster Text Generation with Self-Speculative Decoding
•
58
AI & ML interests
None defined yet.
Recent Activity
Articles
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 12.3k • 130 -
facebook/vjepa2-vith-fpc64-256
Video Classification • 0.7B • Updated • 683 • 12 -
facebook/vjepa2-vitg-fpc64-256
Video Classification • 1B • Updated • 10.3k • 12 -
facebook/vjepa2-vitg-fpc64-384
Video Classification • 1B • Updated • 5.18k • 23
-
facebook/webssl-dino300m-full2b-224
Image Feature Extraction • 0.3B • Updated • 2.44k • 9 -
facebook/webssl-dino1b-full2b-224
Image Feature Extraction • 1B • Updated • 1.38k • 1 -
facebook/webssl-dino2b-full2b-224
Image Feature Extraction • 2B • Updated • 101 -
facebook/webssl-dino3b-full2b-224
Image Feature Extraction • 3B • Updated • 334
A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 12.3k • 130 -
facebook/vjepa2-vith-fpc64-256
Video Classification • 0.7B • Updated • 683 • 12 -
facebook/vjepa2-vitg-fpc64-256
Video Classification • 1B • Updated • 10.3k • 12 -
facebook/vjepa2-vitg-fpc64-384
Video Classification • 1B • Updated • 5.18k • 23
-
facebook/webssl-dino300m-full2b-224
Image Feature Extraction • 0.3B • Updated • 2.44k • 9 -
facebook/webssl-dino1b-full2b-224
Image Feature Extraction • 1B • Updated • 1.38k • 1 -
facebook/webssl-dino2b-full2b-224
Image Feature Extraction • 2B • Updated • 101 -
facebook/webssl-dino3b-full2b-224
Image Feature Extraction • 3B • Updated • 334
spaces
39
pinned
Running
on
Zero
103
MelodyFlow
🎵
Generate music from text and melody
pinned
Running
on
Zero
268
CoTracker
🎨
Track points in a video
pinned
Running
on
A10G
5k
MusicGen
🎵
Generate music from text descriptions
Running
Omniseal Leaderboard
🦀
Leaderboard for watermarking models
Running
14
Leaderboard: Physical Reasoning from Video
🏃
Submit and score model predictions for video and text tasks
Running
11
Bouquet
🔥
Universal Quality Evaluation in Translation
models
2,167
facebook/test-astro
Updated
facebook/KernelLLM
Text Generation
•
8B
•
Updated
•
8.73k
•
•
161
facebook/Perception-LM-8B
Image-Text-to-Text
•
Updated
•
120
•
51
facebook/Perception-LM-3B
Image-Text-to-Text
•
Updated
•
198
•
17
facebook/Perception-LM-1B
Image-Text-to-Text
•
Updated
•
225
•
30
facebook/OMol25
Updated
•
128
facebook/UMA
Updated
•
93
facebook/vjepa2-vitg-fpc64-384
Video Classification
•
1B
•
Updated
•
5.18k
•
23
facebook/vjepa2-vitg-fpc64-256
Video Classification
•
1B
•
Updated
•
10.3k
•
12
facebook/vjepa2-vith-fpc64-256
Video Classification
•
0.7B
•
Updated
•
683
•
12
datasets
70
facebook/seamless-interaction
Updated
•
1
•
18
facebook/bouquet
Viewer
•
Updated
•
25.9k
•
33
•
1
facebook/IntPhys2
Viewer
•
Updated
•
1.07k
•
854
•
9
facebook/minimal_video_pairs
Viewer
•
Updated
•
73.2k
•
467
•
4
facebook/PLM-VideoBench
Viewer
•
Updated
•
44k
•
856
•
9
facebook/PLM-Video-Human
Viewer
•
Updated
•
2.8M
•
1.04k
•
23
facebook/TAPAS
Updated
•
84
•
2
facebook/multiloko
Viewer
•
Updated
•
67.3k
•
203
•
1
facebook/Wildchat-RIP-Filtered-by-8b-Llama
Viewer
•
Updated
•
24.3k
•
56
•
2
facebook/llamafirewall-alignmentcheck-evals
Viewer
•
Updated
•
3.46k
•
133