Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

Learning to Read Out (NeurIPS 2026)

Paper, readout dictionaries, controlled pretraining runs, W_U snapshots and an interactive feature atlas.

Learning to Read Out: Unembedding Dynamics in Language Model Pretraining

Paper • 2610.21025 • Published 10 days ago • 10
Running

Readout Feature Atlas

📖

Browse readout features across Pythia pretraining
hematteo/parameter-trajectory-crosscoders

Other • Updated 6 days ago
hematteo/readout-recipe-control

Text Generation • Updated 6 days ago

Psrsonalization

Explaining the Roles of Experts in Mixture-of-Experts LLMs for Personalization

Paper • 2610.22127 • Published 9 days ago • 5

Speculative decoding artifacts for Lissa1: the target checkpoint and experimental DFlash drafter.

lomelidev/Lissa1-4B

Text Generation • 4B • Updated 6 days ago • 48
lomelidev/Lissa1-4B-DFlash

Text Generation • 0.5B • Updated 6 days ago • 36

Small Edge-Large Cloud Optimizations

EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation

Paper • 2610.17560 • Published 11 days ago • 30

Nemotron 3.5 Bolt for oMLX

NVIDIA Nemotron 3.5 Bolt, unchanged, with MLX model files for oMLX and mlx-vlm. Vision included. LiLiCorr version: speculative decoding in oMLX.

txgsync/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-MLX

Image-Text-to-Text • 23B • Updated 7 days ago • 404
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB

Image-Text-to-Text • 22B • Updated 3 days ago • 8.38k • 152
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16

Image-Text-to-Text • 75B • Updated about 4 hours ago • 3.82k • 46
txgsync/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr-MLX

Image-Text-to-Text • 23B • Updated 7 days ago • 321

TencentARC/Pixal3D

TencentARC/Pixal3D

Image-to-3D • Updated Aug 31 • 381

FDE-Gym: The Last Mile of AI Delivery

Paper • 2610.22350 • Published 9 days ago • 78

Lissa1 model family: the reference Transformers checkpoint and verified inference formats.

lomelidev/Lissa1-4B

Text Generation • 4B • Updated 6 days ago • 48
lomelidev/Lissa1-4B-FP8

Text Generation • 4B • Updated 6 days ago • 35
lomelidev/Lissa1-4B-AWQ

Text Generation • 4B • Updated 6 days ago • 36
lomelidev/Lissa1-4B-GGUF

Text Generation • 4B • Updated 6 days ago • 402

3D Code Interop

3DCodeVerse: Exploring 3D Worlds as Code

Paper • 2610.22341 • Published 9 days ago • 67

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 9 days ago • 2.28M • 4.88k

Learning to Read Out (NeurIPS 2026)

Paper, readout dictionaries, controlled pretraining runs, W_U snapshots and an interactive feature atlas.

Learning to Read Out: Unembedding Dynamics in Language Model Pretraining

Paper • 2610.21025 • Published 10 days ago • 10
Running

Readout Feature Atlas

📖

Browse readout features across Pythia pretraining
hematteo/parameter-trajectory-crosscoders

Other • Updated 6 days ago
hematteo/readout-recipe-control

Text Generation • Updated 6 days ago

TencentARC/Pixal3D

TencentARC/Pixal3D

Image-to-3D • Updated Aug 31 • 381

Psrsonalization

Explaining the Roles of Experts in Mixture-of-Experts LLMs for Personalization

Paper • 2610.22127 • Published 9 days ago • 5

FDE-Gym: The Last Mile of AI Delivery

Paper • 2610.22350 • Published 9 days ago • 78

Speculative decoding artifacts for Lissa1: the target checkpoint and experimental DFlash drafter.

lomelidev/Lissa1-4B

Text Generation • 4B • Updated 6 days ago • 48
lomelidev/Lissa1-4B-DFlash

Text Generation • 0.5B • Updated 6 days ago • 36

Lissa1 model family: the reference Transformers checkpoint and verified inference formats.

lomelidev/Lissa1-4B

Text Generation • 4B • Updated 6 days ago • 48
lomelidev/Lissa1-4B-FP8

Text Generation • 4B • Updated 6 days ago • 35
lomelidev/Lissa1-4B-AWQ

Text Generation • 4B • Updated 6 days ago • 36
lomelidev/Lissa1-4B-GGUF

Text Generation • 4B • Updated 6 days ago • 402

Small Edge-Large Cloud Optimizations

EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation

Paper • 2610.17560 • Published 11 days ago • 30

3D Code Interop

3DCodeVerse: Exploring 3D Worlds as Code

Paper • 2610.22341 • Published 9 days ago • 67

Nemotron 3.5 Bolt for oMLX

NVIDIA Nemotron 3.5 Bolt, unchanged, with MLX model files for oMLX and mlx-vlm. Vision included. LiLiCorr version: speculative decoding in oMLX.

txgsync/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-MLX

Image-Text-to-Text • 23B • Updated 7 days ago • 404
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB

Image-Text-to-Text • 22B • Updated 3 days ago • 8.38k • 152
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16

Image-Text-to-Text • 75B • Updated about 4 hours ago • 3.82k • 46
txgsync/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr-MLX

Image-Text-to-Text • 23B • Updated 7 days ago • 321

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 9 days ago • 2.28M • 4.88k

Previous
1
...
260
261
262
263
264
...
24,230
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs