StepFun

company

https://www.stepfun.com/

AI & ML interests

None defined yet.

Recent Activity

bwang3579 authored a paper about 22 hours ago

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

huangyu-nv new activity 2 days ago

stepfun-ai/Step-3.7-Flash-NVFP4:MTP-layer weights?

huangyu-nv new activity 2 days ago

stepfun-ai/Step-3.7-Flash-NVFP4:RuntimeError: The size of tensor a (2048) must match the size of tensor b (4096) at non-singleton dimension 1

View all activity

Papers

Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation

Step-Audio-R1.5 Technical Report

View all Papers

authored a paper about 22 hours ago

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

Paper • 2606.09669 • Published 2 days ago • 38

in stepfun-ai/Step-3.7-Flash-NVFP4 2 days ago

MTP-layer weights?

#1 opened 12 days ago by

RuntimeError: The size of tensor a (2048) must match the size of tensor b (4096) at non-singleton dimension 1

#4 opened 5 days ago by

in stepfun-ai/Step-3.7-Flash-NVFP4 5 days ago

What's the suggested model settings?

#3 opened 8 days ago by

updated a model 7 days ago

stepfun-ai/Step-3.7-Flash-GGUF

Image-Text-to-Text • 197B • Updated 7 days ago • 56.4k • 113

in stepfun-ai/Step-3.7-Flash 7 days ago

add cache_position to mask_kwargs in modeling_step3p7.py

#13 opened 7 days ago by

authored 3 papers 9 days ago

Step-Audio-R1.5 Technical Report

Paper • 2604.25719 • Published Apr 28 • 15

Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability

Paper • 2601.22661 • Published Jan 30

StepAudio 2.5 Technical Report

Paper • 2605.23463 • Published 19 days ago • 49

updated a model 9 days ago

stepfun-ai/Step-3.7-Flash-NVFP4

Image-Text-to-Text • 104B • Updated 9 days ago • 199k • 46

in stepfun-ai/Step-3.7-Flash-GGUF 9 days ago

Recommended settings

#2 opened 12 days ago by

updated 3 models 9 days ago

stepfun-ai/Step-3.7-Flash-NVFP4

Image-Text-to-Text • 104B • Updated 9 days ago • 199k • 46

stepfun-ai/Step-3.7-Flash-FP8

Image-Text-to-Text • 201B • Updated 9 days ago • 34k • 14

stepfun-ai/Step-3.7-Flash

Image-Text-to-Text • 201B • Updated 7 days ago • 46.7k • • 362

in stepfun-ai/Step-3.7-Flash-dev 9 days ago

fix examples

#1 opened 10 days ago by

in stepfun-ai/Step-3.7-Flash-GGUF 10 days ago

how to prevent the model from reasoning

#1 opened 12 days ago by

Could you please provide a visual model for version Q8?

#5 opened 10 days ago by

updated a collection 11 days ago

Step-3.7-Flash

6 items • Updated 11 days ago • 16

updated a Space 11 days ago

Step 3.7 Flash

Chat with an AI that explains its reasoning

in stepfun-ai/Step-3.7-Flash-GGUF 11 days ago

Add IQ3 for 96Gb VRAM

#4 opened 12 days ago by