StepFun

company

https://www.stepfun.com/

AI & ML interests

None defined yet.

Recent Activity

apohelios new activity 16 days ago

stepfun-ai/Step-3.7-Flash-GGUF:Some practical tips for using Step 3.7 GGUFs

bwang3579 authored a paper 20 days ago

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

huangyu-nv new activity 21 days ago

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

View all activity

Papers

ShutterMuse: Capture-Time Photography Guidance with MLLMs

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

View all Papers

in stepfun-ai/Step-3.7-Flash-GGUF 16 days ago

Some practical tips for using Step 3.7 GGUFs

#6 opened 29 days ago by

authored a paper 20 days ago

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

Paper • 2606.09669 • Published 21 days ago • 46

in stepfun-ai/Step-3.7-Flash-NVFP4 21 days ago

MTP-layer weights?

#1 opened about 1 month ago by

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

#4 opened 24 days ago by

in stepfun-ai/Step-3.7-Flash-NVFP4 24 days ago

What's the suggested model settings?

#3 opened 27 days ago by

updated a model 26 days ago

stepfun-ai/Step-3.7-Flash-GGUF

Image-Text-to-Text • 197B • Updated 26 days ago • 53.5k • 133

in stepfun-ai/Step-3.7-Flash 26 days ago

add cache_position to mask_kwargs in modeling_step3p7.py

#13 opened 26 days ago by

authored 3 papers 28 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 May 22 • 49

updated a model 28 days ago

stepfun-ai/Step-3.7-Flash-NVFP4

Image-Text-to-Text • 104B • Updated 28 days ago • 299k • 55

in stepfun-ai/Step-3.7-Flash-GGUF 28 days ago

Recommended settings

#2 opened about 1 month ago by

updated 3 models 28 days ago

stepfun-ai/Step-3.7-Flash-NVFP4

Image-Text-to-Text • 104B • Updated 28 days ago • 299k • 55

stepfun-ai/Step-3.7-Flash-FP8

Image-Text-to-Text • 201B • Updated 28 days ago • 41k • 16

stepfun-ai/Step-3.7-Flash

Image-Text-to-Text • 201B • Updated 26 days ago • 150k • • 395

in stepfun-ai/Step-3.7-Flash-dev 28 days ago

fix examples

#1 opened 29 days ago by

in stepfun-ai/Step-3.7-Flash-GGUF 29 days ago

how to prevent the model from reasoning

#1 opened about 1 month ago by

Could you please provide a visual model for version Q8?

#5 opened 29 days ago by

updated a collection 30 days ago

Step-3.7-Flash

6 items • Updated 30 days ago • 16

updated a Space 30 days ago

Step 3.7 Flash

Chat with an AI that explains its reasoning