Hugging Face's logo

stepfun-ai
/
Step-3.5-Flash

Text Generation
Transformers
Safetensors
step3p5
conversational
custom_code
Eval Results
Model card Files
xet
Community
29
WinstonDeng commited on
Commit
14cd490
·
verified ·
1 Parent(s): 06ab720

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -23,8 +23,11 @@ library_name: transformers
23
  [![License](https://img.shields.io/badge/License-Apache%202.0-green)]()
24
  [![Chat with the model on OpenRouter](https://img.shields.io/badge/Chat%20with%20the%20model-OpenRouter-5B3DF5?logo=chatbot&logoColor=white)](https://openrouter.ai/chat?models=stepfun/step-3.5-flash:free)
25
 
 
26
  </div>
27
 
 
 
28
  ## 1. Introduction
29
 
30
  **Step 3.5 Flash** ([visit website](https://static.stepfun.com/blog/step-3.5-flash/)) is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. This "intelligence density" allows it to rival the reasoning depth of top-tier proprietary models, while maintaining the agility required for real-time interaction.
 
23
  [![License](https://img.shields.io/badge/License-Apache%202.0-green)]()
24
  [![Chat with the model on OpenRouter](https://img.shields.io/badge/Chat%20with%20the%20model-OpenRouter-5B3DF5?logo=chatbot&logoColor=white)](https://openrouter.ai/chat?models=stepfun/step-3.5-flash:free)
25
 
26
+ **Quick chat in [Huggingface Space](https://huggingface.co/spaces/stepfun-ai/Step-3.5-Flash)**
27
  </div>
28
 
29
+
30
+
31
  ## 1. Introduction
32
 
33
  **Step 3.5 Flash** ([visit website](https://static.stepfun.com/blog/step-3.5-flash/)) is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. This "intelligence density" allows it to rival the reasoning depth of top-tier proprietary models, while maintaining the agility required for real-time interaction.