Multimodal model

Intern S1

Intern-S1 is a scientific multimodal foundation model built on a 235B-parameter Qwen3 MoE LLM plus a 6B vision encoder, trained on 5T multimodal tokens with over half from scientific domains.

Type
Multimodal
Weights
Open
Downloads
26k
Likes
258
Pipeline
image text to text
License
apache-2.0

Model hub

internlm/Intern-S1

Repo
internlm/Intern-S1
Library
transformers
Access
Public
Technical tags and languages
transformers safetensors interns1 text-generation image-text-to-text conversational custom_code eval-results
Open on Hugging Face

Papers

1

More from InternLM

3

About InternLM

1

Welcome to the InternLM (Intern Large Models) organization. Intern-series large models (chinese name: 书生) are developed by Shanghai AI Laboratory and we keep open-sourcing high quality LLMs/MLLMs as well as toolchains for development and application.