---
title: Intern-S2-Preview
description: Intern-S2-Preview is a 35B multimodal scientific foundation model from Shanghai AI Laboratory (InternLM), trained on hundreds of professional scientific tasks from pretraining to reinforcement learning, with agent abilities for scientific workflows and time-series input. A preview release; no paper yet.
tags:
- conversational
- custom_code
- eval-results
- image-text-to-text
- intern_s2_preview
- multimodal
- reasoning
- scientific-llm
license: apache-2.0
source_url: https://huggingface.co/internlm/Intern-S2-Preview
---

# Intern-S2-Preview

> **Mirrored metadata.** This card is reproduced on Atlas for discovery. The artifact itself is not hosted here — follow the source link for the files, and refer to the upstream licence for terms of use.

Intern-S2-Preview is a 35B multimodal scientific foundation model from Shanghai AI Laboratory (InternLM), trained on hundreds of professional scientific tasks from pretraining to reinforcement learning, with agent abilities for scientific workflows and time-series input. A preview release; no paper yet.

Upstream identifier: `internlm/Intern-S2-Preview`.

**Source:** https://huggingface.co/internlm/Intern-S2-Preview

**Licence:** apache-2.0

_This model is part of the Atlas demo catalogue. See the repository history for provenance._