🥳Introducing Intern-S2-Preview, an efficient 35B scientific multimodal foundation model.
1⃣Delivers performance comparable to the trillion-scale Intern-S1-Pro on core scientific tasks.
2⃣The first open-source model with material crystal structure generation capabilities and strong general capabilities.
3⃣Significantly stronger scientific agent capabilities on multiple benchmarks.
4⃣Improves MTP acceptance rate and token generation speed via shared-weight MTP + KL loss.
5⃣CoT compression shortens responses while preserving strong reasoning , improving both performance and efficiency.
🥰Now supported by vLLM (@vllm_project) and SGLang ( @lmsysorg ) — with more ecosystem integrations on the way.
🤗Model：
@huggingface
https://huggingface.co/collections/internlm/intern-s2
@ModelScope2022
https://modelscope.cn/collections/Shanghai_AI_Laboratory/Intern-S2
🤗GitHub:
https://github.com/InternLM/Intern-S1
🤗Try it now at:
https://chat.intern-ai.org.cn
Intern-S2-Preview: 35B Open Scientific Multimodal Model Released
AISummary
Shanghai AI Laboratory's Intern Large Models introduces Intern-S2-Preview, a 35B scientific multimodal foundation model, and says it matches the trillion-scale Intern-S1-Pro on core scientific tasks.
The post says it is the first open-source model with material crystal structure generation and strong general capabilities, with shared-weight MTP plus KL loss improving acceptance rate and speed.
It is already supported by vLLM and SGLang, with weights on Hugging Face and ModelScope.
Post on XView on X
@intern_lm
Source: Intern Large Models · x.comPublished · added here