InternLM 2.5
Shanghai AI LaboratoryShanghai AI Lab's open-weights model family. The InternLM 2.5 generation at 7B and 20B reaches a one-million-token context through dynamic NTK interpolation. It was superseded by InternLM3 in January 2025, an 8B model trained on four trillion tokens with an integrated deep-thinking chain-of-thought mode.
Scores the InternLM2.5-7B base; the Chat release is a separate finetuned_chat record. The code and weights carry different terms and the compound resolves on the weights half. Verified 2026-08-13 via the model card and the InternLM repository.
Openness
3 medium confidence- weights
- open(custom 'Free Commercial License', academic free, commercial use free but requires an application form)
- data
- closed(pretraining corpus not released)
- code
- open(Apache-2.0 training/inference code on GitHub)
- license
- Apache-2.0(code, OSI) + custom weights license(non-OSI, application step)
The training and inference code is Apache-2.0, but the weights ship under a custom, non-OSI 'Free Commercial License': free for academic work and free for commercial use, but only once an application form has been approved. That application step on the weights, together with a pretraining corpus that is not released, is what keeps this at open weights rather than open source.
- https://huggingface.co/internlm/internlm2_5-7b recorded 2026-08-13
model card - "The code is licensed under Apache-2.0, while model weights are fully open for academic research and also allow free commercial usage. To apply for a commercial license, please fill in the application form"; no pretraining corpus named.
- https://api.github.com/repos/InternLM/InternLM recorded 2026-08-13
`private: false`, `archived: false`, license `Apache-2.0`, 7,264 stars, description "Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3)".
Adoption
1 medium confidence3,095 downloads in the trailing 30 days for the single declared artifact internlm/internlm2_5-7b, which bands at level 1 (<10K) on the model adoption scale.
- https://huggingface.co/api/models/internlm/internlm2_5-7b recorded 2026-08-13
3,095 downloads in the trailing 30 days for internlm/internlm2_5-7b
Capability
2 medium confidenceA strong sub-8B model for 2024, with a 1M-token context, but well below the 2026 frontier: InternLM2.5-7B base scores MMLU 71.6 (5-shot, OpenCompass), matching Yi-1.5-9B and beating Llama-3-8B at 66.4. That puts it beside Falcon 3 and Yi-1.5 on the dated small-model ladder, which both also score 2.
- https://huggingface.co/internlm/internlm2_5-7b recorded 2026-08-13
OpenCompass benchmark table - InternLM2.5-7B MMLU 71.6, against InternLM2-7B 65.8, LLaMA3-8B 66.4 and Yi-1.5-9B 71.6.
- https://raw.githubusercontent.com/InternLM/InternLM/main/model_cards/internlm2.5_7b.md recorded 2026-08-13
InternLM2.5-7B base model card, MMLU 71.6 (OpenCompass). Cited previously as a github.com blob URL; the raw form is what the fetcher reads and what the digest is taken over.
Verified 2026-08-13