InternLM 2.5

Name: InternLM 2.5
Author: Shanghai AI Laboratory

Shanghai AI LaboratoryOpen WeightsPending Human Review

InternLM 2.5 is Shanghai AI Laboratory’s language model release for multilingual conversation, reasoning, and local customization. The reasoning and long-context generation introduces 7B weights followed by 1.8B and 20B checkpoints; the 1M context is available on the explicitly extended 7B version. Official weights and deployment examples support reproducible research and private deployment. This page represents the named generation rather than creating duplicate entries for base, chat, and quantized packages. Chinese and English capabilities are emphasized. A large advertised context does not establish reliable retrieval or reasoning throughout every input length.

2024-07-03

1.8B, 7B, 20B

Dense decoder-only Transformer

InternLM Model License

Compare with other models

Specifications

Parameters: 1.8B, 7B, 20B
Architecture: Dense decoder-only Transformer
License: InternLM Model License
Context Window: 1,000,000 tokens
Type: text
Modalities: text

Benchmark Scores

Advanced Specifications

Model Family: InternLM
API Access: Not Available
Chat Interface: Not Available
Multilingual Support: Yes

Capabilities & Limitations

Capabilities: reasoningmultilingual conversationlocal fine-tuningtool calling
Known Limitations: Generated claims require verificationExtended context applies to specific checkpointsDeployment requires model-compatible inference tooling
Notable Use Cases: private assistantsChinese and English applicationslanguage research

Resources

Related Models

AstaBrief

Allen Institute for AI

AstaBrief is Ai2’s 8B scientific report-generation model, trained from Qwen3-8B with citation-focused supervised fine-tuning and direct preference optimization. It turns a research question and retrieved literature excerpts into a complete cited report in a single pass, and powers Asta’s Fast report mode. Ai2 releases the weights, training data, and a workflow for using local PDFs. The reported latency advantage evaluates the complete report pipeline rather than the checkpoint alone. Citation grounding is improved but does not guarantee that a synthesis preserves every study’s scope or conclusions.

Atria Dawn Preview

Shanghai AI Laboratory

Atria Dawn Preview is Shanghai AI Laboratory’s agentic model for turning research and engineering questions into executable results. Built on GLM-5.2’s 744B mixture-of-experts foundation, it is post-trained for discovery, code creation, office deliverables, and cybersecurity tasks in authorized environments. The released text-only checkpoint supports a documented 256K inference context, downloadable MIT-licensed weights, and hosted API access. It combines tool execution with environmental feedback for experiment design, failure recovery, and verification. Configuration maximums above the documented serving limit are not treated as evidence of a larger supported context.

Intern S2 397B

Shanghai AI Laboratory

Intern S2 is the stable scientific multimodal follow-up to the 397B preview checkpoint. It strengthens extended agent execution and research workflows, with deep-thinking and ordinary-response modes. Public API documentation identifies the stable model separately and schedules preview decommissioning for October 31. The release includes downloadable Apache-licensed weights and chat access. The official laboratory announcement identifies the public release date as 2026-09-13.