InternLM/InternLM

Health v2 · maintenance only

Adoption not part of the score

7269 stars · 509 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Official repository for the InternLM series of open-source large language models (InternLM, InternLM2, InternLM2.5, InternLM3), including pretrained and chat-tuned weights and training tooling. InternLM3-8B-Instruct targets general-purpose use and advanced reasoning with deep-thinking chain-of-thought mode.

Use cases

• download and run an open-source 8B chat LLM locally
• fine-tune a large language model with RLHF
• run a bilingual Chinese-English instruction model
• evaluate reasoning-capable open LLMs against Llama or Qwen
• self-host a chatbot backed by an open-weights model
• train an LLM with long-context support and flash attention

When to choose

• you need open-weights LLMs with strong Chinese-language capability
• you want to fine-tune or do RLHF on a permissively licensed (Apache-2.0) model
• you need a small-to-mid size model with deep reasoning / chain-of-thought modes

When to avoid

• you only need an inference server for third-party models rather than model weights and training code
• you need the largest frontier-scale models
• you lack GPU hardware for training or local inference

Facets

library · maturity active

llm-training llm-inference machine-learning deep-learning large-language-models artificial-intelligence python chatbot rlhf fine-tuning long-context flash-attention chinese pretrained-models open-weights natural-language-processing gpu linux docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="InternLM/InternLM")