Overview
InternLM developed and released the InternLM3-8B-Instruct, an 8-billion parameter instruction-tuned language model designed for general-purpose usage and advanced reasoning tasks. The model delivers state-of-the-art performance on reasoning and knowledge-intensive tasks, outperforming other models like Llama3.1-8B and Qwen2.5-7B. Trained on 4 trillion high-quality tokens, InternLM3 achieves exceptional efficiency, reducing training costs by over 75% compared to other models of similar scale.
The model features dual operational modes: a deep thinking mode for solving complex reasoning tasks through long chain-of-thought processes and a normal response mode for fluent and interactive user experiences. These capabilities make InternLM3-8B-Instruct ideal for applications in conversational AI, advanced reasoning, and general-purpose language understanding.
Variants
| No | Variant | Cortex CLI command |
|---|---|---|
| 1 | gguf | cortex run internlm3-8b-it |
Use it with Jan (UI)
- Install Jan using Quickstart
- Use in Jan model Hub:
cortexso/internlm3-8b-it
Use it with Cortex (CLI)
- Install Cortex using Quickstart
- Run the model with command:
cortex run internlm3-8b-it
Credits
- Author: InternLM
- Converter: Homebrew
- Original License: License
- Papers: InternLM2 Technical Report