|
--- |
|
license: apache-2.0 |
|
pipeline_tag: text-generation |
|
tags: |
|
- cortex.cpp |
|
--- |
|
## Overview |
|
|
|
**InternLM** developed and released the [InternLM3-8B-Instruct](https://huggingface.co/internlm/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 | [Internlm3-8b-it](https://huggingface.co/cortexso/internlm3-8b-it/tree/8b) | `cortex run internlm3-8b-it:8b` | |
|
|
|
## Use it with Jan (UI) |
|
|
|
1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart) |
|
2. Use in Jan model Hub: |
|
```bash |
|
cortexso/internlm3-8b-it |
|
``` |
|
|
|
## Use it with Cortex (CLI) |
|
|
|
1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart) |
|
2. Run the model with command: |
|
```bash |
|
cortex run internlm3-8b-it |
|
``` |
|
|
|
## Credits |
|
|
|
- **Author:** InternLM |
|
- **Converter:** [Homebrew](https://www.homebrew.ltd/) |
|
- **Original License:** [License](https://huggingface.co/internlm/internlm3-8b-instruct/blob/main/LICENSE.txt) |
|
- **Papers:** [InternLM2 Technical Report](https://arxiv.org/abs/2403.17297) |
