40 lines
1.3 KiB
Markdown
40 lines
1.3 KiB
Markdown
|
---
|
||
|
|
license: other
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- cortex.cpp
|
||
|
|
---
|
||
|
|
|
||
|
|
## Overview
|
||
|
|
|
||
|
|
Intellect-1 is a high-performance instruction-tuned model developed by Qwen, designed to handle a broad range of natural language processing tasks with efficiency and precision. Optimized for dialogue, reasoning, and knowledge-intensive applications, Intellect-1 excels in structured generation, summarization, and retrieval-augmented tasks. It is part of an open ecosystem, providing transparency in training data, model architecture, and fine-tuning methodologies.
|
||
|
|
|
||
|
|
|
||
|
|
## Variants
|
||
|
|
|
||
|
|
| No | Variant | Cortex CLI command |
|
||
|
|
| --- | --- | --- |
|
||
|
|
| 1 | [Intellect-1-10b](https://huggingface.co/cortexso/intellect-1/tree/10b) | `cortex run intellect-1:10b` |
|
||
|
|
|
||
|
|
## Use it with Jan (UI)
|
||
|
|
|
||
|
|
1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
|
||
|
|
2. Use in Jan model Hub:
|
||
|
|
```bash
|
||
|
|
cortexhub/intellect-1
|
||
|
|
```
|
||
|
|
|
||
|
|
## 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 intellect-1
|
||
|
|
```
|
||
|
|
|
||
|
|
## Credits
|
||
|
|
|
||
|
|
- **Author:** Qwen
|
||
|
|
- **Converter:** [Homebrew](https://homebrew.ltd/)
|
||
|
|
- **Original License:** [Licence](https://choosealicense.com/licenses/apache-2.0/)
|
||
|
|
- **Papers:** [Technical Paper](https://github.com/PrimeIntellect-ai/prime)
|