|
--- |
|
license: other |
|
--- |
|
|
|
## Overview |
|
|
|
Mistral 7B, a 7-billion-parameter Large Language Model by Mistral AI. Designed for efficiency and performance, it suits real-time applications requiring swift responses. |
|
|
|
## Variants |
|
|
|
| No | Variant | Cortex CLI command | |
|
| --- | --- | --- | |
|
| 1 | [7b-gguf](https://huggingface.co/cortexhub/mistral/tree/7b-gguf) | `cortex run mistral:7b-gguf` | |
|
| 2 | [tensorrt-llm](https://huggingface.co/cortexso/mistral/tree/tensorrt-llm-windows-ada) | `cortex run mistral:tensorrt-llm` | |
|
| 3 | [7b-onnx](https://huggingface.co/cortexso/mistral/tree/7b-onnx) | `cortex run mistral:7b-onnx` | |
|
| 4 | [7b-v0.3](https://huggingface.co/cortexso/mistral/tree/7b-v0.3-gguf-q4-km) | `cortex run mistral:7b-v0.3-gguf-q4-km` | |
|
| 4 | [7b-small](https://huggingface.co/cortexso/mistral/tree/small-gguf-q4-km) | `cortex run mistral:small-gguf-q4-km | |
|
|
|
## Use it with Jan (UI) |
|
|
|
1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart) |
|
2. Use in Jan model Hub: |
|
``` |
|
cortexhub/mistral |
|
``` |
|
|
|
## Use it with Cortex (CLI) |
|
|
|
1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart) |
|
2. Run the model with command: |
|
``` |
|
cortex run mistral |
|
``` |
|
|
|
## Credits |
|
|
|
- **Author:** MistralAI |
|
- **Converter:** [Homebrew](https://www.homebrew.ltd/) |
|
- **Original License:** [Licence]((https://mistral.ai/licenses/MNPL-0.1.md)) |
|
- **Papers:** [Mistral paper](https://arxiv.org/abs/2310.06825) |
