prabodbc's picture
Upload README.md with huggingface_hub
4943a41 verified
|
Raw
History Blame Contribute Delete
836 Bytes
---
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.3
library_name: basert
pipeline_tag: text-generation
tags:
- basert
- apple-silicon
- quantized
---
# Mistral-7B-Instruct-v0.3
[BaseRT](https://github.com/basecompute/baseRT) `.base` builds of
[`mistralai/Mistral-7B-Instruct-v0.3`](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) for fast local inference on Apple
Silicon (Metal).
## Files
| File | Precision | Size |
|------|-----------|------|
| `Mistral-7B-Instruct-v0.3-Q4.base` | 4-bit | 3.8G |
| `Mistral-7B-Instruct-v0.3-Q8.base` | 8-bit | 7.0G |
## Usage
```bash
curl -LsSf https://basecompute.co/install.sh | sh
basert pull basecompute/Mistral-7B-Instruct-v0.3
basert chat basecompute/Mistral-7B-Instruct-v0.3
```
Released under the apache-2.0 license, inherited from the base model.