Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: coreml
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Mistral-7B-Instruct-v0.3 + CoreML
|
| 7 |
+
|
| 8 |
+
> [!IMPORTANT]
|
| 9 |
+
> ❗ This repo requires the use of the macOS Sequoia (15) Developer Beta to utilize the latest and greatest CoreML has to offer!
|
| 10 |
+
> Sign up for the Apple Beta Software Program [here](https://beta.apple.com/en/) to get acccess.
|
| 11 |
+
> Check out the companion blog post to learn more about what's new in iOS 18 & macOS 15 [here](https://hf.co/blog/wwdc24).
|
| 12 |
+
|
| 13 |
+
This repo contains Mistral 7B Instruct v0.3 converted to CoreML in both FP16 & Int4 precision.
|
| 14 |
+
|
| 15 |
+
Mistral-7B-Instruct-v0.3 is an instruct fine-tuned version of the Mistral-7B-v0.3 by Mistral AI.
|
| 16 |
+
|
| 17 |
+
Mistral-7B-v0.3 has the following changes compared to [Mistral-7B-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2/edit/main/README.md)
|
| 18 |
+
- Extended vocabulary to 32768
|
| 19 |
+
- Supports v3 Tokenizer
|
| 20 |
+
- Supports function calling
|
| 21 |
+
|
| 22 |
+
## Download
|
| 23 |
+
|
| 24 |
+
Install `huggingface-cli`
|
| 25 |
+
|
| 26 |
+
```bash
|
| 27 |
+
brew install huggingface-cli
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
To download one of the `.mlpackage` folders to the `models` directory:
|
| 31 |
+
|
| 32 |
+
```bash
|
| 33 |
+
huggingface-cli download \
|
| 34 |
+
--local-dir models --local-dir-use-symlinks False \
|
| 35 |
+
apple/coreml-mistral-7b-instruct-v0.3 \
|
| 36 |
+
--include "StatefulMistral7BInstructInt4.mlpackage/*"
|
| 37 |
+
```
|
| 38 |
+
|
| 39 |
+
To download everything, skip the `--include` argument.
|
| 40 |
+
|
| 41 |
+
## Integrate in Swift apps
|
| 42 |
+
|
| 43 |
+
The [`huggingface/swift-chat`](https://github.com/huggingface/swift-chat) repository contains a demo app to get you up and running quickly!
|
| 44 |
+
You can integrate the model right into your Swift apps using the `preview` branch of [`huggingface/swift-transformers`](https://github.com/huggingface/swift-transformers/tree/preview)
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
## Limitations
|
| 48 |
+
|
| 49 |
+
The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
|
| 50 |
+
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
|
| 51 |
+
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
|
| 52 |
+
|
| 53 |
+
## The Mistral AI Team
|
| 54 |
+
|
| 55 |
+
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Jean-Malo Delignon, Jia Li, Justus Murke, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Nicolas Schuhl, Patrick von Platen, Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibaut Lavril, Timothée Lacroix, Théophile Gervet, Thomas Wang, Valera Nemychnikova, William El Sayed, William Marshall
|