Commit
•
4c23f0b
1
Parent(s):
7c1e72c
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- llamafile
|
| 5 |
+
- GGUF
|
| 6 |
+
base_model: qwp4w3hyb/Mixtral-8x7B-Instruct-v0.1-iMat-GGUF
|
| 7 |
+
---
|
| 8 |
+
## MixtralIMAT
|
| 9 |
+
|
| 10 |
+
llamafile lets you distribute and run LLMs with a single file. [announcement blog post](https://hacks.mozilla.org/2023/11/introducing-llamafile/)
|
| 11 |
+
|
| 12 |
+
#### Downloads
|
| 13 |
+
|
| 14 |
+
- [mixtral-8x7b-instruct-v0.1-imat-IQ1_S.llamafile](https://huggingface.co/blueprintninja/MixtralIMAT/resolve/main/mixtral-8x7b-instruct-v0.1-imat-IQ1_S.llamafile)
|
| 15 |
+
|
| 16 |
+
This repository was created using the [llamafile-builder](https://github.com/rabilrbl/llamafile-builder)
|