Update README.md
Browse files
README.md
CHANGED
|
@@ -10,3 +10,4 @@ tags:
|
|
| 10 |
- mlx
|
| 11 |
pipeline_tag: text-generation
|
| 12 |
---
|
|
|
|
|
|
| 10 |
- mlx
|
| 11 |
pipeline_tag: text-generation
|
| 12 |
---
|
| 13 |
+
Mistral-7B-Instruct-v0.3 quantized with mixed precision: This is a Mistral-7B-Instruct model where the embedding layer and output (head) layer are quantized to 8-bit precision, while the rest of the model uses 6-bit quantization. This mixed-precision approach aims to balance model size and inference speed with improved precision in critical layers.
|