Update README.md
Browse files
README.md
CHANGED
@@ -247,3 +247,4 @@ tags:
|
|
247 |
pipeline_tag: text-generation
|
248 |
base_model: mistralai/Ministral-8B-Instruct-2410
|
249 |
---
|
|
|
|
247 |
pipeline_tag: text-generation
|
248 |
base_model: mistralai/Ministral-8B-Instruct-2410
|
249 |
---
|
250 |
+
Ministral-8B-Instruct-2410 quantized with mixed precision: This is a Ministral-8B-Instruct model where the embedding layer and output (head) layer are quantized to 6-bit precision, while the rest of the model uses 4-bit quantization. This mixed-precision approach aims to balance model size and inference speed with improved precision in critical layers.
|