dgomes03 commited on
Commit
34b9eed
·
verified ·
1 Parent(s): 283d26b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
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.