mrfakename commited on
Commit
1f57312
·
verified ·
1 Parent(s): 2a0a705

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -7,6 +7,8 @@ base_model:
7
 
8
  This is Mistral's Ministral 3 8B Instruct model with the vision encoder removed and converted to the Llama format. The model may be slightly different due to conversion but should be largely identical (besides the removal of the vision encoder).
9
 
 
 
10
  The main benefits of Llama-converted models:
11
 
12
  - Easier to train: compatible with all trainers that support the Llama model
 
7
 
8
  This is Mistral's Ministral 3 8B Instruct model with the vision encoder removed and converted to the Llama format. The model may be slightly different due to conversion but should be largely identical (besides the removal of the vision encoder).
9
 
10
+ **Note: Mistral's Ministral 3 Instruct models are quantized by default, so this is an upcasted version of the model.**
11
+
12
  The main benefits of Llama-converted models:
13
 
14
  - Easier to train: compatible with all trainers that support the Llama model