Update README.md
Browse files
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
|