Commit
•
f302978
1
Parent(s):
2223ec4
Update README.md
Browse files
README.md
CHANGED
@@ -32,7 +32,9 @@ An initial foray into the world of fine-tuning. The goal of this release was to
|
|
32 |
## Sample Question - Vision
|
33 |
<img src="https://i.imgur.com/7aRWtzU.jpeg" width="425"/>
|
34 |
|
35 |
-
|
|
|
|
|
36 |
|
37 |
Select the gguf file of your choice in Kobold as usual, then make sure to choose the mmproj file above in the LLaVA mmproj field of the model submenu:
|
38 |
<img src="https://i.imgur.com/x8vqH29.png" width="425"/>
|
|
|
32 |
## Sample Question - Vision
|
33 |
<img src="https://i.imgur.com/7aRWtzU.jpeg" width="425"/>
|
34 |
|
35 |
+
*<b>Requires additional mmproj file. You have two options for vision functionality (available inside original repo or linked below):</b>
|
36 |
+
* [Quantized - Limited VRAM Option (197mb)](https://huggingface.co/InferenceIllusionist/Excalibur-7b-DPO-GGUF/resolve/main/mistral-7b-mmproj-v1.5-Q4_1.gguf?download=true)
|
37 |
+
* [Unquantized - Premium Option / Best Quality (596mb)](https://huggingface.co/InferenceIllusionist/Excalibur-7b-DPO-GGUF/resolve/main/mmproj-model-f16.gguf?download=true)
|
38 |
|
39 |
Select the gguf file of your choice in Kobold as usual, then make sure to choose the mmproj file above in the LLaVA mmproj field of the model submenu:
|
40 |
<img src="https://i.imgur.com/x8vqH29.png" width="425"/>
|