Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,7 @@ license: apache-2.0
|
|
| 22 |
|
| 23 |
GGUFs can be found [here](https://huggingface.co/InferenceIllusionist/Excalibur-7b-GGUF)
|
| 24 |
|
|
|
|
| 25 |
### Performance Comparison
|
| 26 |
| Name | Avg. | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|
| 27 |
| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
|
|
@@ -53,8 +54,8 @@ The challenge this time was placing more weight on Merlinite-7b as an unknown qu
|
|
| 53 |
<b>Requires additional [mistral-7b-mmproj-v1.5-Q4_1.gguf](https://huggingface.co/koboldcpp/mmproj/tree/main) file for vision functionality</b>
|
| 54 |
<img src="https://i.imgur.com/4wbUrjf.jpeg" width="550"/>
|
| 55 |
|
| 56 |
-
|
| 57 |
-
|
| 58 |
|
| 59 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 60 |
|
|
|
|
| 22 |
|
| 23 |
GGUFs can be found [here](https://huggingface.co/InferenceIllusionist/Excalibur-7b-GGUF)
|
| 24 |
|
| 25 |
+
|
| 26 |
### Performance Comparison
|
| 27 |
| Name | Avg. | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|
| 28 |
| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
|
|
|
|
| 54 |
<b>Requires additional [mistral-7b-mmproj-v1.5-Q4_1.gguf](https://huggingface.co/koboldcpp/mmproj/tree/main) file for vision functionality</b>
|
| 55 |
<img src="https://i.imgur.com/4wbUrjf.jpeg" width="550"/>
|
| 56 |
|
| 57 |
+
Select up 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:
|
| 58 |
+
<img src="https://i.imgur.com/u1vo8Rs.jpeg" width="550"/>
|
| 59 |
|
| 60 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 61 |
|