Update README.md
Browse files
README.md
CHANGED
@@ -12,15 +12,3 @@ language:
|
|
12 |
# Quants From Bartowski <3: https://huggingface.co/bartowski/Hathor-L3-8B-v.02-GGUF https://huggingface.co/bartowski/Hathor-L3-8B-v.02-exl2
|
13 |
---
|
14 |
# Notes: Hathor is trained on 3 epochs of private data, synthetic opus instructons, a mix of light/classical novel data, roleplaying chat pairs over llama 3 8B instruct. (expanded)
|
15 |
-
---
|
16 |
-
|
17 |
-
- If you want to use vision functionality:
|
18 |
-
|
19 |
-
* You must use the latest versions of [Koboldcpp](https://github.com/LostRuins/koboldcpp).
|
20 |
-
|
21 |
-
- To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo. [Llava MMProj](https://huggingface.co/Nitral-AI/Llama-3-Update-3.0-mmproj-model-f16)
|
22 |
-
|
23 |
-
* You can load the **mmproj** by using the corresponding section in the interface:
|
24 |
-
|
25 |
-
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/UX6Ubss2EPNAT3SKGMLe0.png)
|
26 |
-
---
|
|
|
12 |
# Quants From Bartowski <3: https://huggingface.co/bartowski/Hathor-L3-8B-v.02-GGUF https://huggingface.co/bartowski/Hathor-L3-8B-v.02-exl2
|
13 |
---
|
14 |
# Notes: Hathor is trained on 3 epochs of private data, synthetic opus instructons, a mix of light/classical novel data, roleplaying chat pairs over llama 3 8B instruct. (expanded)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|