Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# "Hathor-v0.1 is a model based on the LLaMA 3 architecture: Designed to seamlessly integrate the qualities of creativity, intelligence, and robust performance. Making it an ideal tool for a wide range of applications; such as creative writing, educational support and human/computer interaction."
|
| 3 |
+
|
| 4 |
+
# Recomended ST Presets: [Hathor Presets](https://huggingface.co/Nitral-AI/Hathor-L3-8B-v.01/tree/main/Hathor%20Presets)
|
| 5 |
+
|
| 6 |
+
---
|
| 7 |
+
# 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)
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
- If you want to use vision functionality:
|
| 11 |
+
|
| 12 |
+
* You must use the latest versions of [Koboldcpp](https://github.com/LostRuins/koboldcpp).
|
| 13 |
+
|
| 14 |
+
- 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)
|
| 15 |
+
|
| 16 |
+
* You can load the **mmproj** by using the corresponding section in the interface:
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
---
|