|
--- |
|
license: other |
|
language: |
|
- en |
|
--- |
|
|
|
#WARNING: This model is completely unstable and i would not recommend its use. |
|
- May be good as potential merge fodder given the datasets and domain. |
|
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/jAr9h8RMRbpenfgm6oDmT.png) |
|
|
|
"Hathor-v0.4 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." |
|
|
|
# Recomended ST Presets: [Hathor Presets](https://huggingface.co/Nitral-AI/Hathor_Presets/tree/main) |
|
|
|
# Quants From Bartowski <3: https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-exl2 https://huggingface.co/bartowski/Hathor_Enigmatica-L3-8B-v0.4-GGUF |
|
--- |
|
# Notes: Hathor is trained on 3 epochs of private: synthetic opus instructons, a mix of light/classical novel data, roleplaying chat pairs over llama 3 8B instruct. (update- Additional Private RP data from Hathor 0.2, Medical/Biology/Anatomy and Programming/Cybersecurity Data) |