README.md

metadata

license: other
language:
  - en

Hathor_Tahsin [v-0.9] is designed to seamlessly integrate the qualities of creativity, intelligence, and robust performance.

GGUF Quant's available Thanks to Bartowski <3: GGUF's Here

EXL2 Quant's available Thanks to Nitral-Ai <3: 5bpw exl2 Here

Recomended ST Presets: Hathor Presets(Updated)

---

Note: Hathor_Tahsin [v0.9] is trained on 3 epochs of Private RP, STEM (Intruction/Dialogs), Opus instructons, mixture light/classical novel data, roleplaying chat pairs over llama 3 8B instruct.

Additional Note's: (Based on Hathor_Fractionate-v0.5 - Slightly different hparams, and changed the order i applied the datasets. This train was done around the same time as 0.85 but i kind of forgot it existed.)