#warning model has a tendency to speak as the user in chatml, and performance seems degraded in l3. Id use 0.2 or 0.5.
"Hathor-v0.6 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 (Updated)
Quants From Bartowski <3: https://huggingface.co/bartowski/Hathor_Gamma-L3-8B-0.6-exl2 https://huggingface.co/bartowski/Hathor_Gamma-L3-8B-0.6-GGUF
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. (update- More Private RP, Cybersecurity, Programming, Biology/Anatomy data in ChatML.)
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.