image/png

Hathor_Sofit [v1] is designed to seamlessly integrate the qualities of creativity, intelligence, and robust performance.

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

EXL2 Quant's available Thanks to RiveRiPH <3 Exl2 8bpw Here Exl2 6.3bpw Here

Recomended ST Presets: Hathor Presets(Updated)


Training-Note: Hathor_Sofit [v1] is trained on 1 epoch of Private - STEM (Intruction/Dialogs), swallow-magpie-ultra-v0.1, Hathor_0.5 Instructions, mixture of creative writing data (light/web/classical novels), roleplaying chat pairs over Hathor_0.85.

Additional Notes: This will be the last of the Hathor Model series, and all my trains over Llama 3.

Downloads last month
239
Safetensors
Model size
8.03B params
Tensor type
BF16
Β·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Nitral-AI/Hathor_Sofit-L3-8B-v1

Finetunes
4 models
Merges
3 models
Quantizations
8 models

Spaces using Nitral-AI/Hathor_Sofit-L3-8B-v1 6

Collection including Nitral-AI/Hathor_Sofit-L3-8B-v1