Taurus 7B 1.0 GGUF
These are llama.cpp quants for Taurus 7B 1.0.
Description
Taurus is an OpenHermes 2.5 finetune using the Economicus dataset, an instruct dataset synthetically generated from Economics PhD textbooks.
The model was trained for 2 epochs (QLoRA) using axolotl. The exact config I used can be found here.
Prompt format
Taurus uses ChatML.
<|im_start|>system
System message
<|im_start|>user
User message<|im_end|>
<|im_start|>assistant
- Downloads last month
- 76
Hardware compatibility
Log In to add your hardware
4-bit
5-bit
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for rxavier/Taurus-7B-1.0-GGUF
Base model
mistralai/Mistral-7B-v0.1 Finetuned
teknium/OpenHermes-2.5-Mistral-7B Finetuned
rxavier/Taurus-7B-1.0