This project is sponsored by 
Model Card
This model is an finetuned version for german instructions and conversations in style of Open Assistant tokens. "<|prompter|>" "<|endoftext|>" "<|assistant|>"
The dataset used is deduplicated and cleaned, with no codes inside. The focus is on instruction following and conversational tasks.
The model archictecture is based on OpenLlama with 7B parameters, trained on 100% renewable energy powered hardware.
This work is contributed by private research of flozi00
- Downloads last month
- 8