🇩🇪 nanochat German: Base Model Checkpoint
This repository hosts the first base German nanochat model.
It was pretrained with a modified version of the awesome nanochat implementation from Andrej Karpathy. The model was trained on 8xA100 from Lambda.
Notice: this repo hosts the final checkpoint from the original implementation. More information about the pretraining can be found in this repo, where the HF Transformers-compatible model lives.
License
The model is licences under a permissive Apache 2.0 license.
Acknowledgements
- Many thanks to Andrej Karpathy's original nanochat repo!
- Thanks to the LLäMmlein team for making the pretraining data publicly available.
- Thanks to Ben and Joshua for help and working on the nanochat HF integration.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support