Uploaded finetuned model
- Developed by: Robo420
- License: Gemma
- Finetuned from model : unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit
This model was finetuned on a german dataset and should be better at staying coherent in german.
This gemma3n model was trained 2x faster with Unsloth and Huggingface's TRL library.
Notice: I still had to pay for Google Colab though, even if the unsloth finetune collab tells you it works in free mode, since it kept running OOM when generating the final weigths.
GGUF following as soon as i get around to do it.
- Downloads last month
- 45
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support