Large model fine tunes
Collection
LoRA
•
4 items
•
Updated
-informational){kind=icon}
-GGUF files (coming)
- info
This model has been fine-tuned with 1.75 million tokens. Gemma-27b-it was used as the base model.
WARNING: This AI model may make mistakes. PLEASE CHECK ITS RESPONSES. This model fine-tuning metod unsloth LoRA Used GPU a100 40gb Colab version v2
- Developed by: Ali-Yaser
- License: Gemma licance
- Finetuned from model : Google/gemma-3-27b-it
This gemma3 model was trained with Unsloth and Huggingface's TRL library.
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support