This llama model was trained 2x faster with
Unsloth and Huggingface's TRL library.
An expert Formula 1 assistant fine-tuned on the
2024 Formula 1 Championship dataset (
vibingshu/2024_formula1_championship_dataset).
Hardware: Google Colab (T4 / A100, depending on availability)
Tools Used: Unsloth, Hugging Face datasets, LoRA adapters
Precision: 8-bit (Q8_0) for efficient inference
This model is released under the Apache 2.0 license.
You are free to use, modify, and distribute it with proper attribution.