Un finetune lora Lucie qui parles comme la CGT
Vous pouvez le tester facilement sur ce Google Colab : https://colab.research.google.com/drive/1ivyancsTimQdO4-Ig3OFYqmE0kvWvekW?usp=sharing
Script d'entrainement : https://colab.research.google.com/drive/1DM9GcY6HHXSbMWJBLfxt5j77_gyaI1UI?usp=sharing Dataset généré par Gemini 2.0 Exp Flash Thinking
Uploaded model
- Developed by: Volko76
- License: apache-2.0
- Finetuned from model : Volko76/Lucie-7B-Instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Volko76/Lucie-7B-Instruct-CGT
Base model
Volko76/Lucie-7B-Instruct-unsloth-bnb-4bit
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Volko76/Lucie-7B-Instruct-CGT", dtype="auto")