Certaines informations sont présentées en anglais.
À propos de moi
I specialize in custom LLM fine-tuning, dataset preparation, and local AI model deployment. Using efficient QLoRA methods and Unsloth optimization, I train open-weight models (Llama 3, Qwen 2.5, Mistral) tailored to your specific needs.
What I offer:
• Fine-tuning open-source LLMs on custom datasets (.jsonl, .csv, plain text)
• Model optimization, LoRA adapter extraction, and GGUF conversions for local running (Ollama / LM Studio)
• Dataset cleaning, formatting, and prompt formatting
• High data privacy: Secure local training pipelines with zero external cloud retention... Plus d’infos