X @Avi Chawla

What goes into fine-tuning models like DeepSeek-R1?- Dataset preparation- Defining LoRA config- Defining a Trainer- Fine-tuning the LLM- Exporting to OllamaThe thread below covers this: https://t.co/78A3YXiWSyAvi Chawla (@_avichawla):Let's fine-tune DeepSeek-R1 (distilled Llama) 100% locally: ...