Tinker is cool. If you're a researcher/developer, tinker dramatically simplifies LLM post-training. You retain 90% of algorithmic creative control (usually related to data, loss function, the algorithm) while tinker handles the hard parts that you usually want to touch much less often (infra, forward/backward of the LLM... See more

4 tutorials that helped me learn LLM fine-tuning in 3 weeks: 1. “How to Fine-Tune LLMs in 2024 with Hugging Face” by @_philschmid: https://t.co/bl07sjIQCA 2. “Kaggle Gemma2 9b Unsloth notebook” by @danielhanchen on... See more