I'm interested to know if anyone is using fine-tuning to train a model on proprietary or in-house codebases and documentation.<p>RAG solutions seem to have their limitations, and fine-tuning might be a more effective approach.<p>How much effort is required to turn code into something one can use for fine-tuning?
Are people fine-tuning LLMs on their local machines with a single GPU? What are people using to scale their training to multiple nodes / gpus? I've been playing around with Hugging Face Estimators in sagemaker.huggingface but not sure if there are better options for this?
is anyone outside of the research labs fine tuning models for production use cases? I have been seeing more people just using foundational models off the shelf especially in light of a new advancement that seems to come every few months
Instead of versions, these things should be labeled by their release date, since this kind of training is based on started at a dataset snapshot in time, colloquially called knowledge-cutoff date which isnt really accurate<p>we are optimizing these on different dimensions at once, and multiple branches of evolution from each model<p>so a successor version name doesn't really convey that
Great article, but I didn't see anything about the costs.<p>I'm particularly interested in this aspect because we're considering fine-tuning Gemma 3, but our budget is tight. We're looking into (real-world) cost estimates for this approach.
It likely makes sense to use more expensive frontier models as teachers or architects for smaller fine-tuned ones that generate the majority of tokens (though possibly against the ToS).