41–50 of 60 posts
Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!
Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!
I’ve been wanting to fine tune models for home assistant but unsure how to get some synthetic data, any recommendations?
Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!
Earlier quoted context omitted.
Some fine tuning data questions: i see the the dataset Google published in this notebook https://github.com/google-gemini/gemma-cookbook/blob/main/Fu... -- from looking at the dataset on huggingface, it looks synthetically generated. 1. do you recommend any particular mix or focus in the dataset for finetuning this model, without losing too much generality? 2. do you have any recommendations for how many examples per…
> Do you recommend any particular mix or focus in the dataset for finetuning this model, without losing too much generality? Astute questions, there's sort of two ways to think about finetuning, 1. Obliterate any general functionality and train the model on your general commands 2. As you asked maintain generality trying to preserve initial model ability For 2 typically low learning rate or LORA is a good strategy. W…
I’ve been wanting to fine tune models for home assistant but unsure how to get some synthetic data, any recommendations?
Great work from the Google ML teams, I’ll be trying this model out.
Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!
Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!
If I have a simple mainly question-answering AI using only a couple of tools (web search), am I better off starting with Gemma or FunctionGemma?
Another hard constraint is context limit, Gemma 270m is at 32k so if the search results returned are massive then this not a great model. The larger 4b+ Gemma models have 128k, and Gemini token window is in the millions
Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!
hi! Does this bring us closer to a gemini-cli like experience using a local modal that can run on a macbook pro? It felt like gemma3n was already 'smart' enough it just wasn't tuned for tool use.