gemma

Prompt injection allows third-party to inject a system prompt with simple message, by inserting special HTML-like sequence (details below). Some of the issues are well-known and pretty old (almost 2 years for Transformers library) Issues: • Ollama: https://github.com/ollama/ollama/issues/15931 • HuggingFace: https://github.com/huggingface/transformers/issues/29279 (labeled as feature request) https://github.com/huggingface/transformers/issues/47822 (with a bug label) • Gemma4: https://github.com/google-deepmind/gemma/issues/768 The problem is that for tools like Ollama there is no solution except of to fix it by Ollama developers More context Why this is important: prompt injections are pretty dangerous and as long as user input is an instruction to the model it could be decided as code injections vulnerability. And in combination with lo

Wait, what files are you reading? https://github.com/google-deepmind/gemma/blob/main/LICENSE (Even then, releasing some source code under Apache-2 does not make a model "open source".) Ah I found https://ai.google.dev/gemma/terms > You must not use any of the Gemma Services: > > 1. for the restricted uses set forth in the Gemma Prohibited Use Policy at ai.google.dev/gemma prohibited_use_policy ("Prohibited Use Policy"), which is hereby incorporated by reference into this Agreement; or > 2. in violation of applicable laws and regulations. https://ai.google.dev/gemma/prohibited_use_policy Yeah, definitely not open source, even if they had released all the training data.

Your reply adds more confusion, imo. The inference code and model architecture IS open source[0] and there are many other high quality open source implementations of the model (in many cases contributed by Google engineers[1]). To your point: they do not publish the data used to train the model so you can't re-create it from scratch. [0] https://github.com/google-deepmind/gemma [1] https://github.com/vllm-project/vllm/pull/2964

Gemma is called "open weights." This terminology is correct. You don't get to redefine terms just because you happened to do something that other people like. https://github.com/google-deepmind/gemma

* the code is at https://github.com/google-deepmind/gemma * you download the weights at https://www.kaggle.com/models/google/gemma-3/

Hi, haven't followed this thread for a while so just happened to see this now. I'm assuming you mean in other languages/implementations? (since the gemma.cpp repo linked above has code + links for gemma.cpp specific weights) If so, you can find the weights here https://www.kaggle.com/models/google/gemma - each of the "model variations" (flax, jax, pytorch, keras, etc.) has a download for the weights and links to its code. If you're comfortable with flax, that's DM's own reference implementation: https://github.com/google-deepmind/gemma

We've documented the architecture (including key differences) in our technical report here (https://goo.gle/GemmaReport), and you can see the architecture implementation in our Git Repo (https://github.com/google-deepmind/gemma).