Google Company announced on the publication of a large machine learning language model Gemmabuilt using technologies used to build a chatbot model Gemini, trying to compete with ChatGPT. Model available in four variants covering 2 And 7 billions of parameters, in basic and dialog-optimized representations. Options with 2 billion parameters are suitable for use in consumer applications and the CPU is enough to process it. Options with 7 billion parameters require more powerful hardware and a GPU or TPU.
Among the areas of application of the Gemma model are the creation of dialogue systems and virtual assistants, text generation, generation of answers to questions asked in natural language, summary and generalization of content, explanation of the essence of concepts and terms, correction of errors in the text, assistance in learning languages. It supports the creation of various types of text data, including poetry, code in programming languages, rewriting works in other words, and generating letters using a template. At the same time, the model has a relatively small size, allowing it to be used on your own equipment with limited resources, for example, on ordinary laptops and PCs.
License The model allows free use and distribution not only in research and personal projects, but also in commercial products. The creation and publication of modified versions of the model is also allowed. At the same time, the terms of use prohibit the use of the model to perform malicious actions and require, whenever possible, to use the latest version of Gemma in your products.
Support for working with Gemma models is already added to the toolkit Transformers and in Responsible Generative AI Toolkit. To optimize the model, you can use the framework Keras and backends for TensorFlow, JAX and PyTorch. It is also possible to use Gemma with frameworks MaxText, NVIDIA NeMo And TensorRT-LLM.
The size of the context taken into account by the Gemma model is 8 thousand tokens (the number of tokens that the model can process and remember when generating text). For comparison, the context size for the Gemini and GPT-4 models is 32 thousand tokens, and for the GPT-4 Turbo model it is 128 thousand. The model only supports English. By productivity the Gemma-7B model is slightly inferior to the LLama 2 70B Chat and is slightly ahead of the models DeciLM-7B, PHI-2 (2.7B) And Mistral-7B-v0.1. IN
comparison Google's Gemma-7B model is slightly ahead of LLama 2 7B/13B and Mistral-7B.
Thanks for reading: