# google/gemma_pytorch

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/google-gemma-pytorch).**

5,697 stars · 598 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/google/gemma_pytorch
- Homepage: https://ai.google.dev/gemma
- awesome-repositories: https://awesome-repositories.com/repository/google-gemma-pytorch.md

## Topics

`gemma` `google` `pytorch`

## Description

The official PyTorch implementation of Google's Gemma models

## Tags

### Artificial Intelligence & ML

- [Long-Context Models](https://awesome-repositories.com/f/artificial-intelligence-ml/large-language-models/long-context-models.md) — Supports input sequences up to 256K tokens, enabling reasoning over large documents or conversations. ([source](https://ai.google.dev/gemma/docs))
- [Long Context Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/long-context-processing.md) — Supports input sequences up to 256K tokens for reasoning over large documents or conversations.
- [Text-Only Inference Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/inference-servers-and-runtimes/text-only-inference-engines.md) — Loads and executes a decoder-only language model on CPU, GPU, or TPU for generating text completions. ([source](https://ai.google.dev/gemma/docs))
- [Multimodal Model Runners](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-models/multimodal-model-runners.md) — Ships a PyTorch implementation that loads and runs Gemma models for multimodal text-and-image inference. ([source](https://ai.google.dev/gemma))
- [Pretrained Model Loading](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-processing/language-model-pretraining/pretrained-model-loading.md) — Downloads and loads open-weight model checkpoints from Kaggle or Hugging Face for local inference. ([source](https://cdn.jsdelivr.net/gh/google/gemma_pytorch@main/README.md))
- [PyTorch Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/pytorch-implementations.md) — Provides an official PyTorch port of Google's Gemma language models for inference and fine-tuning.
- [LLM Inference Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/pytorch-implementations/llm-inference-engines.md) — Runs Google's Gemma models for text generation using PyTorch on CPU, GPU, or TPU.
- [Pretrained Checkpoint Loaders](https://awesome-repositories.com/f/artificial-intelligence-ml/pytorch-model-components/pretrained-checkpoint-loaders.md) — Downloads model weights and tokenizer files from Kaggle or Hugging Face Hub for any supported variant. ([source](https://cdn.jsdelivr.net/gh/google/gemma_pytorch@main/README.md))
- [Open-Weight Checkpoint Loaders](https://awesome-repositories.com/f/artificial-intelligence-ml/pytorch-model-components/pretrained-checkpoint-loaders/open-weight-checkpoint-loaders.md) — Downloads and loads pretrained Gemma model weights from Kaggle or Hugging Face.
- [Decoder-Only Inference](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-decoding-models/sequence-decoders/decoder-only-inference.md) — Loads and executes a decoder-only transformer to generate text completions from a prompt on CPU, GPU, or TPU. ([source](https://ai.google.dev/gemma))
- [AI Safety Guardrails](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-safety-guardrails.md) — Includes a safety evaluation module that checks model inputs and outputs against defined safety policies. ([source](https://ai.google.dev/gemma/docs))
- [Function Calling Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/function-calling-interfaces.md) — Generates structured function-call arguments from natural language prompts for agentic workflows. ([source](https://ai.google.dev/gemma))
- [Content Safety Classifiers](https://awesome-repositories.com/f/artificial-intelligence-ml/safety-and-alignment-frameworks/content-safety-classifiers.md) — Implements a safety classifier that evaluates text against policy-defined categories to detect violations. ([source](https://ai.google.dev/gemma))
- [Text Embedding Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/text-embedding-generators.md) — Produces dense vector representations of text for search, clustering, or similarity tasks.
- [Text Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-numeric-transformations/text-embeddings.md) — Produces numerical vector representations of text for use in retrieval, similarity search, and classification. ([source](https://ai.google.dev/gemma/docs))

### Part of an Awesome List

- [Model Fine-Tuning](https://awesome-repositories.com/f/awesome-lists/ai/model-training-and-fine-tuning/model-fine-tuning.md) — Customizes pre-trained Gemma models on specific datasets to improve task performance.
- [Large Language Models (LLMs)](https://awesome-repositories.com/f/awesome-lists/more/large-language-models-llms.md) — Listed in the “Large Language Models (LLMs)” section of the The Incredible Pytorch awesome list.

### User Interface & Experience

- [Multimodal Input Processors](https://awesome-repositories.com/f/user-interface-experience/form-and-input-management/input-handling/multimodal-input-processors.md) — Accepts text, audio, and image data as input to a single model for combined understanding and generation. ([source](https://ai.google.dev/gemma/docs))

### Security & Cryptography

- [Model Safety Filters](https://awesome-repositories.com/f/security-cryptography/model-safety-filters.md) — Evaluates model inputs and outputs against predefined safety policies to detect violations.