# gemma Gemma is a family of lightweight open AI models developed by Google DeepMind and other Google teams, available to run in applications and on user hardware. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Autonomous LLM post-training with Tunix on TPUs DevFeed: [Autonomous LLM post-training with Tunix on TPUs]() Original publisher: [Read original article]() Author: Wei Wei Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [post-training](), [AI Agent](), [Fine-tuning](), [Large Language Model](), [grpo](), [lora](), [gemma](), [Google](), [Reinforcement learning](), [dataset](), [Command-line interface]() Tags: [autonomous](), [cli](), [fine-tuning](), [gemma](), [git](), [google](), [grpo](), [llm](), [lora](), [post-training](), [reinforcement-learning](), [training]() ### AI overview This article presents autofinetune, an autonomous research loop for LLM post-training. Using AI agents and Google's AI stack, including Tunix, Gemma, Cloud TPUs, Antigravity CLI, and Gemini Flash 3.7, it automates supervised fine-tuning and reinforcement learning with GRPO, exploring hyperparameters such as LoRA configurations, learning rates, batch sizes, and rollout settings. ### Source excerpt Imagine going to sleep after writing a single Markdown specification and waking up to find that an A... ## Abliterated Models Show Verdict Bias in FreeBSD Kernel Bug Hunting DevFeed: [Abliterated Models Show Verdict Bias in FreeBSD Kernel Bug Hunting]() Original publisher: [Read original article]() Author: clearbluejar Published: 2026-09-01T06:00:00Z Content type: article Language: en Sources: [clearbluejar]() Topics: [freebsd](), [vulnerability](), [bug](), [Kernel](), [gemma4](), [Testing](), [gemma]() Tags: [bug](), [bug-hunting](), [cve](), [false-positives](), [freebsd](), [gemma](), [gemma-4](), [kernel](), [llms](), [testing](), [vulnerability](), [vulnerability-research]() ### AI overview The article examines local abliterated open-weight models during vulnerability scanning of FreeBSD kernel source. Compared with base models of the same family and size, the modified models produced substantially more candidate and VALID findings, including false positives, while the most aggressive build did not surface the real CVE in a 28-file scan. The article describes this tendency as verdict bias: a greater willingness to return positive findings under uncertainty. ### Source excerpt Abliterated models never refuse, which makes them tempting for bug hunting. But on the same kernel source, they graduate three to four times as many findings to VALID, including false positives the base correctly rejects, and across a 28-file scan of FreeBSD's sys/rpc the most aggressive build never surfaced the real CVE at all. ## Batch-Evaluating LLM Agent Trajectories for Responsible AI Checks on Cloud TPU v5e DevFeed: [Batch-Evaluating LLM Agent Trajectories for Responsible AI Checks on Cloud TPU v5e]() Original publisher: [Read original article]() Author: Noble Ackerson Published: 2026-08-04T23:28:06Z Content type: tutorial Language: en Sources: [Google Developer Experts - Medium]() Topics: [Monitoring](), [vllm](), [Cloud](), [hugging face](), [Large Language Model](), [Claude](), [gemma](), [Security](), [Benchmark](), [Artificial Intelligence](), [incident]() Tags: [ai](), [ai-agent](), [artificial-intelligence](), [benchmark](), [claude](), [cybersecurity](), [evaluation](), [gemma](), [google-cloud-platform](), [hugging-face](), [incident](), [infrastructure](), [monitoring](), [responsible-ai](), [security](), [vllm]() ### AI overview This article describes batch-evaluating LLM agent trajectories for responsible-AI checks before incidents occur. It connects reported production-system breaches with Hugging Face's use of LLM-driven analysis over more than 17,000 attacker events, then presents a scheduled approach using Gemma through vLLM on Cloud TPU v5e. ### Source excerpt Batch-evaluating agent trajectories on Cloud TPU v5e (compliance-at-scale, part 2) Trajectory batch eval pipeline for rai-checklist-cli A week or so ago, Hugging Face disclosed that an autonomous agent had broken into its production infrastructure. Five days later, OpenAI confirmed the agent was theirs: a combination of its own models, running an internal cyber-capability eval with the production safety classifiers switched off. The models were being tested on a benchmark called ExploitGym. The fastest observable path to a solution ran through the answer key. They escaped the isolated environment through a package-registry proxy, chained stolen credentials with zero-day vulnerabilities, and pulled the test solutions out of Hugging Face's production database. Per Axios, the agent kept pursuing its assigned objective even after it had escaped the test environment. Nine days later, Anthropic said hold my beer, checked its own logs and found three more. It reviewed 141,006 runs and found three cases where Claude models had reached the open internet and breached real production systems, the earliest dating to April. Two of the three organizations learned about it when Anthropic notified them. One lab looked and found something. A second lab looked and found something. That is the whole story here, and it should be the uncomfortable part: none of this surfaced through production monitoring. It surfaced because somebody went back and read the trajectories. Nobody has published what score that run produced. It doesn't matter. The part of this story that matters for this series is what Hugging Face did next with their findings. To reconstruct the intrusion, Hugging Face's security team ran LLM-driven analysis agents over the full attacker action log: more than 17,000 recorded events. Reporting indicates they did that analysis with an open-weight model on their own infrastructure, partly so no hosted safety classifier sat between the responders and the attack data, and partly ## Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction DevFeed: [Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction]() Original publisher: [Read original article]() Published: 2026-06-26T18:30:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [AI Inference](), [On-device AI](), [Google](), [LLMs](), [gemma]() Tags: [ai](), [efficiency](), [energy](), [gemini](), [inference](), [machine-intelligence](), [mobile-systems](), [natural-language-processing](), [on-device](), [on-device-ai](), [phones]() ### AI overview Google Research describes a method for retrofitting Multi-Token Prediction onto frozen Gemini Nano v3 production models to accelerate on-device inference on Pixel phones. The approach targets mobile energy and memory constraints, improving the speed and energy efficiency of features such as notification summaries and proofreading without requiring separate drafting models. ### Source excerpt Machine Intelligence ## Using local Gemma and Qwen models to triage OpenClaw issues and pull requests DevFeed: [Using local Gemma and Qwen models to triage OpenClaw issues and pull requests]() Original publisher: [Read original article]() Author: Onur Solmaz; ben burtenshaw; shaun smith Published: 2026-06-22T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [OpenClaw](), [Agent Harness](), [Open Source](), [Artificial Intelligence](), [gemma](), [qwen]() Tags: [agent](), [agent-harness](), [artificial-intelligence](), [free](), [gemma](), [guide](), [open-source](), [open-source-collab](), [openclaw](), [pull-requests](), [qwen](), [real-time]() ### AI overview The article describes using local Gemma and Qwen models in an agent harness to classify and triage issues and pull requests in the OpenClaw repository. It presents local execution as a way to support near-real-time notifications without relying on a paid hosted-model quota, using structured outputs and a finite label set. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Gemma 4: Byte for byte, the most capable open models DevFeed: [Gemma 4: Byte for byte, the most capable open models]() Original publisher: [Read original article]() Author: Clement Farabet Published: 2026-04-02T16:00:49Z Content type: release Language: en Sources: [Google DeepMind News]() Topics: [gemma4](), [gemma](), [Artificial Intelligence](), [Mixture of Experts (MoE)](), [multimodal](), [Low Latency](), [Android]() Tags: [agentic](), [ai](), [android](), [apache](), [gemma](), [latency](), [low-latency](), [mixture-of-experts-moe](), [models](), [multimodal](), [none](), [on-device](), [open](), [performance](), [products](), [reasoning](), [research](), [tools](), [workflows]() ### AI overview Gemma 4 is a family of open models designed for advanced reasoning and agentic workflows. It includes E2B, E4B, 26B Mixture of Experts, and 31B Dense variants, with an Apache 2.0 license and designs optimized for hardware ranging from Android devices and laptop GPUs to developer workstations and accelerators. ### Source excerpt Gemma 4: Our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows. ## Local AI Setup Guide for Android Developers DevFeed: [Local AI Setup Guide for Android Developers]() Original publisher: [Read original article]() Author: blundell Published: 2026-01-18T14:03:28Z Content type: tutorial Language: en Sources: [Blundell]() Topics: [android-development](), [Ollama](), [gemma](), [Large Language Model]() Tags: [android](), [android-development](), [beginner](), [beginner-reference](), [gemma](), [how-to](), [intermediate](), [llm](), [local](), [offline](), [ollama](), [reference]() ### AI overview A Day 1 setup guide for Android developers that recommends AI-focused browser resources and Ollama for running open-source models locally. It discusses Gemma 3, including its multimodal capabilities, 128k-token context window, and hardware considerations. ### Source excerpt Forget just installing Android Studio and calling it a day. To operate at scale, you need a local environment that augments your engineering intuition with LLM-powered efficiency. Here is your Day 1 guide to setting up your machine for success. The post Zero to AI: An Android Developer's Vital Local Setup first appeared on Blundell. ## Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior DevFeed: [Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior]() Original publisher: [Read original article]() Author: Language Model Interpretability team Published: 2025-12-16T10:14:24Z Content type: article Language: en Sources: [Google DeepMind News]() Topics: [ai safety](), [gemma](), [Large Language Model](), [AI Research](), [Open Source](), [Development]() Tags: [ai-models](), [ai-research](), [ai-safety](), [debug](), [demo](), [gemma](), [language-models](), [open-source](), [responsibility-safety](), [safety]() ### AI overview Google DeepMind announces Gemma Scope 2, an open suite of interpretability tools covering all Gemma 3 model sizes from 270M to 27B parameters. The tools use sparse autoencoders and transcoders to help researchers examine language model behavior, investigate safety risks, and study issues such as jailbreaks, hallucinations, and sycophancy. ### Source excerpt Open interpretability tools for language models are now available across the entire Gemma 3 family with the release of Gemma Scope 2. ## Gemma 3 AI model in Clojure DevFeed: [Gemma 3 AI model in Clojure]() Original publisher: [Read original article]() Published: 2025-12-09T22:35:00Z Content type: tutorial Language: en Sources: [Dragan Djuric]() Topics: [Clojure](), [Artificial Intelligence](), [Inference](), [Large Language Model](), [onnx](), [gemma]() Tags: [3](), [ai](), [clojure](), [code](), [deep](), [diamond](), [gemma](), [inference](), [llms](), [onnx]() ### AI overview This tutorial demonstrates loading and running a one-step Gemma 3 inference in Clojure through the ONNX runtime integration in Deep Diamond. It configures a smaller one-billion-parameter model, uses main-memory tensors with the oneDNN engine, and explains that the demonstrated output is a next-token tensor rather than a complete generated response. ### Source excerpt Recently I've been working on the ONNX runtime integration into Deep Diamond, backed by the grant sponsored by the Clojurists Together Foundation. In the past few articles, we've seen how ONNX models are integrated into Deep Diamond, using only a single function onnx, with almost no need for additional configuration (which is available). I used a simple MNIST model in the demonstration. But, can we now load and run the inference on the real deal models, such as the open LLMs from the Hugging Face, for example? Let's see! The Hugging Face model card has this to say about Gemma 3: "Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models." (etc., etc.) So, it seems to be something worth trying. I'll try to be brief, and skip the unnecessary talk. Let's just show the code, which I've just lifted up and adapted from the Diamond's midje tests. What we need for this? First, decide on the backend engine; this time we'll use tensors in main memory backed up by the oneDNN engine (DNNL). (def fact (dnnl-factory)) (def neand-fact (neanderthal-factory fact)) Next, load and configure a particular flavor of Gemma 3 (a smaller one, only 1 billion parameters). The onnx function creates a generalized blueprint, which can create the actual functions when evaluated with the specific input tensors. (def onnx-bp (onnx fact "data/gemma-3-1b-it-ONNX-GQA/onnx/model.onnx" {:options (-> (options) (override-dimension! "batch_size" 1) (override-dimension! "sequence_length" 1) (override-dimension! "past_sequence_length" 1) (override-dimension! "total_sequence_length" 1))}) Gemma 3 has 63 inputs and 61 outputs. We'll need to provide these, but even here we can automate some parts with Clojure, since past-key values are pretty uniform. We only need to provide inputs, while the engine can create the outputs for us. (def src-tz (tensor fact [1 1 28 28] :float :nchw)) (def input-ids (tensor neand-fact [1 ## Toward provably private insights into AI use DevFeed: [Toward provably private insights into AI use]() Original publisher: [Read original article]() Published: 2025-10-30T10:56:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Artificial Intelligence](), [Generative AI](), [Confidential Computing](), [Google](), [trusted-execution-environment](), [data-processing](), [Large language models (LLMs)](), [gemma](), [Open Source]() Tags: [ai](), [confidential-computing](), [data-processing](), [gemma](), [generative-ai](), [google](), [large-language-models-llms](), [mobile-systems](), [on-device](), [open-source](), [research](), [security-privacy-and-abuse-prevention](), [software-systems-engineering]() ### AI overview Google Research introduces provably private insights, a system that combines large language models, differential privacy, and trusted execution environments to analyze aggregate patterns in on-device generative AI use without exposing individual data. ### Source excerpt Generative AI ## T5Gemma: A new collection of encoder-decoder Gemma models DevFeed: [T5Gemma: A new collection of encoder-decoder Gemma models]() Original publisher: [Read original article]() Author: Biao Zhang; Paul Suganthan; Ben Hora Published: 2025-10-25T18:14:00Z Content type: article Language: en Sources: [Google DeepMind News]() Topics: [gemma](), [Large Language Model](), [Transformer](), [LLM Techniques](), [LLM evaluation / benchmarking]() Tags: [architecture](), [benchmarks](), [gemma](), [inference](), [inference-efficiency](), [llms](), [models](), [performance](), [research](), [training]() ### AI overview The article introduces T5Gemma, a collection of encoder-decoder large language models created by adapting pretrained decoder-only Gemma 2 models. It describes pretrained and instruction-tuned variants, flexible encoder-decoder configurations, and reported quality and inference-efficiency advantages across benchmarks such as SuperGLUE. ### Source excerpt Introducing T5Gemma, a new collection of encoder-decoder LLMs. ## MedGemma: Our most capable open models for health AI development DevFeed: [MedGemma: Our most capable open models for health AI development]() Original publisher: [Read original article]() Published: 2025-10-25T18:02:50Z Content type: article Language: en Sources: [Google DeepMind News]() Topics: [AI Development](), [Artificial Intelligence](), [multimodal](), [gemma](), [gemma4](), [Application Development](), [GPU](), [Hardware](), [Google]() Tags: [2025](), [ai](), [ai-development](), [classification](), [development](), [gemma](), [generation](), [google](), [gpu](), [hardware](), [health](), [healthcare](), [image](), [mobile](), [models](), [multimodal](), [open](), [product-development](), [research](), [retrieval]() ### AI overview Google Research announces two open models in the MedGemma collection for health AI development: MedGemma 27B Multimodal and MedSigLIP. The models support medical text and imaging tasks, including electronic health record interpretation, report generation, visual question answering, classification, and retrieval. ### Source excerpt We're announcing new multimodal models in the MedGemma collection, our most capable open models for health AI development. ## Gemma 3n fully available in the open-source ecosystem! DevFeed: [Gemma 3n fully available in the open-source ecosystem!]() Original publisher: [Read original article]() Author: Aritra Roy Gosthipaty; Pedro Cuenca; Sergio Paniego; Vaibhav Srivastav; Christopher Fleetwood; Joshua; Steven Zheng; Kashif Rasul Published: 2025-06-26T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [gemma](), [Open Source](), [AI Development](), [llama.cpp](), [MLX](), [Ollama](), [transformers.js](), [GPU](), [Hardware](), [timm](), [asr](), [Embeddings]() Tags: [ai](), [artificial-intelligence](), [audio](), [community](), [embeddings](), [gemma](), [gpu](), [hardware](), [implementation](), [llama-cpp](), [llm](), [mlx](), [multimodal](), [ollama](), [open-source](), [release](), [research](), [speech](), [timm](), [transformers](), [transformers-js](), [translation](), [vision](), [vlm]() ### AI overview This article announces the availability of Gemma 3n in major open-source libraries and presents practical usage and fine-tuning examples. It describes the model variants, memory-efficient hardware requirements, multimodal audio and vision encoders, speech-to-text and translation capabilities, and architectural features including MatFormer and Per-Layer Embeddings. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Google I/O 2025: AI developments and implications for Android developers DevFeed: [Google I/O 2025: AI developments and implications for Android developers]() Original publisher: [Read original article]() Author: blundell Published: 2025-05-23T12:47:47Z Content type: article Language: en Sources: [Blundell]() Topics: [Artificial Intelligence](), [Android](), [Google](), [On-device AI](), [Google AI](), [gemma]() Tags: [2025](), [ai](), [android](), [androiddev](), [blog-post](), [developer](), [google](), [intermediate](), [reference]() ### AI overview This article reviews Google I/O 2025 keynote themes related to Gemini, on-device AI, the Gemma family, and AI-assisted Android development. It also discusses reported growth in Google's processed token volume and the implications for Android developers. ### Source excerpt The intro before the intro. Like every year I watched the keynote & developer keynote with excitement, taking my usual notes and reactive thoughts as it streams. This year though instead of myself turning those thoughts into a blog post, I asked Gemini to do it! This post is the outcome of using Gemini's new [...] The post Google I/O 2025: AI Unleashed - What Android Devs Need to Know! first appeared on Blundell. ## Getting Started with Gemma 3 LLM on Android for On-Device Inference DevFeed: [Getting Started with Gemma 3 LLM on Android for On-Device Inference]() Original publisher: [Read original article]() Author: blundell Published: 2025-03-12T22:11:14Z Content type: tutorial Language: en Sources: [Blundell]() Topics: [gemma](), [On-device AI](), [Large Language Model](), [Android](), [Inference](), [MediaPipe](), [App](), [Fine-tuning]() Tags: [android](), [androiddev](), [fine-tuning](), [gemma](), [inference](), [intermediate](), [llm](), [mediapipe](), [on-device](), [reference](), [tutorial]() ### AI overview A tutorial for integrating the Gemma 3 1B open-weight language model into an Android app for on-device inference. It covers downloading the model after installation, using MediaPipe for inference, and the trade-offs involving model size, performance, and device compatibility. ### Source excerpt This post gets you started with the new Gemma 3 model for on-device inference. Giving you the simplest steps to get started with AI on Android. Gemma 3 1B is a new model size in the Gemma family of open weight models. When deploying small language models (SLMs) in production settings, models need to be small [...] The post Get started with Gemma 3 LLM on Android now! first appeared on Blundell. ## Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM DevFeed: [Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM]() Original publisher: [Read original article]() Author: Aritra Roy Gosthipaty; merve; Pedro Cuenca; Vaibhav Srivastav Published: 2025-03-12T00:00:00Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [gemma](), [Google](), [LLMs](), [long-context](), [multimodal](), [Open Source]() Tags: [8k](), [artificial-intelligence](), [community](), [gemma](), [google](), [llm](), [long-context](), [multimodal](), [nlp](), [open-source](), [research](), [vlm]() ### AI overview Google introduces Gemma 3, an open-weight language model family ranging from 1B to 27B parameters. Larger variants support image and text inputs, context windows up to 128k tokens, and more than 140 languages, with pretrained and instruction-tuned versions available through Hugging Face. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## PaliGemma 2 Mix - New Instruction Vision Language Models by Google DevFeed: [PaliGemma 2 Mix - New Instruction Vision Language Models by Google]() Original publisher: [Read original article]() Author: merve; Aritra Roy Gosthipaty; Andreas P. Steiner Published: 2025-02-19T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [vlm](), [Fine-tuning](), [Google](), [gemma](), [object-detection](), [datasets]() Tags: [artificial-intelligence](), [datasets](), [demo](), [fine-tuning](), [gemma](), [google](), [llm](), [multimodal](), [object-detection](), [ocr](), [open-source](), [vision](), [vlms]() ### AI overview Google's PaliGemma 2 mix models are fine-tuned on a mixture of vision-language tasks, including OCR, image captioning, visual question answering, document understanding, object detection, and image segmentation. The article explains how the mix models indicate the performance of pretrained PaliGemma 2 checkpoints after fine-tuning and describes their prompting approach. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Hugging Face models in Amazon Bedrock DevFeed: [Hugging Face models in Amazon Bedrock]() Original publisher: [Read original article]() Author: Simon Pagezy; Philipp Schmid; Jeff Boudier; Violette Published: 2024-12-09T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [Amazon Bedrock](), [hugging face](), [Amazon SageMaker JumpStart](), [gemma](), [Generative AI](), [Open Source](), [Google]() Tags: [amazon-bedrock](), [amazon-sagemaker](), [amazon-sagemaker-jumpstart](), [api](), [artificial-intelligence](), [aws](), [bedrock](), [cloud](), [deployment](), [gemma](), [generative-ai](), [hugging-face](), [open-source](), [partnerships]() ### AI overview This tutorial explains how to deploy open Hugging Face models, including Google Gemma 2 27B Instruct, through the Amazon Bedrock Marketplace. It covers model selection, deployment, endpoint configuration, Bedrock API usage, and cleanup, with model endpoints managed by Amazon SageMaker JumpStart. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Welcome PaliGemma 2 - New vision language models by Google DevFeed: [Welcome PaliGemma 2 - New vision language models by Google]() Original publisher: [Read original article]() Author: merve; Andreas P. Steiner; Pedro Cuenca; Aritra Roy Gosthipaty Published: 2024-12-05T00:00:00Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [Google](), [vlm](), [Fine-tuning](), [gemma](), [datasets](), [Open Source](), [Machine learning]() Tags: [artificial-intelligence](), [data](), [demo](), [fine-tuning](), [gemma](), [google](), [image](), [llm](), [models](), [multimodal](), [open-source](), [release](), [research](), [transformers](), [vision](), [vlm]() ### AI overview PaliGemma 2 is Google's new vision-language model family, combining a SigLIP image encoder with Gemma 2 language models. It adds 3B, 10B, and 28B variants, multiple input resolutions, open model repositories, Transformers integration, fine-tuning scripts, and a visual question answering demo. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Announcing New Hugging Face and KerasHub integration DevFeed: [Announcing New Hugging Face and KerasHub integration]() Original publisher: [Read original article]() Author: Aritra Roy Gosthipaty Published: 2024-07-10T00:00:00Z Content type: news Language: en Sources: [Hugging Face - Blog]() Topics: [hugging face](), [Keras](), [Transformers](), [gemma](), [llama](), [Open Source]() Tags: [gemma](), [hugging-face](), [json](), [keras](), [llama](), [nlp](), [open-source](), [open-source-collab](), [pytorch](), [tensorflow](), [transformers]() ### AI overview The article announces an integration between Hugging Face Transformers and KerasHub through a shared model save format. It allows KerasHub users to load many Transformers checkpoints, initially including Gemma, Llama 3, and PaliGemma, and use them with TensorFlow, JAX, or PyTorch backends. The integration handles conversion of configuration variables, weight names, and tokenizer vocabularies internally. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Google Cloud TPUs made available to Hugging Face users DevFeed: [Google Cloud TPUs made available to Hugging Face users]() Original publisher: [Read original article]() Author: Simon Pagezy; Michelle Habonneau; Philipp Schmid; Alvaro Moran Published: 2024-07-09T00:00:00Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [inference-endpoints](), [Sovereign AI](), [Google Cloud Platform (GCP)](), [hugging face](), [spaces](), [optimum](), [tgi](), [gemma](), [llama](), [model-deployment](), [Latency](), [Hardware]() Tags: [gcp](), [gemma](), [google-cloud](), [hardware](), [hugging-face](), [inference](), [inference-endpoints](), [latency](), [llama](), [open-source](), [optimum](), [partnerships](), [performance](), [spaces](), [tgi](), [tpu]() ### AI overview Hugging Face announces that Google Cloud TPUs are available for Inference Endpoints and Spaces. Google TPU v5e configurations can deploy supported models through managed infrastructure, while Optimum TPU and Text Generation Inference help train and serve models on TPUs. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Welcome Gemma 2 - Google's new open LLM DevFeed: [Welcome Gemma 2 - Google's new open LLM]() Original publisher: [Read original article]() Author: Philipp Schmid; Omar Sanseviero; Pedro Cuenca; Lewis Tunstall; Tom Aarsen; Vaibhav Srivastav Published: 2024-06-27T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [gemma](), [Large Language Model](), [Google](), [Open Source](), [Fine-tuning](), [rlhf](), [Transformer]() Tags: [community](), [fine-tuning](), [gcp](), [gemma](), [google](), [llm](), [nlp](), [open-source](), [research](), [rlhf](), [tokens](), [tpu](), [transformers](), [warp]() ### AI overview The article introduces Gemma 2, Google's open large language model family available in 9-billion- and 27-billion-parameter sizes, with base and instruction-tuned variants. It describes the models' training data, permissive licensing, architectural improvements, TPU-based training, and instruction-tuning methods including supervised fine-tuning, distillation, RLHF, and model merging. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## CodeGemma - an official Google release for code LLMs DevFeed: [CodeGemma - an official Google release for code LLMs]() Original publisher: [Read original article]() Author: Pedro Cuenca; Omar Sanseviero; Vaibhav Srivastav; Philipp Schmid; Mishig ᠮᠢᠰᠾᠢᠭ; Loubna Ben Allal Published: 2024-04-09T00:00:00Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [gemma](), [Large Language Model](), [code-completion](), [Google](), [hugging face](), [AI Development](), [Transformers](), [AI Chat](), [Benchmark](), [inference-endpoints](), [Cloud](), [Java]() Tags: [artificial-intelligence](), [c-plus-plus](), [cloud](), [code-completion](), [community](), [evaluation](), [gcp](), [gemma](), [google](), [hugging-face](), [inference-endpoints](), [java](), [javascript](), [llm](), [llms](), [nlp](), [open-source](), [research](), [transformers]() ### AI overview Google's CodeGemma release introduces open-access 2B and 7B code-specialist LLMs, including base and instruction-tuned variants. The models support code infilling, completion, generation, code understanding, conversational use, and mathematical reasoning, with integrations across the Hugging Face ecosystem and Google Cloud. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science.