https://techgazette.com.br/learn/fine-tuning/ New guides on training and fine-tuning, by the people who build it. Adapting models to a task. en 180 Tue, 13 Oct 2026 17:01:00 GMT https://medium.com/airbnb-engineering/castle-training-natural-language-search-before-the-first-real-query-3818ef8b4828?source=rss----53c7c27702d5---4 https://medium.com/airbnb-engineering/castle-training-natural-language-search-before-the-first-real-query-3818ef8b4828?source=rss----53c7c27702d5---4 Tue, 13 Oct 2026 17:01:00 GMT Airbnb Tech Training and fine-tuning Airbnb Tech — How we addressed the cold-start problem for Airbnb’s natural language search by jointly generating synthetic training data — queries and relevance labels — from de-identified booking and search signals. By: Wendy Ran Wei… https://machinelearning.apple.com/research/mix-dont-tune https://machinelearning.apple.com/research/mix-dont-tune Tue, 13 Oct 2026 00:00:00 GMT Apple Machine Learning Training and fine-tuning Apple Machine Learning — For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperpa… https://realpython.com/what-can-i-do-with-python/ https://realpython.com/what-can-i-do-with-python/ Sun, 11 Oct 2026 14:00:00 GMT Real Python Training and fine-tuning Real Python — What can I do with Python? Build software, train AI, automate chores, and drive robots, plus the tools and projects to start with. https://www.databricks.com/blog/post-training-production-how-tinyfish-runs-its-web-native-model-databricks-ai-runtime https://www.databricks.com/blog/post-training-production-how-tinyfish-runs-its-web-native-model-databricks-ai-runtime Fri, 09 Oct 2026 16:32:00 GMT Databricks Training and fine-tuning Databricks — TinyFish builds infrastructure for enterprises that need agents to work across the live web. Its Search, Fetch, Browser... https://aws.amazon.com/blogs/compute/scaling-rl-rollouts-with-firecracker-on-amazon-ec2-metal/ https://aws.amazon.com/blogs/compute/scaling-rl-rollouts-with-firecracker-on-amazon-ec2-metal/ Fri, 09 Oct 2026 14:38:00 GMT AWS Compute Training and fine-tuning AWS Compute — Reinforcement learning at scale runs thousands of isolated rollout sandboxes in parallel, and packing more of them onto each host lowers your cost per training step. This post shows how to tune Firecracker microVM densit… https://www.digitalocean.com/community/tutorials/should-you-use-spot-or-on-demand-gpus-for-model-training https://www.digitalocean.com/community/tutorials/should-you-use-spot-or-on-demand-gpus-for-model-training Fri, 09 Oct 2026 00:00:00 GMT DigitalOcean Tutorials Training and fine-tuning DigitalOcean Tutorials — Spot vs on-demand GPUs for model training: measured reclaim and resume costs on MI355X and B300, and the break-even discount at which spot actually saves money. https://stripe.dev/blog/training-llms-for-risk-assessment https://stripe.dev/blog/training-llms-for-risk-assessment Fri, 09 Oct 2026 00:00:00 GMT Stripe Developers Training and fine-tuning Stripe Developers — SFT helps Stripes make more precise risk assessments. We explain the training approach and investigate what the model learns about legitimate businesses. https://qdrant.tech/blog/jevjitsu/ https://qdrant.tech/blog/jevjitsu/ Thu, 08 Oct 2026 00:00:00 GMT Qdrant Training and fine-tuning Qdrant — Classification is one of the oldest problems in machine learning. Unlike modern decoding transformers, most classification models were non-autoregressive by nature. Before Jev, the common approaches were training your ow… https://www.digitalocean.com/community/tutorials/agent-observability-evaluation-signals https://www.digitalocean.com/community/tutorials/agent-observability-evaluation-signals Thu, 08 Oct 2026 00:00:00 GMT DigitalOcean Tutorials Training and fine-tuning DigitalOcean Tutorials — Signals flags the AI agent conversations that went wrong. It watches only the agents you turn it on for, hides personal details, keeps the data in your region, and never uses it to train AI for anyone else. It found all… https://rocm.blogs.amd.com/artificial-intelligence/primus-hybrid-llm/README.html https://rocm.blogs.amd.com/artificial-intelligence/primus-hybrid-llm/README.html Thu, 08 Oct 2026 00:00:00 GMT AMD ROCm Training and fine-tuning AMD ROCm — In this blog you will learn how to pre-train hybrid LLMs from scratch with Primus on AMD Instinct™ MI355X GPUs. In particular, we will cover how to declare a hybrid layer stack with a single configuration string, how thr… https://developer.nvidia.com/blog/scale-bitwise-deterministic-pretraining-with-nvidia-megatron-core/ https://developer.nvidia.com/blog/scale-bitwise-deterministic-pretraining-with-nvidia-megatron-core/ Tue, 06 Oct 2026 19:58:00 GMT NVIDIA Developer Training and fine-tuning NVIDIA Developer — Bitwise determinism makes large-scale pretraining easier to debug, validate, and resume reproducibly. These benefits become especially valuable when training... https://openai.com/index/advancing-computer-use-with-ironclad https://openai.com/index/advancing-computer-use-with-ironclad Tue, 06 Oct 2026 10:00:00 GMT OpenAI Training and fine-tuning OpenAI — Learn how OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows to advance computer use for professional work. https://launchdarkly.com/blog/machine-learning-pipeline-architecture/ https://launchdarkly.com/blog/machine-learning-pipeline-architecture/ Sat, 03 Oct 2026 14:02:00 GMT LaunchDarkly Training and fine-tuning LaunchDarkly — Learn how machine learning pipeline architecture connects data validation, feature engineering, training, deployment, guarded rollouts, and monitoring. https://aws.amazon.com/blogs/machine-learning/fine-tune-a-search-agent-with-multi-turn-rl-on-amazon-sagemaker-ai/ https://aws.amazon.com/blogs/machine-learning/fine-tune-a-search-agent-with-multi-turn-rl-on-amazon-sagemaker-ai/ Fri, 02 Oct 2026 15:44:00 GMT AWS Machine Learning Training and fine-tuning AWS Machine Learning — Fine-tuning teaches a small search agent your tools and environment, giving it the reliability of a frontier model at lower latency and cost. In this post, we fine-tune an LLM-powered search agent with multi-turn reinfor… https://wf.coreweave.com/blog/why-open-models-can-win-on-enterprise-cost-and-control https://wf.coreweave.com/blog/why-open-models-can-win-on-enterprise-cost-and-control Fri, 02 Oct 2026 14:12:00 GMT CoreWeave Training and fine-tuning CoreWeave — See how enterprise teams cut inference costs and keep control of fine-tuning, distillation, and guardrails by running open models on their own infrastructure. https://aws.amazon.com/blogs/machine-learning/how-uniopen-customized-amazon-nova-to-their-retail-moderation-policies-for-production-deployment/ https://aws.amazon.com/blogs/machine-learning/how-uniopen-customized-amazon-nova-to-their-retail-moderation-policies-for-production-deployment/ Thu, 01 Oct 2026 15:33:00 GMT AWS Machine Learning Training and fine-tuning AWS Machine Learning — See how uniopen, a retail platform from Taiwan's Uni-President Enterprises Group, adapted Amazon Nova 2 Lite to its content-moderation policies using supervised fine-tuning in Amazon SageMaker AI and prompt optimization.… https://developer.nvidia.com/blog/fine-tuning-nvidia-nemotron-for-saudi-arabic-dialects-with-a-path-to-other-languages/ https://developer.nvidia.com/blog/fine-tuning-nvidia-nemotron-for-saudi-arabic-dialects-with-a-path-to-other-languages/ Thu, 01 Oct 2026 05:00:00 GMT NVIDIA Developer Training and fine-tuning NVIDIA Developer — Automatic speech recognition must handle how people actually speak, not only the languages and styles that dominate pretraining data. Regional dialects and... https://rocm.blogs.amd.com/software-tools-optimization/tracelens-analysis-agent/README.html https://rocm.blogs.amd.com/software-tools-optimization/tracelens-analysis-agent/README.html Wed, 30 Sep 2026 00:00:00 GMT AMD ROCm Training and fine-tuning AMD ROCm — GPUs are valuable resources, and it is imperative to make training and inference workloads on them as efficient as possible. Bottlenecks in these workloads can arise from multiple sources, and mitigations vary depending… https://rocm.blogs.amd.com/artificial-intelligence/sim2real-rl-instinct/README.html https://rocm.blogs.amd.com/artificial-intelligence/sim2real-rl-instinct/README.html Tue, 29 Sep 2026 00:00:00 GMT AMD ROCm Training and fine-tuning AMD ROCm — Training a policy in simulation and transferring those weights to a real robot (sim2real) is a highly desirable goal in physical AI. Simulation scales data collection far beyond what a single robot can provide, but misma… https://s46486.pcdn.co/blog/rl-environments-for-llm-agents-design-rewards-and-validation/ https://s46486.pcdn.co/blog/rl-environments-for-llm-agents-design-rewards-and-validation/ Mon, 28 Sep 2026 23:08:00 GMT Snorkel AI Training and fine-tuning Snorkel AI — TLDR: An agent, by definition, can take actions and is more than just a language model. The model is only one part of the system, and is only one element that you are training. The environment determines what the agent c… https://snorkel.ai/blog/rl-environments-for-llm-agents-design-rewards-and-validation/ https://snorkel.ai/blog/rl-environments-for-llm-agents-design-rewards-and-validation/ Mon, 28 Sep 2026 23:08:00 GMT Snorkel AI Training and fine-tuning Snorkel AI — TLDR: An agent, by definition, can take actions and is more than just a language model. The model is only one part of the system, and is only one element that you are training. The environment determines what the agent c… https://openai.com/index/towards-safety-cases-for-frontier-ai-training https://openai.com/index/towards-safety-cases-for-frontier-ai-training Mon, 28 Sep 2026 19:00:00 GMT OpenAI Training and fine-tuning OpenAI — Our early guidelines for safety cases in frontier AI training cover technical safeguards, operational practices, and investigating misalignment incidents https://aws.amazon.com/blogs/machine-learning/automating-amazon-textract-adapter-lifecycle-management-across-accounts/ https://aws.amazon.com/blogs/machine-learning/automating-amazon-textract-adapter-lifecycle-management-across-accounts/ Mon, 28 Sep 2026 15:49:00 GMT AWS Machine Learning Training and fine-tuning AWS Machine Learning — Learn how to operationalize Amazon Textract Custom Queries adapters for production: infrastructure as code with AWS CloudFormation and Terraform, a cross-account adapter promotion process, a pre-classification routing pa… https://rocm.blogs.amd.com/artificial-intelligence/verl_0.9.0_rocm7.15/README.html https://rocm.blogs.amd.com/artificial-intelligence/verl_0.9.0_rocm7.15/README.html Mon, 28 Sep 2026 00:00:00 GMT AMD ROCm Training and fine-tuning AMD ROCm — In Scaling RL with verl on AMD Instinct™ MI355X, we walked through verl’s Fully Async Policy trainer on AMD Instinct™ MI355X GPUs. That post used verl 0.7.1.amd0 on ROCm™ 7.0.2, with a 4+4 GPU split for GRPO on Qwen2.5-V… https://aws.amazon.com/blogs/machine-learning/accelerate-multimodal-rl-training-with-skyrl-on-amazon-sagemaker-hyperpod/ https://aws.amazon.com/blogs/machine-learning/accelerate-multimodal-rl-training-with-skyrl-on-amazon-sagemaker-hyperpod/ Fri, 25 Sep 2026 16:18:00 GMT AWS Machine Learning Training and fine-tuning AWS Machine Learning — Learn how to run SkyRL, an open-source reinforcement learning framework, on Amazon SageMaker HyperPod to post-train a Qwen3-VL-8B vision-language model with GRPO. This walkthrough covers building the container image, lau… https://cloud.google.com/blog/topics/developers-practitioners/best-practices-guide-for-customizing-gemini-models/ https://cloud.google.com/blog/topics/developers-practitioners/best-practices-guide-for-customizing-gemini-models/ Fri, 25 Sep 2026 16:00:00 GMT Google Cloud AI & ML Training and fine-tuning Google Cloud AI & ML — Reinforcement learning (RL) has been a keystone of modern LLM post-training, but it demands large training clusters and access to model internals that external customers can't have with proprietary models like Gemini. So… https://aws.amazon.com/blogs/machine-learning/multi-region-training-with-amazon-sagemaker-hyperpod-and-qumulo/ https://aws.amazon.com/blogs/machine-learning/multi-region-training-with-amazon-sagemaker-hyperpod-and-qumulo/ Fri, 25 Sep 2026 15:49:00 GMT AWS Machine Learning Training and fine-tuning AWS Machine Learning — Amazon SageMaker HyperPod and Cloud Native Qumulo let you place training compute in one AWS Region while keeping your dataset in another. This post shares the architecture and validation results from a cross-Region train… https://developer.nvidia.com/blog/efficient-moe-training-for-biological-foundation-models/ https://developer.nvidia.com/blog/efficient-moe-training-for-biological-foundation-models/ Thu, 24 Sep 2026 15:00:00 GMT NVIDIA Developer Training and fine-tuning NVIDIA Developer — As language models grow, scaling dense architectures becomes increasingly expensive. In a dense transformer, every token passes through every layer, so adding... https://developers.googleblog.com/reproducing-olmo-3-7b-pre-training-in-maxtext-case-study-of-large-scale-training-on-tpus/ https://developers.googleblog.com/reproducing-olmo-3-7b-pre-training-in-maxtext-case-study-of-large-scale-training-on-tpus/ Thu, 24 Sep 2026 00:00:00 GMT Google for Developers Training and fine-tuning Google for Developers — The MaxText team successfully reproduced Ai2’s Olmo 3 7B language model from scratch on Google Cloud TPUs using JAX/XLA, precisely matching the original PyTorch-on-GPU reference across pre-training and mid-training stage… https://machinelearning.apple.com/research/latent-space-distillation https://machinelearning.apple.com/research/latent-space-distillation Thu, 24 Sep 2026 00:00:00 GMT Apple Machine Learning Training and fine-tuning Apple Machine Learning — System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the representation the l… https://www.lancedb.com/blog/practical-llm-pretraining https://www.lancedb.com/blog/practical-llm-pretraining Wed, 23 Sep 2026 21:38:00 GMT LanceDB Training and fine-tuning LanceDB — Training a GPT-2-like model from raw text in 25 minutes with LanceDB, using one table for curation, tokenization, shuffling, packing, training, and analysis. https://developer.nvidia.com/blog/validate-gpu-cluster-readiness-before-ai-workloads-land/ https://developer.nvidia.com/blog/validate-gpu-cluster-readiness-before-ai-workloads-land/ Wed, 23 Sep 2026 19:45:00 GMT NVIDIA Developer Training and fine-tuning NVIDIA Developer — A GPU cluster can pass every health check and still fail to run an AI workload. Even when every GPU, network link, and pod reports healthy, a 512-GPU training... https://ubuntu.com//blog/fine-tune-your-own-custom-llm-with-canonical-charmed-kubeflow-and-feast https://ubuntu.com//blog/fine-tune-your-own-custom-llm-with-canonical-charmed-kubeflow-and-feast Wed, 23 Sep 2026 15:09:00 GMT Ubuntu Training and fine-tuning Ubuntu — So you want your own pet LLM huh? Knowing where to start can be quite tricky, so luckily for you I’ve put together this end-to-end guide. It’ll get you not just started; you’ll end with a fully working chatbot that you’v… https://www.together.ai/blog/how-to-train-your-own-jev https://www.together.ai/blog/how-to-train-your-own-jev Wed, 23 Sep 2026 00:00:00 GMT Together AI Training and fine-tuning Together AI — We just launched our own Jev-like classifier, together/Tev1-4B-experimental, on top of Qwen3.5 4B on Together’s serverless platform. In this blog post we’ll show you how to fine-tune your own version! https://www.datadoghq.com/blog/ai/investigate-production-alerts/ https://www.datadoghq.com/blog/ai/investigate-production-alerts/ Wed, 23 Sep 2026 00:00:00 GMT Datadog Training and fine-tuning Datadog — Learn how we fine-tuned Qwen3.5-9B into a specialized agent for change attribution that achieved 87% of GLM-5.3’s Recall@5 roughly 5% of the investigation cost. https://rocm.blogs.amd.com/software-tools-optimization/logprob-debug/README.html https://rocm.blogs.amd.com/software-tools-optimization/logprob-debug/README.html Wed, 23 Sep 2026 00:00:00 GMT AMD ROCm Training and fine-tuning AMD ROCm — In online reinforcement learning (RL), a language model generates responses, receives rewards, and updates its weights to improve future responses. Many systems split this loop between a rollout engine, which generates t…