25 articles tagged with “fine-tuning”.
Google DeepMind and GovTech Singapore are building a fine-tuned, lightweight on-device Gemma model to intercept conversational scams in private chats with no cloud data egress.
A Hugging Face Blog post introduces Falcon-Emirati, a language model focused on learning the Emirati dialect along with its cultural context and nuance.
Reflection has debuted Beam, an open-weight AI model aimed at enterprises and sovereign nations, positioned to rival Chinese models at lower compute cost.
AWS describes fine-tuning a small LLM search agent using multi-turn reinforcement learning on Amazon SageMaker AI, aiming for frontier-model reliability at lower latency and cost.
AWS presents an architecture combining Amazon EKS, EFA, and S3 to scale Mixture-of-Experts reinforcement learning, reporting a 40% increase in aggregate rollout throughput for RLHF and GRPO training.
AWS details how to use SkyRL on SageMaker HyperPod to post-train a Qwen3-VL-8B vision-language model with GRPO, covering setup, job execution, and adapter hosting.
AWS presents a decision framework for selecting generative AI customization methods, spanning prompt engineering, RAG, fine-tuning, continued pre-training, and Amazon Nova Forge.
Fyxer developed an AI executive assistant on OpenAI models, using fine-tuning, memory, and user feedback to sort inboxes and draft emails matching each user's voice.
Garry Tan of Y Combinator wants smaller US open-weight AI labs to apply distillation techniques on American frontier models, expanding the pool of open-weight alternatives that aren't Chinese.
Anthropic released a report alleging persistent distillation attacks by China-based AI companies, which it says have escalated recently amid intensifying competition.
This article details the approach used to fine-tune a 350 million parameter model to generate better structured outputs efficiently.
The latest version of Gemini Omni, 1.1 Flash, introduces features that provide developers with greater control in their building processes.
The article discusses the methods for training and fine-tuning multi-vector embedding models with Sentence Transformers to optimize representation learning.
Nvidia research indicates that the harness around an AI agent, including fine-tuning, can drive reliable performance even when the base model is not especially capable at the task.
An AWS blog post details how to build custom multi-turn reward functions for Amazon Nova Forge, run model-generated code safely, and instrument reward components.
Writer introduced a new AI model and an upgraded harness designed to contain token costs, built as a post-training variation on Z.ai's open source GLM-5.2 model.
ONESTRUCTION, advised by the AWS Generative AI Innovation Center, built Ishigaki-IDS, a foundation model for construction and BIM workflows using synthetic data and a three-stage training pipeline on Amazon EC2.
Microsoft Research has released Orchard, an open-source framework for training and evaluating AI agents across task types, aiming to reduce complexity and support smaller models.
An AWS post introduces Self-Distilled Reasoning (SDR), an approach for adding reasoning traces to supervised fine-tuning datasets that lack them, validated across three benchmarks with Amazon Nova.
NVIDIA's Vera Rubin is positioned to reduce cost per token for post-training workloads through codesign, maximizing intelligence per dollar for agentic AI.
NVIDIA's Nemotron Labs highlights open models as a way for enterprises and nations to build AI they can trust, control and tailor to domain-specific needs.
Fine-tuning a large model used to mean owning a data centre. LoRA changed that by training a tiny fraction of the weights. Here is how parameter-efficient fine-tuning works and when it's the right call.
An AWS blog post explains four deployment patterns for serving Unsloth-quantized models on AWS infrastructure, covering EC2, SageMaker AI endpoints, EKS, and ECS.
Fine-tuning takes a general-purpose AI model and specializes it for your task, tone, or format by training it further on your examples. Here is when it helps — and when prompting or RAG is the better tool.
Fine-tuning a giant model used to require giant resources. LoRA showed you can adapt one by training a tiny number of extra parameters — and it became the default method for customizing open models.