Search AI News
Find articles from 100+ AI sources
Found 298 results for "LLaMA"
LinkedIn Highlights, Dec 2024
Welcome to LinkedIn Highlights!Each month, I'll share my five top-performing LinkedIn posts, bringing you the…
We Looked at 78 Election Deepfakes. Political Misinformation is not an AI Problem.
AI-generated misinformation was one of the top concerns during the 2024 U.S. presidential election. In…
The Open-Source Toolkit for Building AI Agents
June ‘25 update: Released an updated map with new frameworks and repositories since this post was published…
You could have designed state of the art positional encoding
Back to Articles You could have designed state of the art positional encoding Published November 25, 2024…
Introducing Transluce — A Letter from the Founders
We are launching an independent research lab that builds open, scalable technology for understanding AI…
Releasing Outlines-core 0.1.0: structured generation in Rust and Python
Back to Articles Releasing Outlines-core 0.1.0: structured generation in Rust and Python Published October…
Accelerate 1.0.0
Back to Articles Accelerate 1.0.0 Published September 13, 2024 Update on GitHub Upvote 54 +48 Zachary Mueller…
What's Missing From LLM Chatbots: A Sense of Purpose
LLM-based chatbots’ capabilities have been advancing every month. These improvements are mostly measured by…
Fine-tune FLUX.1 with an API
Replicate Blog Fine-tune FLUX.1 with an API Posted September 9, 2024 by zeke Info You can now fine-tune…
Fine-tune FLUX.1 to create images of yourself
Replicate Blog Fine-tune FLUX.1 to create images of yourself Posted August 30, 2024 by zeke Info Update (May…
Competing in search
A search engine is a vast mechanical Turk - a reinforcement learning engine that uses human activity to…
Introduction to ggml
Back to Articles Introduction to ggml Published August 13, 2024 Update on GitHub Upvote 295 +289 Xuan-Son…
The Convergence of Proprietary and Open Source LLMs
A few months ago, I wrote about building LLM systems with self-hosted, open source models that beat…
Tool Use, Unified
NousResearch/Hermes-2-Pro-Llama-3-8B Text Generation • 8B • Updated Sep 14, 2024 • 10.8k • 454
Serverless Inference with Hugging Face and NVIDIA NIM
meta-llama/Meta-Llama-3-8B-Instruct Text Generation • 8B • Updated Jun 18, 2025 • 1.43M • 4.7k
Announcing New Hugging Face and KerasHub integration
Back to Articles Announcing New Hugging Face and KerasHub integration Published July 10, 2024 Update on…
XLSCOUT Unveils ParaEmbed 2.0: a Powerful Embedding Model Tailored for Patents and IP with Expert Support from Hugging Face
Back to Articles XLSCOUT Unveils ParaEmbed 2.0: a Powerful Embedding Model Tailored for Patents and IP with…
Apple intelligence and AI maximalism
No-one outside Apple has really used any Apple Intelligence features yet. It won't launch until the autumn,…
Ways to think about AGI
The manuscript for ‘A Logic Named Joe’ In 1946, my grandfather, writing as ‘Murray Leinster’,…
How to Beat Proprietary LLMs With Smaller Open Source Models
IntroductionWhen designing systems that use text generation models, many people first turn to proprietary…
A Guide to Structured Generation Using Constrained Decoding
IntroductionWe often want specific outputs when interacting with generative language models. This is…
Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon
Back to Articles Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon Published April 3, 2024 Update…
GaLore: Advancing Large Model Training on Consumer-grade Hardware
Back to Articles GaLore: Advancing Large Model Training on Consumer-grade Hardware Published March 20, 2024…
Quanto: a PyTorch quantization backend for Optimum
Back to Articles Quanto: a PyTorch quantization backend for Optimum Published March 18, 2024 Update on GitHub…