Posts
Hugging Face
Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler <a class="archive-item-link" href="https://huggingface.co/blog/torch-mlp-fusion target="_blank" rel="noopener noreferrer">Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP</a> Harness, Scaffold, and the AI Agent Terms Worth Getting Right Unlocking asynchronicity in continuous batching Pallas for people who know JAX but not Kernels yet Mixture of Experts (MoEs) in Transformers Custom Kernels for All from Codex and Claude How to Use Multiple GPUs in Hugging Face Transformers: Device Map vs Tensor Parallelism Tokenization in Transformers v5: Simpler, Clearer, and More Modular Porting nanochat to Transformers: an AI modeling history lesson Welcome FLUX.2 - BFL’s new open image generation model 🤗 Supercharge your OCR Pipelines with Open Models Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers Welcome EmbeddingGemma, Google's new efficient embedding model Vision Language Model Alignment in TRL ⚡️ Efficient Multimodal Data Pipeline Gemma 3n fully available in the open-source ecosystem! KV Cache from scratch in nanoVLM SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data nanoVLM: The simplest repository to train your VLM in pure PyTorch Vision Language Models (Better, Faster, Stronger) Welcoming Llama Guard 4 on Hugging Face Hub Transformers backend integration in vLLM Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM SigLIP 2: A better multilingual vision language encoder PaliGemma 2 Mix - New Instruction Vision Language Models by Google 🚀 Deploying OLMo-7B with Text Generation Inference (TGI) on Hugging Face Spaces 🚀 Build a Qwen 2.5 VL API endpoint with Hugging Face spaces and Docker! Simplifying Alignment: From RLHF to Direct Preference Optimization (DPO) Timm ❤️ Transformers: Use any timm model with transformers Controlling Language Model Generation with NVIDIA's LogitsProcessorZoo Welcome PaliGemma 2 – New vision language models by Google Faster Text Generation with Self-Speculative Decoding Hugging Face Welcomes the Qwen2.5-Coder Series PyTorchModelHubMixin: Bridging the Gap for Custom AI Models on Hugging Face Hugging Face welcomes the Aya Expanse family of multilingual models 🧨 Diffusers welcomes Stable Diffusion 3.5 Large Llama can now see and run on your device - welcome Llama 3.2 Speedup Llama 3 70B with Speculative Decoding Speedup Llama 3 8B with Speculative Decoding Understanding Vector Quantization in VQ-VAE Building DoRA Support for Embedding Layers in PEFT How to communicate in a Pull Request? The Workflow of peft Announcing New Hugging Face and Keras NLP Integration Counting 'n' objects What is probability? Conditional Probability PyImageSearch
Step-by-Step Guide to Open-Source Implementation of Generative Fill: Part 1 ML Days in Tashkent — Day 1: City Tour ML Days in Tashkent — Day 2: Sprints and Sessions ML Days in Tashkent — Day 3: Demos and Workshops AugMix with KerasCV Breakdown (Part 1): Introduction to AugMix What Is Keras Core? DETR Breakdown Part 3: Architecture and Details DETR Breakdown Part 2: Methodologies and Algorithms DETR Breakdown Part 1: Introduction to DEtection TRansformers Introduction to Causality in Machine Learning Learning JAX in 2023: Part 3 — A Step-by-Step Guide to Training Your First Machine Learning Model with JAX Learning JAX in 2023: Part 2 — JAX’s Power Tools grad, jit, vmap, and pmap Learning JAX in 2023: Part 1 — The Ultimate Guide to Accelerating Numerical Computation and Machine Learning Automatic Differentiation Part 2: Implementation Using Micrograd Automatic Differentiation Part 1: Understanding the Math A Deep Dive into Transformers with TensorFlow and Keras: Part 1 A Deep Dive into Transformers with TensorFlow and Keras: Part 2 A Deep Dive into Transformers with TensorFlow and Keras: Part 3 Neural Machine Translation with Luong’s Attention Using TensorFlow and Keras Neural Machine Translation with Bahdanau’s Attention Using TensorFlow and Keras Neural Machine Translation Introduction to TFRecords Long Short-Term Memory Networks Introduction to RNNs with TensorFlow and Keras Fast Neural Network Training with Distributed Training and Google TPUs Computer Graphics and Deep Learning with NeRF using TensorFlow and Keras: Part 1 Computer Graphics and Deep Learning with NeRF using TensorFlow and Keras: Part 2 Computer Graphics and Deep Learning with NeRF using TensorFlow and Keras: Part 3 Keras
When Recurrence meets Transformers[4] Focal Modulation: A replacement for Self-Attention Investigating Vision Transformer representations[1] A Vision Transformer without Attention Augmenting convnets with aggregated attention Video Vision Transformer Train a Vision Transformer on small datasets Learning to tokenize in Vision Transformers Masked image modeling with Autoencoders[2] Neural Style Transfer with AdaINs Involutional neural networks 3D volumetric rendering with NeRF[3] 1: This tutorial won the Google Open Soruce Expert Prize.
2: This tutorial won the Google Open Soruce Expert Prize.
3: This tutorial won the TensorFlow community spotlight award.
4: This tutorial won the TensorFlow community spotlight award.
Weights and Biases
Ablations on NMT with attention | Part 4 Effective Approaches to Attention-based Neural Machine Translation | Part 3 Neural Machine Translation by Jointly Learning to Align and Translate | Part 2 An Introduction to Attention | Part 1 Enriching Word Vectors with Sub-word Information Sequence to Sequence with `tf.keras` Keras Tuner with W&B Show and Tell GloVe Word2Vec Survival of the Fittest CNN Model Under the hood of RNNs Under the hood of LSTMs Part 1: Deep Representations, a way towards neural style transfer Part 2: Deep Representations, a way towards neural style transfer Towards Representation Learning for an Image Retrieval Task Simple Ways to Tackle Class Imbalance Kaggle
SimCLR LanceDB
Training a Variational AutoEncoder from scratch with Lance file format Vector Arithmetic with LanceDB: An intro to Vector Embeddings Personal Space
Easy switching to backends in Keras Core with conda TensorFlow and GPU Character level language model RNN Similarity of neuron activations between similar classes C++ Progress Creating a static website in minutes Back Propagation in Batch Normalization Medium
[ML Story] My Keras Chronicles Hexato Tad Bit of Java MISC
Choosing Between SigLIP and CLIP for Language Image Pretraining Aritra Roy Gosthipaty - Deep Learning Associate at PyImageSearch </div> </div>