Hugging Face – Community Blogs

Community Articles

Back to Articles

The AI Copyright Debate: Are We Stifling Innovation?

Tutorial: Quantizing Llama 3+ Models for Efficient Deployment

AI Paradigms Explained: Instruct Models vs. Chat Models 🚀

How to Expand Your AI Music Generations of 30 Seconds to Several Minutes

🇪🇺✍️ EU AI Act: Systemic Risks in the First CoP Draft Comments ✍️🇪🇺

The Intersection of CTMU and QCI: Implementing Emergent Intelligence

Building an AI-powered search engine from scratch

Build Your Own AI Server at Home: A Cost-Effective Guide Using Pre-Owned Components

MotionLCM-V2: Improved Compression Rate for Multi-Latent-Token Diffusion

RLHF 101: A Technical Dive into RLHF

[Talk Arena](https://talkarena.org)

Multimodal RAG with Colpali, Milvus and VLMs

In Honour of This Year's NeurIPs Test of Time Paper Awardees

Power steering: Squeeze massive power from small LLMs

Exploring the Power of KaibanJS v0.11.0 🚀

Building a Custom Retrieval System with Motoko and Node.js

Finding Moroccan Arabic (Darija) in Fineweb 2

Running Your Custom LoRA Fine-Tuned MusicGen Large Locally

Building a Local Vector Database Index with Annoy and Sentence Transformers

Practical Consciousness Theory for AI System Design

Releasing QwQ-LongCoT-130K

They Said It Couldn’t Be Done

🐺🐦‍⬛ LLM Comparison/Test: 25 SOTA LLMs (including QwQ) through 59 MMLU-Pro CS benchmark runs

Building a MusicGen API to Generate Custom Music Tracks Locally

Optimizing Deep Learning Training Techniques

BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO

DeMo: Decoupled Momentum Optimization

Reverse Thinking Makes LLMs Stronger Reasoners

Accelerating Embedding & Reranking Models on AMD Using Infinity

Enable ChatGpt using Azure

Bridging the Gap Between Physical Numerical Simulations and Machine Learning: Introducing The Well

EuroLLM-9B

Rethinking Backpropagation: Thoughts on What's Wrong with Backpropagation

Is using a validation set useful for end-to-end learning in robotics?

Turning Home Assistant into an AI Powerhouse: Amy's Guide

SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning

Towards a Fully Arabic Retrieval-Augmented Generation (RAG) Pipeline:

Mastering Chain of Thought (CoT) Prompting for Practical AI Tasks

Use Models from the Hugging Face Hub in LM Studio

An Art Analysis by Mistral Pixtral 12B

Top 20 GitHub Repositories for Autonomous AI Agents in Software Development

Let’s make a generation of amazing image generation models

Zero to Hero with the TRL learning link bomb 💣

Can RLHF with Preference Optimization Techniques Help LLMs Surpass GPT4-Quality Models?

Making LLMs Smaller Without Breaking Them: A GLU-Aware Pruning Approach

Ultimate Guide to Website Crawling for Offline Use: Top 20 Methods

Build Your Own Browser-Based AI Coding Assistant with Gradio Lite and Transformers.js

Top 10 AI Debugging Prompts: A Comprehensive Guide

The Ultimate Guide to Managing Multiple Apps Visually: Open-Source Tools and Solutions

Dynamic Topic Modeling with RedPajama: A New Approach to Hierarchical Content Understanding

🤗 Serve any model with Inference Endpoints + Custom Handlers

Upgrading Kokoro: natural TTS for short bursts

AIGS: Generating Science from AI-Powered Automated Falsification

SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text

Medical Video Generation for Disease Progression Simulation

Conversational Medical AI: Ready for Practice

Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering

Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks

Eyes Slide-Move:Classic-Inpainting fill hole and complete missing iris

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

Introducing Observers: AI Observability with Hugging Face datasets through a lightweight SDK

An Internet Voting System Fatally Flawed in Creative New Ways

SpikingNeRF: Making Bio-inspired Neural Networks See through the Real World

Robust ASR Error Correction with Conservative Data Filtering

Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognition

Symbiotic Intelligence

Halo: Open Source Health Tracking with Wearables

Understanding the Algorithm of Thoughts: A Heuristic Approach Beyond LLMs

KaibanJS v0.10.0: Expanding AI Workflows with New Tools 🚀

StableV2V: Stablizing Shape Consistency in Video-to-Video Editing

Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations

The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use

Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions

Generative Agent Simulations of 1,000 People

That Chip Has Sailed: A Critique of Unfounded Skepticism Around AI for Chip Design

LLaVA-o1: Let Vision Language Models Reason Step-by-Step

Unlock the Power of AI in Your Browser with Transformers.js

Low Code Large Language Model Alignment

The Ultimate Guide to AI-Powered Browser Automation and Web Scraping

GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Image Similarity Data Visualization

The Beginners Guide to Cleaning a Dataset

Results: Converted Guide Images(eyes-closed and mouth-opened) with Flux.1 schenll img2img/inpaint

about 1 month ago

Better img2img results with Flux.1 schnell by using ScaleUp or Sharpen or FillColor pre-processing

Revisiting TemplateGSM: Advancing Mathematical Reasoning in Language Models with Template-based Data Generation

Releasing the largest multilingual open pretraining dataset

Solving NaN Tensors and Pickling Errors in a ZeroGPU Space

Hugging Face Welcomes the Qwen2.5-Coder Series

PyTorchModelHubMixin: Bridging the Gap for Custom AI Models on Hugging Face

Deploying Language Models on Azure Kubernetes: A Complete Beginner's Guide

GRID-6X : Layout for Seamless Image Assembly

Flux1.1 [pro] Ultra : Endpoint by BFL ⛵

SauerkrautLM's Multi-Phase Spectrum Training: A Technical Deep Dive

What We Learned About LLM/VLMs in Healthcare AI Evaluation:

Filtering single image super-resolution datasets with BHI

Recipe: Preparing Multilingual Speech Datasets for TTS Training

Flux1-schnell-Inpaint-Mask Guide

streamlit_supabase_auth_ui

Introducing FutureAI’s Masterpiece Architecture: Build AI-native Applications Leveraging Generative Personalization

Introducing GGUF-my-LoRA

Trick or ResNet Treat

Detoxifying the Commons

Experimenting with different training objectives for an AI evaluator

Building a GraphQL-powered TODO list AI Agent in n8n (Complete tutorial)

🚀 Exciting Announcement: Introducing HelpingAI-3B-reloaded!

VLM Visual Arts Analysis with DeepSeek Janus-1.3B

Product Recommendation using Image Similarity

Decoding Strategies in Large Language Models

Code a simple RAG from scratch

Shrewd’s Llama-Phishsense-1B: SOTA AI-Powered Phishing Detection

Visually Multilingual: Introducing mcdse-2b

Create Stunning Mockups with Your Logo Using Flux AI and Segmind

Towards Automated Penetration Testing: Introducing LLM Benchmark, Analysis, and Improvements

Introducing MotionCLR: Interactive Motion Editing

Hugging Face welcomes the Aya Expanse family of multilingual models

Accelerating LLM Inference: Fast Sampling with Gumbel-Max Trick

nanoJAXGPT: A pedagogical introduction to JAX/Equinox

Navigating Korean LLM Research #2: Evaluation Tools

Chat with any full website (not just a single page). Complete Tutorial

OCR Processing and Text in Image Analysis with DeepSeek Janus-1.3B

Navigating Korean LLM Research #1: Models

Aria: First Open Multimodal Native MoE Model

Allegro: Advanced Video Generation Model

🇮🇹🇯🇵🇧🇷 Generating multilingual instruction datasets with Magpie 🐦‍⬛

Advanced Flux Dreambooth LoRA Training with 🧨 diffusers

Turn your newsletters into a Podcast with NotebookLM

MedEmbed: Fine-Tuned Embedding Models for Medical / Clinical IR

AI is turning nuclear: a review

LLM ChatBots 3.0: Merging LLMs with Dynamic UI Elements

Occam’s Sheath: A Simpler Approach to AI Safety Guardrails

Mamba Out

OCR Processing and Text in Image Analysis with Florence-2-base and Qwen2-VL-2B

EmbeddingAlign RAG: Boosting QA Systems

ColFlor: Towards BERT-Size Vision-Language Document Retrieval Models

¡Lanzamiento de la Comunidad Latinoamericana de NLP en Hugging Face! 🌟

Unlocking the Power of Large Language Models (LLMs) for Business Applications

How to build a custom text classifier without days of human labeling

Organizing a Privacy-preserving Hackathon

Image Search with Text Prompt

bismillah

How to optimize your data labelling project with custom interfaces

A New Era in Multistep Enzyme Design

OpenAI o1 mind blowing Test

The insane waste of time and money in LLM token generation

Make a blog post with your Voice

Turn any FAQ into a chatbot in 5 minutes with Dify and GPT

Three Steps to Keep LogSeq in Sync with all Devices

Talk shows applause are manipulating you, says GPT - try it yourself!

Automating Healthcare AI with Aktiver: Transforming Data into Knowledge Graphs

Fancy Stateful Metaflow Service + UI on Google Colab ?

Model2Vec: Distill a Small Fast Model from any Sentence Transformer

New Image Generation Assistant on HuggingChat!

Inference Endpoints Changelog 🚀

dstack to manage clusters of on-prem servers for AI workloads with ease

Recoloring photos with diffusers

Democratization of AI, Open Source, and AI Auditing: Thoughts from the DisinfoCon Panel in Berlin

Efficient LLM Pretraining: Packed Sequences and Masked Attention

ILMAAM: Index for Language Models For Arabic Assessment on Multitasks

Optimizing Solar Panel Efficiency and Placement Using AI-Driven Project Management Tools

VLM Art Analysis

QLoRA with AutoRound: Cheaper and Better LLM Fine-tuning on Your GPU

Comparing Open-source and Proprietary LLMs in Medical AI

Little Paper Reviews & AutoCodeRover

Tiny Test Models

Fine-Tuning 1B LLaMA 3.2: A Comprehensive Step-by-Step Guide with Code

HTRflow - A tool for HTR and OCR

A Short Summary of Chinese AI Global Expansion

The Similarities Between Human Dreaming and Learning in Large Language Models (LLMs)

Ưu tiên có thể diễn giải thông qua Mô hình Phần thưởng Đa mục tiêu và Hỗn hợp Chuyên gia

Bài học đắng trong AI

Last Week in Medical AI: Top Research Papers/Models 🏅 (September 21 - September 27, 2024)

Artificial Collective Intelligence: Beyond AGI

Model Card Generator Interface: Crafting Clear Insights into AI Models

Exploring Name Diversity in Modern LLMs: A Grimdark Trilogy Experiment

wHy DoNt YoU jUsT uSe ThE lLaMa ToKeNiZeR??

Mastering Arabic NLP: Insights and Lessons from ArabicNLP Series

Performance Comparison: Llama-3.2 vs. Llama-3.1 LLMs and Smaller Models (3B, 1B) in Medical and Healthcare AI Domains 🩺🧬💊

Building a Custom Arabic Semantic Search Model with Arabic Matryoshka Embeddings for RAG Using Sentence Transformers

Evaluations with Chat Formats

🌟 Easy Fine-Tuning with Hugging Face SQL Console, Notebook Creator, and SFT

Does Daily Software Engineering Work Need Reasoning Models?

Document Similarity Search with ColPali

Making the spectrum of ‘openness’ in AI more visible

Recreating o1 at Home with Role-Play LLMs

Self Generative Systems (SGS) and Its Integration with AI Models

This Title Is Already Tokenized (Tokun P.2)

Fine-tuning Parler TTS on a Specific Language

"Diffusers Image Fill" guide

All LLMs Write Great Code, But Some Make (A Lot) Fewer Mistakes

Training Flux Locally on Mac

Improving performance with Arena Learning in post training

Fine Tuning a LLM Using Kubernetes with Intel® Gaudi® Accelerator

Introducing AISAK-O

Full Training Tutorial and Guide and Research For a FLUX Style

Fine-tuning a token classification model for legal data using Argilla and AutoTrain

Llama-3.1 8B Carrot - Capx AI

Getty Images Brings High-Quality, Commercially Safe Dataset to Hugging Face

LLM Inference at scale with TGI

Meet Yi-Coder: A Small but Mighty LLM for Code

Converting Models to Core ML

The Environmental Impacts of AI -- Primer

10 Star Webflow (no-code) Players Providing Premium Services

Selective fine-tuning of Language Models with Spectrum

Key Insights into the Law of Vision Representations in MLLMs

Extending Transformer layers as Painters to DiT's

To what extent are we responsible for our content and how to create safer Spaces?

Understanding Vector Quantization in VQ-VAE

DEMO: French Spoken Language Understanding with the new speech resources from NAVER LABS Europe

How to integrate Apify with Huggging Face

How to Use SSAST Model Weights in the HuggingFace Ecosystem?

Searching for better (Full) ImageNet ViT Baselines

Introducing AuraFace: Open-Source Face Recognition and Identity Preservation Models

Efficient Deep Learning: A Comprehensive Overview of Optimization Techniques 👐 📚

MicroJAX

2D Parallelism using Ray PyTorch

Social Bias NER with BERT

Easy, Fast, and Effective Topic Modeling For Beginners with FASTopic

Building DoRA Support for Embedding Layers in PEFT

How No-Code Platforms Are Making Tech More Accessible to Everyone

Processing Parquets 102

How to build an incremental Web Crawler with Apify

How to communicate in a Pull Request?

dstack: Your LLM Launchpad - From Fine-Tuning to Serving, Simplified

Is Prompt Caching the new RAG?

Using Writer Framework with Hugging Face Spaces

What are Embeddings and Vector Databases?

Extractive Question Answering with AutoTrain

How to get GPT to talk like a consultant

Web Scraping 102

Self-Hosting LLaMA 3.1 70B (or any ~70B LLM) Affordably

Tensor Parallelism

Web Scraping 101

Llama-3.1-Storm-8B: Improved SLM with Self-Curation + Model Merging

∞🧙🏼‍♂️AnyClassifier - Generating Synthetic Data For Text Classification

Data Formats 101

Processing Parquets 101

Outperforming Claude 3.5 Sonnet with Phi-3-mini-4k for graph entity relationship extraction tasks

I Trained a 2D Game Animation Generation Model to Create Complex, Cool Game Actions (Fully Open-Source)

Create Dynamic Typed Videos with 'Type Byte🐧'

Perspectives for first principles prompt engineering

Powering the Future: Be.Ta Labs’ Revolutionary 100% Solar-Powered AI Operation

What is Retrieval-based Voice Conversion WebUI?

BERT for Bias Detection in Text

RAG vs Fine-Tuning for LLMs: A Comprehensive Guide with Examples

Deploying Hugging Face models with Viam: Use models on any robot in the real world

How to Set Up and Run Ollama on a GPU-Powered VM (vast.ai)

Deploying a Private Hugging Face Model for Inference with RunPod and AnythingLLM (serverless)

The Workflow of PEFT

Parquet in Action: A Beginners Guide

20 New SDXL Fine Tuning Tests and Their Results (Better Workflow Obtained and Published)

Context Parallelism

⭐ PySpark and 🤗 Hugging Face Parquet Files

Advanced AI-Driven Code Analysis: A Multi-Agent Framework for Comprehensive Software Optimization

Bulleted Notes eBook Summary: A Different Way to Chat with PDF

Your AI, Everywhere

Unlocking Creativity with Text-to-Image Generation: Exploring LoRA Models and Styles [Generative Vision]

Batch size 30 AdamW vs Batch Size 1 Adafactor SDXL Training Comparison

The Myth of Running Out of Data: Why Infinite Math Makes AI Training Limitless

ArabicWeb24: Creating a High Quality Arabic Web-only Pre-training Dataset

Agentic Task Delegation - Making Agents whole again

HelpingAI2-6B : Revolutionizing Conversational AI with Emotional Intelligence

Creating and Uploading a Dataset with Unsloth: An Adventure in Wonderland

The case for specialized pre-training: ultra-fast foundation models for dedicated tasks

Local AI with Docker's Testcontainers

How to use Instruct Embeddings Correctly

9 Notable Quotes From Mark Zuckerberg's Essay in Favor of Open Source AI

Crazy Challenge: Run Llama 405B on a 8GB VRAM GPU

🔥 Argilla 2.0: the data-centric tool for AI makers 🤗

Clarity AI Upscaler Reproduction

Build static HTML spaces

Train a Llama model from scratch

Simulating Monte Carlo Algorithms With Gaussian Probability

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Encoding Video Locations with SatCLIP: A New Frontier in Geographic Machine Learning

Utilizing Gaussian Probability Space to Simulate Monte Carlo Algorithms with Particle Swarm Optimization

ZebraLogic: Benchmarking the Logical Reasoning Ability of Language Models

MobileNet Baselines

Abliterating Refusal and Code LLMs

Finetuning PaliGemma with AutoTrain

Announcing BigCodeBench-Hard, and More

AI and its Role in Revolutionizing Dating and Relationships

Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!

MMLU-PRO-ITA a new eval for Italian LLMs

Fine-tuning Mistral on Your Dataset

Fine Tuning TinyLlama for Text Generation with TRL

Ghost 8B Beta Released: Game-Changing Language Model

Gambling In The Probability Space

Taxonomy Completion with Embedding Quantization and an LLM-based Pipeline: A Case Study in Computational Linguistics

How to Optimize TTFT of 8B LLMs with 1M Tokens to 20s

Create a Diffusers-compatible Dataset for Stable Diffusion Fine-tuning

Bringing Open-Source Models to Spreadsheets 🚀

Introducing HelpingAI-Flash: Emotionally Intelligent Conversational AI for All Devices

Introduction to State Space Models (SSM)

Announcing Finance Commons and the Bad Data Toolbox: Pioneering Open Data and Advanced Document Processing

Mixedbread 🤝 deepset: Announcing our New German/English Embedding Model

Swarm Neural Networks (SNN) for Image Generation

Querying Datasets with the Datasets Explorer Chrome Extension

Deploy hundreds of open source models on one GPU using LoRAX

Structured Harm Reporting in AI: New Research Paper at AIES and DEFCON event!

Unleash ML Power on iOS: Apple Silicon Optimization Secrets

How OpenGPT 4o works

Market Research using AI Evolutionary Algorithms and Multimodal Regression

Introducing Ghost 8B Beta: A Game-Changing Language Model

The Rise of Agentic Data Generation

Mixture of Agents Model (MAM): An AI-Driven Full-Stack Development Team

Is AI carbon footprint worrisome?

Optimisation d'un système RAG pour la recherche sémantique

In-browser LLM app in pure Python: Gemini Nano + Gradio-Lite

Introducing HelpingAI-15B: Emotionally Intelligent Conversational AI

How to run Gemini Nano locally in your browser

MMLU-Pro-NoMath

RegMix: Data Mixture as Regression for Language Model Pre-training

MInference 1.0: 10x Faster Million Context Inference with a Single GPU

Enhancing Search Capabilities for Non-English Datasets in the Dataset Viewer

Introducing the Polish ASR Leaderboard (PAL) and Benchmark Intended Grouping of Open Speech (BIGOS) Corpora

Metric and Relative Monocular Depth Estimation: An Overview. Fine-Tuning Depth Anything V2 👐 📚

The Great LLM Showdown: Amy's Quest for the Perfect LLM

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡

arXiv实用技巧，如何让你的paper关注度变高？

Swarm Neural Networks: Revolutionizing Function and API Call Execution

_Repetita iuvant_: how to improve AI code generation

RAG using huggingface tools

GPM: Generative Password Manager

ColPali: Efficient Document Retrieval with Vision Language Models 👀

Advanced RAG: Fine-Tune Embeddings from HuggingFace for RAG

Image-based search engine

EU Training Data Transparency: A Proposal for a Sufficiently Detailed Summary 📑📚🖼️🇪🇺

Transformers

Systems of Representation Are All You Need

A Guide to Designing New Functional Proteins and Improving Protein Function, Stability, and Diversity with Generative AI

Building a Neural Network Classifier from the Ground Up: A Step-by-Step Guide

How I train a LoRA: m3lt style training overview

Financial Analysis with Langchain and CrewAI Agents

Train custom AI models with the trainer API and adapt them to 🤗

Formatting Datasets for Chat Template Compatibility

Part 2: Enhancing the Motoku LLM Retrieval System with OpenAI Embeddings and Prompt-based Retrieval

Finetuning clip can be done locally with decent results (even if you are GPU poor).

Building a Motoku LLM Retrieval System Using Internet Computer Protocol, Motoko, and Node.js

Building an AI-Powered Card Counter with TensorFlow

Tokenization Is A Dead Weight (Tokun Part 1)

Evaluate RAG pipeline using HuggingFace Open Source Models

Build Agentic Workflow using OpenAGI and HuggingFace models

MotionLCM: The Fastest and Best Motion Generation Model

💃Introducing the first LLM-based Motion understanding model: MotionLLM

🚨 ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming

𝗝𝘂𝗱𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗝𝘂𝗱𝗴𝗲𝘀: 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗻𝗴 𝗔𝗹𝗶𝗴𝗻𝗺𝗲𝗻𝘁 𝗮𝗻𝗱 𝗩𝘂𝗹𝗻𝗲𝗿𝗮𝗯𝗶𝗹𝗶𝘁𝗶𝗲𝘀 𝗶𝗻 𝗟𝗟𝗠𝘀-𝗮𝘀-𝗝𝘂𝗱𝗴𝗲𝘀

Claude-3.5 Evaluation Results on Open VLM Leaderboard

seemore: Implement a Vision Language Model from Scratch

SeeMoE: Implementing a MoE Vision Language Model from Scratch

Shape Rotation 101: An Intro to Einsum and Jax Transformers

Open-source embeddings and LLMs outperform Gemini and OpenAI for Web Navigation while being faster and cheaper

Recommendation to Revisit the Diffuser Default LoRA Parameters

Introducing Synthetic Data Workshop: Your Gateway to Easy Synthetic Dataset Creation

Extracting Concepts from LLMs: Anthropic’s recent discoveries 📖

Enhancing Image Model Dreambooth Training Through Effective Captioning: Key Observations

Unveiling CIVICS: A New Dataset for Examining Cultural Values in Language Models

Introducing the Ultimate SEC LLM: Revolutionizing Financial Insights with Llama-3-70B

Train a Terrible Tic-Tac-Toe AI

Thoughts on LoRA Training Pt 2: Where to Train

Thoughts on LoRA Training #1

MobileNet-V4 (now in timm)

Against mixing environment setup with code

SwanLab and Transformers: Power Up Your NLP Experiments

CryptGPT: Privacy-Preserving Language Models Using Vigenere Cipher (Part 1)

The CVPR Survival Guide: Discovering Research That's Interesting to YOU!

Uncensor any LLM with abliteration

Low Latency CPU Based Educational Value Classifier With Generic Educational Value

An Optimal Lossy Variant of Speculative Decoding

Reports on the Hub: A First Look at Self-governance in Open Source AI Development

Building a Vision Mixture-of-Expert Model from several fine-tuned Phi-3-Vision Models

Running Large Multimodal Models on an AI PC's NPU

Saving Memory Using Padding-Free Transformer Layers during Finetuning

An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct

Aligning Large Language Models with BRAIn

What CI/CD practitioners know that ML engineers don’t… yet

BrAIn: next generation neurons?

Training an Object Detection Model with AutoTrain

Orchestrating Small Language Models (SLM) using JavaScript and the Hugging Face Inference API

Orquestrando Small Language Models (SLM) usando JavaScript e a API de Inferência do Hugging Face

Announcing Occiglot-Fineweb

🦙⚗️ Using Llama3 and distilabel to build fine-tuning datasets

Fine-tune and deploy open LLMs as containers using AIKit - Part 1: Running on a local machine

Virtual Try-On using IP-Adapter Inpainting

LLM数据工程3——数据收集魔法：获取顶级训练数据的方法

LLM Data Engineering 3——Data Collection Magic: Acquiring Top Training Data

I ran 580 model-dataset experiments to show that, even if you try very hard, it is almost impossible to know that a model is degrading just by looking at data drift results

FiftyOne Computer Vision Datasets Come to the Hugging Face Hub

⚗️ 🔥 Building High-Quality Datasets with distilabel and Prometheus 2

Expert-Level Tutorials on Stable Diffusion & SDXL: Master Advanced Techniques and Strategies

Wikipedia's Treasure Trove: Advancing Machine Learning with Diverse Data

Introducing Tenzin 1.0:

Mergoo: Efficiently Build Your Own MoE LLM

Fine-tuning LLMs with Singular Value Decomposition

Introducing UNA-ThePitbull Series

Indexify: Bringing HuggingFace Models to Real-Time Pipelines for Production Applications

HelpingAI 9B: Cutting Edge Emotionally Intelligent AI

How to directly access 150k+ Hugging Face Datasets with DuckDB and query using GPT-4o

FaceChain-FACT: Open-source 10-second portrait generation, reusing massive LoRa styles, a base-model-friendly portrait application.

Revolutionizing Human-Computer Interaction: The Emotional Intelligence and Ethical Impact of HelpingAI-9B

So WTF is an Audio Embedding Model?

Orchestration of Experts: The First-Principle Multi-Model System

How to Fine-Tune Custom Embedding Models Using AutoTrain

GPU Poor Savior: Revolutionizing Low-Bit Open Source LLMs and Cost-Effective Edge Computing

Not Legal Advice on AI Training Data in Japan

Sales Forecasting with Image Regression

AI has a problem with objectifying women

Training MoE on AWS Trainium

Let's talk about LLM evaluation

Synthetic dataset generation techniques: generating custom sentence similarity data

Journey With Me Into The Mind of Large Language Models: Interesting Findings in AnthropicAI's Scaling Monosemanticity paper.

Enjoy the Power of Phi-3 with ONNX Runtime on your device

What is going on with AlphaFold3?

Decoding GPT-4'o': In-Depth Exploration of Its Mechanisms and Creating Similar AI.

Sora

Explaining the SDXL latent space

Diffusion Models

Evaling llm-jp-eval (evals are hard)

2024-04-22 - Hub Incident Post Mortem

Hugging Face + Google Visual Blocks

Multimodal Augmentation for Documents: Recovering “Comprehension” in “Reading and Comprehension” task

Synthetic dataset generation techniques: Self-Instruct

Glaze and the Effectiveness of Anti-AI Methods for Diffusion Models

RFDiffusion Potentials

Exploration of Job Application Automation with Data Scraping

Everything About Long Context Fine-tuning

Advancing Open-source Large Language Models in the Medical & Healthcare Domain

Energy Scores for AI Models

Train Custom Models on Hugging Face Spaces with AutoTrain SpaceRunner

makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch

Can we create pedagogically valuable multi-turn synthetic datasets from Cosmopedia?

Evalverse: Revolutionizing Large Language Model Evaluation with a Unified, User-Friendly Framework

🧑‍⚖️ "Replacing Judges with Juries" using distilabel

Fish Speech V1 - New Multilingual Open Source TTS Model

Google Search with LLM

Token Merging for fast LLM inference : Background and first trials with Mistral

⚗️ 🧑🏼‍🌾 Let's grow some Domain Specific Datasets together

Expanding Model Context and Creating Chat Models with a Single Click

Estimating Memory Consumption of LLMs for Inference and Fine-Tuning for Cohere Command-R+

Post-OCR-Correction: 1 billion words dataset of automated OCR correction by LLM

Can We Train Chat Models with Raw Data?

RealWorldQA, What's New?

How to Finetune phi-3 on MacBook Pro

Fine Tuning a LLM Using Kubernetes with Intel® Xeon® Scalable Processors

LLM Comparison/Test: Llama 3 Instruct 70B + 8B HF/GGUF/EXL2 (20 versions tested and compared!)

Outpainting III - Inpaint Model

Outpainting II - Differential Diffusion

Outpainting I - Controlnet version

Exploring Emotionally Intelligent AI with HelpingAI

Fine-tune Llama 3 with ORPO

Starting Tiny with Protein LLaMA

Mixture of Depth is Vibe

Custom architectures with HuggingFace 🤗

Run the strongest open-source LLM model: Llama3 70B with just a single 4GB GPU!

On Coding Your First Attention

SVGDreamer: Text Guided Vector Graphics Generation with Diffusion Model

Releasing Youtube-Commons: a massive open corpus for conversational and multimodal data

Design choices for Vision Language Models in 2024

It's raining diffusion personalization techniques☔️🎭🖼️

History of State Space Models (SSM) in 2022

What Historical AI Breakthroughs Have Been Unappreciated by The Mainsteam Media?

Analysis on evaluating 7 bilions italian LLMs

DS-MoE: Making MoE Models More Efficient and Less Memory-Intensive

RAG Empowerment: Cohere C4AI Command-R and Transformers Unveiled

🐦 The IBIS Challenge

The LASER technique: Evaluating SVD compression

Open Source All About Data Processing, Dataverse

Many-shot jailbreaking

Aurora-M: The First Open Source Biden-Harris Executive Order Red teamed Multilingual Language Model

Gecko: Versatile Text Embeddings Distilled from Large Language Models

Finetune Mixtral 8x7B with AutoTrain

How do Textual Inversion tokens destroy prompts?

Experiments with Bitnet 1.5 (~ngmi~)

Create Mixtures of Experts with MergeKit

Elevate Responses: RAG with LlamaIndex & MongoDB

Samantha Mistral Instruct 7b - Comprehensive Bulleted Notes

Policy Questions Blog 1: AI Data Transparency Remarks for NAIAC Panel 📚🔍⚖️

Protein similarity and Matryoshka embeddings

A brief analysis of automerger data, feat. SLERP and DARE-TIES LLM merging

Data exploration and filtering with Nomic Atlas

Giskard Bot: Identifying robustness, performance and ethical vulnerabilities in the Top 10 Most Popular Hugging Face Models

Releasing Common Corpus: the largest public domain dataset for training LLMs

What's Automatic Differentiation?

Dive Deeper into Yi-9B

Sparse Mixture of Experts Language Model from Scratch: Extending makeMoE with Expert Capacity

VideoMamba: State Space Model for Efficient Video Understanding

Better RAG 3: The text is your friend

Better RAG 2: Single-shot is not good enough

Better RAG 1: Advanced Basics

MTEB Leaderboard : User guide and best practices

Revolutionizing Video Transcription: Unveiling Gemma-2b-it and Langchain in the Era of Transformers

Towards actively reasoning LLM systems

SemScore: Evaluating LLMs with Semantic Similarity

Open-Source SORA Has Arrived! Training Your Own SORA Model!

Large Language Models in Quest for Adventure

Streamline Computer Vision Workflows with Hugging Face Transformers and FiftyOne

Deploying 🤗 Hub models in Vertex AI

Genie: Generative Interactive Environments

Molecule retrieval and editing using multimodal text-structure representations

Breaking resolution curse of vision-language models

🌌 Analysis of Spaces in Hugging Face

Fast, High-Fidelity LLM Decoding with Regex Constraints

Rephrasing the Web A Recipe for Compute and Data-Efficient Language Modeling

Exploring a Public Domain dataset with Visual Topic Modeling

Navigating Complexity with Elegance: The P-FAF Approach to Fractal Word Embeddings

Fine-tuning a large language model on Kaggle Notebooks (or even on your own computer) for solving real-world tasks

Transformers and Quadrant: Revolutionizing Data Integration for NLP Tasks

Reformatted Alignment

Rank-Stabilized LoRA: Unlocking the Potential of LoRA Fine-Tuning

Guide : W-Okada, realtime voice cloning

Detecting LLM-Generated Text with Binoculars

Beyond Traditional Fine-tuning: Exploring Advanced Techniques to Mitigate LLM Hallucinations

Humor Understanding Multi-task Optimization & Ranking

Probabilistic Fractal Activation Function (P-FAF) and Its Advantages Over Traditional Word Vectorization

🥐CroissantLLM: A Truly Bilingual French-English Language Model

Quantization of Transformer Models with Neural Compressor

Introduction to LLE

Serverless Image Similarity with Upstash Vector and Huggingface Models, Datasets and Spaces

Phinetuning 2.0

Building autograd engine tinytorch 03

Building autograd engine tinytorch 02

💻Create a Web Interface for your LLM in Python

Robust image watermarking with Stable Signature + IMATAG's BZH

Multilabel Classification using Mistral-7B on a single GPU with quantization and LoRA

Building autograd engine tinytorch 01

AI Lineage Explorer: A Step Towards AI Integrity.

Unleashing the Power of Unsloth and QLora:Redefining Language Model Fine-Tuning

Breaking Barriers: The Critical Role of Art and Design in Advancing AI Capabilities

Implementing Fractional GPUs in Kubernetes with Aliyun Scheduler

Extending the Massive Text Embedding Benchmark to French: the datasets

Unleashing the Power of Logprobs in Language Models: A Practical Guide

Conditional Probability

Merge Large Language Models with mergekit

Temporal Scene Generation w/ Stable Diffusion

Unveiling TinyLlama: An Inspiring Dive into a Revolutionary Small-Scale Language Model

Multi-Label Classification Model From Scratch: Step-by-Step Tutorial

Multimodal IDEFICS: Unveiling the Transparency & Power of Open Visual Language Models

What is Probability?

4D masks support in Transformers

Understanding Mixtral-8x7b

Streamlining Data Management with Hugging Face and DVC: A Seamless Integration

TchAIkovsky – Piano MIDI Generation with Transformers

How Your Ordinary 8GB MacBook’s Untapped AI Power Can Run 70B LLM Models That Will Blow Your Mind!

Leveraging Transformers and PyTorch for Multiple Choice Question Tasks

Build an AI Chatbot to Run Code and Tweak plots

Combating Evaluation Data Contamination in LLMs: Strategies for High-Quality Finetuning and Model Merging

Counting 'n' objects

Kubernetes infrastructure for HF models and chat with Cluster.dev

How to build an interactive HF Space to visualize an Image Dataset

Uniting Forces: Integrating Hugging Face with Langchain for Enhanced Natural Language Processing

Drag GAN - Interactive Point-based Manipulation on the Generative Image Manifold

Running Any HuggingFace Model on SageMaker Endpoint: Walk-Through with Cross Encoder Model Example

Predicting the Effects of Mutations on Protein Function with ESM-2

Deploying Your FastAPI Applications on Huggingface Via Docker

What is a Transformer?

📚 Training Data Transparency in AI: Tools, Trends, and Policy Recommendations 🗳️

🏷️ Build AI Feedback (AIF) datasets for LLM alignment with ⚗️ distilabel

Fine-Tuning LLMs: Supervised Fine-Tuning and Reward Modelling

Easy JAX training loops with Flax and Optax

On Learning JAX – A Framework for High Performance Machine Learning

Sentence Mining with OpenAI's Whisper

Illustrated LLM OS: An Implementational Perspective

💨 Introducing Notus: a DPO fine-tune of Zephyr with a focus on high-quality data

Faster Persistent Homology Alignment and Protein Complex Clustering with ESM-2 and Persistence Landscapes

Evaluating Large Language Models on Gender-Occupational Stereotypes Using the Wino Bias Test

Unbelievable! Run 70B LLM Inference on a Single 4GB GPU with This NEW Technique

Clustering Protein Complexes using Persistent Homology and Finetuning ESM-2 for PPI Network Prediction

Streamlining ML Workflows: Integrating MLFlow Tracking with LangTest for Enhanced Model Evaluations

Automatic Hallucination detection with SelfCheckGPT NLI

Extracting Insights from Model Cards Using Open Large Language Models

ESM-2 for Generating and Optimizing Peptide Binders for Target Proteins

Does Sketching Work?

Understanding Zephyr

Are your NLP models deteriorating post-deployment? Let’s use unlabelled data to find out

Persistent Homology Alignment (PHA): Replacing Multiple Sequence Alignments using ESM-2 and Persistent Homology

In Silico Directed Evolution of Protein Sequences with ESM-2 and EvoProtGrad

QLoRA for ESM-2 and Post Translational Modification Site Prediction

Automating Responsible AI: Integrating Hugging Face and LangTest for More Robust Models

Hugging Face accelerates distribution of models and datasets based on Dragonfly

Introducing the Giskard Bot: Enhancing LLM Testing & Debugging on Hugging Face

Elevate Your NLP Models with Automated Data Augmentation for Enhanced Performance

Goodbye Python, Hello Rust: Building a RAG CLI Application with Orca

StarCoder Memorization Experiment Highlights Privacy Risks of Fine-Tuning On Code

Scaling Self Supervised Learning for Histology: introducing Phikon

Unmasking Language Model Sensitivity in Negation and Toxicity Evaluations

Detecting and Evaluating Sycophancy Bias: An Analysis of LLM and AI Solutions

After 500+ LoRAs made, here is the secret

Detecting the Deceptive: Unmasking Deep Fake Voices

AutoTrain Advanced now supports Experiment Tracking

Hearing is Believing: Revolutionizing AI with Audio Classification via Computer Vision

Next token prediction with GPT

What kind of data lake do we need in the Big Model era?

Fine-tune Flair Models on NER Dataset with 🤗 AutoTrain SpaceRunner

Estimating the Intrinsic Dimension of Protein Sequence Embeddings using ESM-2

Sparse LLM Inference on CPU

Introduction to Dataset Creation - What Makes a Good Dataset?

Building Your First Kubeflow Pipeline: A Comprehensive Guide

Predicting Protein-Protein Interactions Using a Protein Language Model and Linear Sum Assignment

InfiniText: Empowering Conversations & Content with Mistral-7B-Instruct-v0.1

Changes of Embeddings during Fine-Tuning of Vision Transformers (ViT)

🕳️ Attention Sinks in LLMs for endless fluency

Understanding InstaFlow/Rectified Flow

Using 🤗 to Train a GPT-2 Model for Music Generation

Making AI-Generated Content Easier to Identify

Samantha and Mistral 7B: A Powerful and Versatile Language Model Duo

IntenLM-20B is officially released on Hugging Face Hub

Trying IDEFICS on a New Yorker cartoon dataset

Introducing BlindChat, an open-source and privacy-by-design Conversational AI fully in-browser

ESMBind (ESMB) Ensemble Models

Optimizing Convolutional Neural Networks with Mojo - Part 1

AI Total Cost of Ownership Calculator: Evaluate the cost of in-house AI deployment vs AI APIs

🤗 LLM suggestions in Argilla with HuggingFace Inference Endpoints

Hugging Face and Scrimba partner to teach developers to utilize open-source AI models

ESMBind (ESMB): Low Rank Adaptation of ESM-2 for Protein Binding Site Prediction

Introduction to Quantization cooked in 🤗 with 💗🧑‍🍳