Community Blog & Articles

Community Articles

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

WWDC 24: Running Mistral 7B with Core ML

Docmatix - a huge dataset for Document Visual Question Answering

TGI Multi-LoRA: Deploy Once, Serve 30 Models

SmolLM - blazingly fast and remarkably powerful

How we leveraged distilabel to create an Argilla 2.0 Chatbot

How NuminaMath Won the 1st AIMO Progress Prize

Announcing New Hugging Face and KerasHub integration

Experimenting with Automatic PII Detection on the Hub using Presidio

Preference Optimization for Vision Language Models

Google Cloud TPUs made available to Hugging Face users

Banque des Territoires (CDC Group) x Polyconseil x Hugging Face: Enhancing a Major French Environmental Program with a Sovereign Data Solution

Announcing New Dataset Search Features

NEW Articles from Team or Enterprise organizations will get promoted to the main section.

Community Blog & Articles

FineBooks: are open OCR models good enough to unlock historical knowledge?

Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv

Lattice: an 8 MB static retriever that embeds Wikipedia in 7 minutes

Model Genome: Fingerprinting Whether an LLM Was Trained From Scratch or Derived

GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval

Uncensor any LLM with abliteration

The Fast Gemma Challenge: our verified-SOTA recipe, in full

jina-reranker-v3.5: Faster Listwise Reranking with Hybrid Attention and Self-Distillation

Rebuilding Among AIs from Six Log Files

On the integrity of the Arabic TTS Arena leaderboard

Code a simple RAG from scratch

Mastering Tensor Dimensions in Transformers

mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models

The OlmoEarth Platform: Geospatial inference at planetary scale

Language Identification for 42 Indian Languages: Opening New Frontiers in Indic Speech AI

Optimum Intel v2.1.0

Exploring NVIDIA Nemotron 3.5 Lightning: Making it see with little resources

KV Caching Explained: Optimizing Transformer Inference Efficiency

IDEOGRAM-4 for inpainting with Modular Diffusers and Differential Diffusion

A 0.6B model at #2 on MTEB(Law)

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

WWDC 24: Running Mistral 7B with Core ML

Docmatix - a huge dataset for Document Visual Question Answering

TGI Multi-LoRA: Deploy Once, Serve 30 Models

SmolLM - blazingly fast and remarkably powerful

How we leveraged distilabel to create an Argilla 2.0 Chatbot

How NuminaMath Won the 1st AIMO Progress Prize

Announcing New Hugging Face and KerasHub integration

Experimenting with Automatic PII Detection on the Hub using Presidio

Preference Optimization for Vision Language Models

Google Cloud TPUs made available to Hugging Face users

Banque des Territoires (CDC Group) x Polyconseil x Hugging Face: Enhancing a Major French Environmental Program with a Sovereign Data Solution

Announcing New Dataset Search Features

FineBooks: are open OCR models good enough to unlock historical knowledge?

Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv

Lattice: an 8 MB static retriever that embeds Wikipedia in 7 minutes

Model Genome: Fingerprinting Whether an LLM Was Trained From Scratch or Derived

GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval

Uncensor any LLM with abliteration

The Fast Gemma Challenge: our verified-SOTA recipe, in full

jina-reranker-v3.5: Faster Listwise Reranking with Hybrid Attention and Self-Distillation

Rebuilding Among AIs from Six Log Files

On the integrity of the Arabic TTS Arena leaderboard

Code a simple RAG from scratch

Mastering Tensor Dimensions in Transformers

mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models

The OlmoEarth Platform: Geospatial inference at planetary scale

Language Identification for 42 Indian Languages: Opening New Frontiers in Indic Speech AI

Optimum Intel v2.1.0

Exploring NVIDIA Nemotron 3.5 Lightning: Making it see with little resources

KV Caching Explained: Optimizing Transformer Inference Efficiency

IDEOGRAM-4 for inpainting with Modular Diffusers and Differential Diffusion

A 0.6B model at #2 on MTEB(Law)