Community Blog & Articles

Community Articles

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

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

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

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

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

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

Uncensor any LLM with abliteration

Code a simple RAG from scratch

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

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

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

Mastering Tensor Dimensions in Transformers

KV Caching Explained: Optimizing Transformer Inference Efficiency

Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community

The OlmoEarth Platform: Geospatial inference at planetary scale

Optimum Intel v2.1.0

IDEOGRAM-4 for inpainting with Modular Diffusers and Differential Diffusion

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

Total noob’s intro to Hugging Face Transformers

nlpcommunityguide

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

leaderboardarenacollaboration

Introducing the Chatbot Guardrails Arena

partnershipsintelllm

A Chatbot on your Laptop: Phi-2 on Intel Meteor Lake

+2

guidenlpsynthetic-data

Cosmopedia: how to create large-scale synthetic data for pre-training Large Language Models

GaLore: Advancing Large Model Training on Consumer-grade Hardware

+5

partnershipshardwarenvidia

Easily Train Models with H100 GPUs on NVIDIA DGX Cloud

guidequantizationtransformers

Quanto: a PyTorch quantization backend for Optimum

nlpintelquantization

CPU Optimized Embeddings with 🤗 Optimum Intel and fastRAG

+2

Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset

leaderboardcollaborationresearch

Introducing ConTextual: How well can your Multimodal model jointly reason over text and image in text-rich scenes?

+1

communitydatacollaboration

Data is better together: Enabling communities to collectively build better datasets together using Argilla and Hugging Face Spaces

habanapartnershipshardware

Text-Generation Pipeline on Intel® Gaudi® 2 AI Accelerator

February 29, 2024

nlpcommunityresearch

StarCoder2 and The Stack v2

February 28, 2024

Community Articles

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

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

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

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

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

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

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

Uncensor any LLM with abliteration

Code a simple RAG from scratch

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

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

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

Mastering Tensor Dimensions in Transformers

KV Caching Explained: Optimizing Transformer Inference Efficiency

Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community

The OlmoEarth Platform: Geospatial inference at planetary scale

Optimum Intel v2.1.0

IDEOGRAM-4 for inpainting with Modular Diffusers and Differential Diffusion

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

View all articles