🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do
•
37
Community Blog & Articles
Community Articles
view all
llmexpert-support-programexpert-support
Investing in Performance: Fine-tune small models with LLM insights - a CFM case study
- +3
39
December 3, 2024 
RAGllmexpert-support-program
Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge
29
October 28, 2024 
case-studies
Banque des Territoires (CDC Group) x Polyconseil x Hugging Face: Enhancing a Major French Environmental Program with a Sovereign Data Solution
-
- +1
6
July 9, 2024 
case-studies
XLSCOUT Unveils ParaEmbed 2.0: a Powerful Embedding Model Tailored for Patents and IP with Expert Support from Hugging Face
11
June 25, 2024 
case-studies
Going multimodal: How Prezi is leveraging the Hub and the Expert Support Program to accelerate their ML roadmap
12
June 19, 2024 
case-studies
Ryght’s Journey to Empower Healthcare and Life Sciences with Expert Support from Hugging Face
6
April 16, 2024 
case-studies
Rocket Money x Hugging Face: Scaling Volatile ML Models in Production
1
September 19, 2023 
case-studies
Fetch Cuts ML Processing Latency by 50% Using Amazon SageMaker & Hugging Face
September 1, 2023
case-studies
Leveraging Hugging Face for complex generative AI use cases
July 1, 2023
case-studies
Databricks ❤️ Hugging Face: up to 40% faster training and tuning of Large Language Models
April 26, 2023
case-studies
Snorkel AI x Hugging Face: unlock foundation models for enterprises
April 6, 2023
nlpcase-studies
How Hugging Face Accelerated Development of Witty Works Writing Assistant
-
- +1
3
March 1, 2023 
case-studies
Fetch Consolidates AI Tools and Saves 30% Development Time with Hugging Face on AWS
February 23, 2023
case-studies
Why we’re switching to Hugging Face Inference Endpoints, and maybe you should too
4
February 15, 2023 NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do
•
37
Beyond Semantic Similarity: Introducing NVIDIA NeMo Retriever’s Generalizable Agentic Retrieval Pipeline
•
30
How NVIDIA AI-Q Reached \#1 on DeepResearch Bench I and II
•
27
NEO-unify: Building Native Multimodal Unified Models End to End
•
95
How NVIDIA Builds Open Data for AI
•
13
Uncensor any LLM with abliteration
•
806
Arabic TTS Arena: Ranking Voice Models the Way Chess Ranks Grandmasters
•
11
Build an Agent That Thinks Like a Data Scientist: How We Hit #1 on DABStep with Reusable Tool Generation
•
9
Kanon 2 Reranker: the most powerful reranker for legal RAG
•
6
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
243
From GRPO to DAPO and GSPO: What, Why, and How
•
101
Norm-Preserving Biprojected Abliteration
•
72
MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning
•
15
Code Concepts: A Large-Scale Synthetic Dataset Generated from Programming Concept Seeds
•
5
SILMA TTS: A Lightweight Open Bilingual Text to Speech Model
•
5
Code a simple RAG from scratch
•
310
OpenMed: Six Months of Open-Source Medical AI and the Road Ahead
•
19
We’re open-sourcing our text-to-image model and the process behind it
•
96
LLM based Audio models
•
55
The ML Engineer's Guide to Protein AI
•
27