Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community
ResterChed
• • 93Community Blog & Articles
Community Articles
view all
communityopen-source-collab
Gradio is joining Hugging Face!
7
December 21, 2021 
researchguidenlp
Perceiver IO: a scalable, fully-attentional model that works on any modality
17
December 15, 2021 
guideresearchnlp
Training CodeParrot 🦜 from Scratch
8
December 8, 2021 
researchrl
Introducing Snowball Fight ☃️, our first ML-Agents environment
4
December 2, 2021 
partnershipsgraphcoreguide
Getting Started with Hugging Face Transformers for IPUs with Optimum
November 30, 2021
research
Introducing the Data Measurements Tool: an Interactive Tool for Looking at Datasets
November 29, 2021
guide
Accelerating PyTorch distributed fine-tuning with Intel technologies
2
November 19, 2021 
guideaudio
Fine-Tune XLSR-Wav2Vec2 for low-resource ASR with 🤗 Transformers
43
November 15, 2021 
partnershipsintelguide
Scaling up BERT-like model Inference on modern CPU - Part 2
1
November 4, 2021 
communitynlp
Course Launch Community Event
3
October 26, 2021 
analysisnlp
Large Language Models: A New Moore's Law?
7
October 26, 2021 
communitynlp
Train a Sentence Embedding Model with 1B Training Pairs
2
October 25, 2021 
analysis
The Age of Machine Learning As Code Has Arrived
1
October 20, 2021 
communitycvnlp
Fine tuning CLIP with Remote Sensing (Satellite) images and captions
- +2
8
October 13, 2021 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community
ResterChed
• • 93Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers
nvidia
• • 79Introducing Cosmos 3 Edge
nvidia
• • 33Aether-7B-5Attn: A 100% Open-Source Sovereign Foundation Model — and a Controlled Experiment in Heterogeneous Attention
FINAL-Bench
• • 21NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval
nvidia
• • 56Be Ready Before the Attack: A Practical Guide to Self-Hosting an Open Model for Cyber Defense
jeffboudier
• • 14Hugging Face on AMD Instinct MI455X: First Transformers Results
badaoui
• • 12POCKET: a 35-billion-parameter model that runs on your iPhone — and on your PC with no GPU
FINAL-Bench
• • 10KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 380Uncensor any LLM with abliteration
mlabonne
• • 881The influx of specialist models on the Open SLM Leaderboard
Banaxi-Tech
• • 7J-Space: Yet Another LLM Mind Reader?
dlouapre
• • 34One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker
lightonai
• • 17Introduction to State Space Models (SSM)
lbourdois
• • 238Code a simple RAG from scratch
ngxson
• • 366From GRPO to DAPO and GSPO: What, Why, and How
NormalUhr
• • 132Tokenization is Killing our Multilingual LLM Dream
omarkamali
• • 17Building Moon Bot: A Slack-Native Coding Agent Backed by HuggingFace Buckets
huggingface
• • 49Introducing North Mini Code: Cohere’s First Model For Developers
CohereLabs
• • 83We Just Surgically Changed What Your Model Believes
ApolloRaines
• • 3