The Optimal Architecture for Small Language Models
•
56
Community Blog & Articles
Community Articles
view all
open-source-collabnlp
Retrieval Augmented Generation with Huggingface Transformers and Ray
6
February 10, 2021
open-source-collab
Hugging Face on PyTorch / XLA TPUs
3
February 9, 2021
guidenlp
Faster TensorFlow models in Hugging Face Transformers
January 26, 2021
guide
Fit More and Train Faster With ZeRO via DeepSpeed and FairScale
4
January 19, 2021
analysisnlp
How we sped up transformer inference 100x for 🤗 API customers
January 18, 2021
guidenlp
Leveraging Pre-trained Language Model Checkpoints for Encoder-Decoder Models
15
November 9, 2020
open-source-collabnlp
Porting fairseq wmt19 translation system to transformers
1
November 3, 2020
open-source-collabnlp
Hyperparameter Search with Transformers and Ray Tune
4
November 2, 2020
researchnlp
Transformer-based Encoder-Decoder Models
19
October 10, 2020
researchnlp
Block Sparse Matrices for Smaller and Faster Language Models
September 10, 2020
researchnlp
The Reformer - Pushing the limits of language modeling
3
July 3, 2020
guidenlp
Hot
How to generate text: using different decoding methods for language generation with Transformers
275
March 1, 2020
guidenlp
How to train a new language model from scratch using Transformers and Tokenizers
56
February 14, 2020
NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
The Optimal Architecture for Small Language Models
•
56
Deriving the PPO Loss from First Principles
•
28
LLM based Audio models
•
48
Encoding the World's Medical Knowledge into 970K
•
14
Skill is All You Need: Lessons from Building Marketing Agents at Noumena
•
9
Qwen-Image-i2L: Training Strategies for Image-to-LoRA Generation
•
40
Uncensor any LLM with abliteration
•
746
What makes good reasoning data
•
40
Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models
•
101
Nano-BEIR: A Multilingual Information Retrieval Benchmark with Quality-Enhanced Queries
•
5
How to make NeuTTS-air generate over 200 seconds of audio in a single second.
•
21
Apriel-1.6-15b-Thinker: Cost-efficient Frontier Multimodal Performance
•
82
Code a simple RAG from scratch
•
270
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
•
263
Why You Should Care About Partial Differential Equations (PDEs)
•
33
Make and publish your Reachy Mini App
•
25
cua-bench: A Framework for Benchmarking, Training Data, and RL Environments for Computer-Use Agents
•
9
Understanding InstaFlow/Rectified Flow
•
35
Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth
•
365
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
202