Hieu Ngo's picture

Hieu Ngo

hiieu

·

AI & ML interests

Applied, Post-Training LLM

Organizations

hiieu's activity

upvoted an article 3 days ago

Article

Improving Hugging Face Training Efficiency Through Packing with Flash Attention

4 days ago

• 8

upvoted a paper 12 days ago

Synthesizing Text-to-SQL Data from Weak and Strong LLMs

Paper • 2408.03256 • Published 18 days ago • 8

upvoted a paper 21 days ago

Improving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuning

Paper • 2408.00690 • Published 23 days ago • 21

upvoted a collection 24 days ago

ShieldGemma Release

A series of safety classifiers, trained on top of Gemma 2, for developers to filter inputs and outputs of their applications. • 3 items • Updated 24 days ago • 11

upvoted a paper about 1 month ago

Compact Language Models via Pruning and Knowledge Distillation

Paper • 2407.14679 • Published Jul 19 • 35

upvoted a collection about 1 month ago

Minitron

A family of compressed models obtained via pruning and knowledge distillation • 6 items • Updated 3 days ago • 48

upvoted a paper about 1 month ago

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities

Paper • 2407.14482 • Published Jul 19 • 22

upvoted a collection about 1 month ago

NuminaMath

Datasets and models for training SOTA math LLMs. See our GitHub for training & inference code: https://github.com/project-numina/aimo-progress-prize • 6 items • Updated Jul 21 • 50

upvoted 2 articles about 1 month ago

Article

How we leveraged distilabel to create an Argilla 2.0 Chatbot

Jul 16

• 30

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16

• 225

upvoted a collection about 1 month ago

H2O Danube3

6 items • Updated Jul 16 • 50

upvoted an article about 1 month ago

Article

The Rise of Agentic Data Generation

By

•

Jul 15

• 73

upvoted a collection about 1 month ago

Gemma 2 Release

14 items • Updated 24 days ago • 155

upvoted a collection 2 months ago

sentence-transformers-from-synthetic-data

Example of using distilabel to generate synthetic triplets data for fine-tuning a Sentence Transformer model • 4 items • Updated Jun 21 • 21

upvoted 3 collections 3 months ago

Embedding Model Datasets

A curated subset of the datasets that work out of the box with Sentence Transformers: https://huggingface.co/datasets?other=sentence-transformers • 67 items • Updated Jul 3 • 56

MoEs papers reading list

55 items • Updated 10 days ago • 131

Preference Datasets for DPO

This collection contains a list of curated preference datasets for DPO fine-tuning for intent alignment of LLMs • 7 items • Updated 25 days ago • 26

upvoted an article 3 months ago

Article

🦙⚗️ Using Llama3 and distilabel to build fine-tuning datasets

By

•

Jun 4

• 66

upvoted 2 collections 4 months ago

Llama3-ChatQA-1.5

Llama3-ChatQA-1.5 models excel at conversational question answering (QA) and retrieval-augmented generation (RAG). • 6 items • Updated Jul 17 • 39

OpenELM Pretrained Models

4 items • Updated Jun 19 • 46