Daniel Bourke's picture

Daniel Bourke PRO

mrdbourke

·

https://www.mrdbourke.com

AI & ML interests

Computer vision. Small on-device models. VLMs. High-quality tutorials.

Recent Activity

liked a dataset about 13 hours ago

sasha/birdsnap

liked a model 2 days ago

lusxvr/nanoVLM-222M

liked a model 4 days ago

OpenGVLab/InternVL3-8B-hf

View all activity

Organizations

None yet

mrdbourke's activity

upvoted 2 collections 8 days ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory. • 19 items • Updated 21 days ago • 27

InternVL3

34 items • Updated 19 days ago • 66

upvoted 2 papers 8 days ago

BitNet b1.58 2B4T Technical Report

Paper • 2504.12285 • Published 23 days ago • 70

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 615

upvoted a collection 8 days ago

Llama 4

Llama 4 release • 13 items • Updated 10 days ago • 484

upvoted a collection 10 days ago

Qwen3

37 items • Updated about 10 hours ago • 553

upvoted an article 10 days ago

Article

Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs

11 days ago

• 23

upvoted 2 collections 16 days ago

Web-SSL

17 items • Updated 16 days ago • 14

DataDecide

A suite of models, data, and evals over 25 corpora, 14 sizes, and 3 seeds to measure how accurately small experiments predict rankings at large scale. • 358 items • Updated 9 days ago • 13

upvoted an article 16 days ago

Article

Cohere on Hugging Face Inference Providers 🔥

24 days ago

• 124

upvoted a collection 16 days ago

Describe Anything

Multimodal Large Language Models for Detailed Localized Image and Video Captioning • 7 items • Updated 4 days ago • 49

upvoted a collection 22 days ago

Perception Encoder

9 items • Updated 22 days ago • 50

upvoted a collection 30 days ago

Kimi-VL-A3B

Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 6 items • Updated 27 days ago • 66

upvoted a collection about 1 month ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated 21 days ago • 187

upvoted an article about 1 month ago

Article

Welcome Llama 4 Maverick & Scout on Hugging Face!

Apr 5

• 142

upvoted a paper about 1 month ago

Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

Paper • 2504.00595 • Published Apr 1 • 36

upvoted a collection about 1 month ago

ShieldGemma

ShieldGemma is a family of models for text and image content moderation. • 4 items • Updated Apr 3 • 6

upvoted an article about 1 month ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

Mar 26

• 126

upvoted a paper about 1 month ago

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Paper • 2503.11576 • Published Mar 14 • 104