60 15 65

Kenneth Hamilton PRO

ZennyKenny

https://nevskycollective.com

AI & ML interests

Development and Ops for LLMs and CV.

Recent Activity

updated a Space 24 days ago

ZennyKenny/kghamilton

posted an update 24 days ago

Has the AI movement gone too far? https://blueskyroast.com/

reacted to takarajordan's post with 🔥 27 days ago

I'm not sure why I haven't done this already! I just made a space to count and visualize tokens for Diffusion models, no more guesswork! It's super fast too. Check it out here and try out your prompts: https://huggingface.co./spaces/takarajordan/DiffusionTokenizer Uses these tokenizers below: https://huggingface.co./openai/clip-vit-large-patch14 https://huggingface.co./google/t5-v1_1-xxl

View all activity

Organizations

ZennyKenny's activity

upvoted 2 articles 5 months ago

Article

WWDC 24: Running Mistral 7B with Core ML

Jul 22

• 56

Article

Train a Llama model from scratch

•

Jul 29

• 48

upvoted a paper 5 months ago

The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism

Paper • 2407.10457 • Published Jul 15 • 22

upvoted an article 6 months ago

Article

Data Is Better Together: A Look Back and Forward

Jun 20

• 19

upvoted 2 papers 6 months ago

Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer

Paper • 2403.13570 • Published Mar 20 • 3

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published Jun 20 • 86

upvoted 2 papers 8 months ago

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

Paper • 2309.10400 • Published Sep 19, 2023 • 26

Evaluating Text-to-Visual Generation with Image-to-Text Generation

Paper • 2404.01291 • Published Apr 1 • 6

upvoted 2 papers 9 months ago

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Paper • 2312.00752 • Published Dec 1, 2023 • 138

Chronos: Learning the Language of Time Series

Paper • 2403.07815 • Published Mar 12 • 46

upvoted 3 collections 9 months ago

upvoted a paper 9 months ago

Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation

Paper • 2403.06164 • Published Mar 10 • 2