Jan (Homebrew Research)'s picture

Jan (Homebrew Research) PRO

jan-hq

·

https://homebrew.ltd

AI & ML interests

Also at: https://huggingface.co/jan-ai https://huggingface.co/homebrewltd

Recent Activity

updated a dataset 4 minutes ago

jan-hq/Maze-Reasoning

published a dataset 16 minutes ago

jan-hq/Maze-Reasoning

updated a model about 22 hours ago

jan-hq/WhisperVQ

View all activity

Organizations

jan-hq's activity

upvoted a paper 24 days ago

LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs

Paper • 2501.06186 • Published 26 days ago • 60

upvoted an article about 2 months ago

Article

Understanding Vector Quantization in VQ-VAE

By

•

Aug 28, 2024

• 15

upvoted a paper 4 months ago

Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant

Paper • 2410.15316 • Published Oct 20, 2024 • 10

upvoted a collection 4 months ago

🍓 Ichigo v0.3

The experimental family designed to train LLMs to understand sound natively. • 6 items • Updated Nov 11, 2024 • 17

upvoted a collection 7 months ago

llama3-s

The experimental family designed to train LLMs to understand sound natively. • 3 items • Updated Aug 26, 2024 • 5

upvoted 6 collections about 1 year ago

Stealth

This is designed to enhance Mathematical and Logical abilities. • 5 items • Updated Jul 10, 2024 • 1

Merged Mistral

These are merged models with Mistral as a base • 2 items • Updated Sep 27, 2024 • 1

Phoenix

The experimental family of MOE merge. • 1 item • Updated Sep 27, 2024 • 1

Pandora

The experimental family using Passthrough merge method • 2 items • Updated Sep 27, 2024 • 1

Trinity

The experimental 7B merge using Slerp method • 3 items • Updated Sep 27, 2024 • 3

Trinity

Flagship merged models using SLERP method from Jan • 3 items • Updated Jul 10, 2024 • 1