Jan (Homebrew Research) PRO

jan-hq's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 15 days ago

Speechless: Speech Instruction Training Without Speech for Low Resource Languages

Paper • 2505.17417 • Published 18 days ago • 11

upvoted a paper about 1 month ago

ReZero: Enhancing LLM search ability by trying one-more-time

Paper • 2504.11001 • Published Apr 15 • 14

upvoted a paper 3 months ago

AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning

Paper • 2503.18769 • Published Mar 24 • 10

upvoted 2 articles 3 months ago

view article

Article

Open-R1: a fully open reproduction of DeepSeek-R1

By and 2 others •

Jan 28

• 866

view article

Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

By •

Jan 30

• 74

upvoted a paper 5 months ago

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

Paper • 2501.06186 • Published Jan 10 • 66

upvoted an article 6 months ago

view article

Article

Understanding Vector Quantization in VQ-VAE

By •

Aug 28, 2024

• 30

upvoted a paper 8 months ago

Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant

Paper • 2410.15316 • Published Oct 20, 2024 • 12

upvoted a collection 8 months ago

🍓 Ichigo v0.3

Collection

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

upvoted a collection 11 months ago

llama3-s

Collection

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

upvoted 6 collections over 1 year ago

Stealth

Collection

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

Merged Mistral

Collection

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

Phoenix

Collection

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

Pandora

Collection

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

Trinity

Collection

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

Trinity

Collection

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