 AlphaMaze: Teaching LLMs to think visually

With the latest checkpoint, we're teaching AI to talk and recognize when it can't listen.

🍓 Ichigo: Llama learns to talk

Homebrew research shares llama3-s, an open & ongoing research experiment to teach llama3 to listen.

Llama3 just got ears

Can llama learn to listen?

We are now Homebrew, a research lab on human-augmenting AI.

Jan is now part of something bigger: Homebrew 🖖

This post compares the performance of TensorRT-LLM and llama.cpp on consumer NVIDIA GPUs, highlighting the trade-offs among speed, resource usage, and convenience.

Blog

AlphaMaze: Teaching LLMs to think visually

🍓 Ichigo: Llama learns to talk

Llama3 just got ears

Can llama learn to listen?

Jan is now part of something bigger: Homebrew 🖖

Benchmarking NVIDIA TensorRT-LLM