1-bit Bonsai
3 likes
1-bit Bonsai 8B implements a proprietary 1-bit model design across the entire network: embeddings, attention layers, MLP layers, and the LM head are all 1-bit. There are no higher-precision escape hatches. It is a true 1-bit model, end to end, across 8.2 billion parameters.
Features
Highlights All activities
1-bit Bonsai News & Activities
Recent activities
- Abdulmajid-Yunusov liked 1-bit Bonsai
- plyght liked 1-bit Bonsai
- niksavc liked 1-bit Bonsai
Paul added 1-bit Bonsai as alternative to Kimi, Open R1, Google Gemma, Meta Llama and 8 more- Paul added 1-bit Bonsai



No comments or reviews, maybe you want to be first?