---
license: mit
base_model:
- 1bitLLM/bitnet_b1_58-3B
library_name: transformers
tags:
- mergekit
- merge
- bitnet
---
# bitnet-5B-v1
I redesigned mergekit so that I could merge the bitnet 3B model (unlike version v0, where I did merge via PyTorch).

In theory, this is compatible with quantization via llama.cpp , but tests are needed.