configuration files for custom training?
Hi,
I'm working on custom training with the bitnet-b1.58-2B-4T-bf16 model and would like to retain 1-bit quantization compatibility for CPU inference using tools like llama.cpp.
However, the current repository appears to be missing the configuration_bitnet.py and modeling_bitnet.py files typically required to enable trust_remote_code=True with Transformers. Are there official versions of these files available, or recommended alternatives that preserve compatibility with the quantization pipeline (e.g. i2_s / GGUF for CPU use)?
Any guidance or references would be much appreciated.
Thanks!
You can find alternative files here: https://huggingface.co./1bitLLM/bitnet_b1_58-3B/tree/main Just put them into the model path.
And install transformers==4.52.0.dev0 by pip install git+https://github.com/shumingma/transformers.git.
Hope it works for you as well.
I just wanted to say thanks, the config files worked great and I'm training! Stuck on CPU for now due to the Mac MPS 512 limit, figuring out the local GPU path so I can avoid needing a cloud resource for my use case.
Really impressed with this model's local performance and efficiency. It's a fantastic start!
Hopeful that larger context windows and bigger models might be possibilities down the line.
Thanks again for sharing!