BitNet icon indicating copy to clipboard operation
BitNet copied to clipboard

Official inference framework for 1-bit LLMs

Results 227 BitNet issues
Sort by recently updated
recently updated
newest added

Do you test the others 1-bit models from Hugginface ? bitnet_b1_58-large bitnet_b1_58-3B Llama3-8B-1.58-100B-tokens Falcon3 Family | 1B-10B What are the results in inference ? I personnaly use Falcon3-10B-Instruct-1.58bit.gguf and results...

Caused #178 most likely Code was looking for `BitNetForCausalLM`, name in `convert-hf-to-gguf-bitnet.py` was: https://github.com/microsoft/BitNet/blob/fd9f1d6e46b476d449417d49851f50a569165835/utils/convert-hf-to-gguf-bitnet.py#L952 `BitNetForCausalLM` vs. `BitnetForCausalLM`

I've been following gpt4.1 instructions to build BitNet from source, but I'm unable to proceed because `include/bitnet-lut-kernels.h` is missing from both the main repository and my local clone. The build...

https://github.com/werruww/bitnet-run-good/blob/main/Untitled225%20(2).ipynb

Does it support distributed inference? I want to deploy large models on an XPU cluster. like cpu cluster

Fix: chrono-template and llama.cpp to run 1bit llm in Win11

When I run `run_inference.py` in interactive mode using the provided `ggml-model-i2_s.gguf` from Hugging Face, the model only outputs the character `G` in a loop, no matter what prompt I use....

When I build by executing `python setup_env.py -md models/BitNet-b1.58-2B-4T -q i2_s`: > Project "E:\Bitnet\BitNet\build\CMakeFiles\4.0.0-rc2\VCTargetsPath.vcxproj" on node 1 (default targets). > C:\Program Files (x86)\Microsoft Visual Studio\2022\BuildTools\MSBuild\Microsoft\VC\v170\Microsoft.CppBuild.targets(456,5): error MSB8020: The build tools...

Hi I get the below error ![Image](https://github.com/user-attachments/assets/2e4ace2d-1ffb-404b-88c8-9020f8637c27)