BitNet
BitNet copied to clipboard
Register BitNetForCausalLM as another spelling for BitnetForCausalLM in utils scripts
This feels like a waste of a good full request.
Microsoft configured their newly released bitnet model as using the BitNetForCausalLM architecture (see) while the conversion script in utils and other community models refers to it as BitnetForCausalLM (lowercase N). This just adds BitNetForCausalLM as another valid architecture name to use in convert-hf-to-gguf-bitnet.py and generate-dummy-bitnet-model.py.
Should fixes #193
@microsoft-github-policy-service agree