Support for Zephyr and other "StableLmForCausalLM" models?
BBC-Esq opened this issue · comments
BBC-Esq commented
Any plans to support conversion of ```StableLmForCausalLM" models? I've noticed that they're very good; for example the new Zephyr model here:
https://huggingface.co/stabilityai/stablelm-zephyr-3b
Amazing performance for a 3B model, much better than Phi2 IMHO. Support was added into Transformers in version 4.38.2:
https://github.com/huggingface/transformers/releases/tag/v4.38.0
Here's the link to a description of the model architecture to help:
https://huggingface.co/docs/transformers/v4.38.2/en/model_doc/stablelm