fix architecture
#3
by TPM-28 - opened
ValueError: The checkpoint you are trying to load has model type `helium` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
and
"Overall, our architecture is almost identical to the one introduced by LLaMA 1, allowing an easy and straightforward deployment using existing tools such as MLX, vLLM, ollama or llama.cpp."
The issue there is that the code to support our model was only released recently in transformers so you can either use the github version of transformers or wait for the next release and install it via pip. Fwiw the PR that added it: https://github.com/huggingface/transformers/pull/35669 The llama architecture will not work out of the box as there are some differences in rope/rmsnorm.
Please support gguf (llama.cpp)
TPM-28 changed pull request status to closed