How did you bypass deepseek-v32 not recognized in Tranformers?

#3
by Fernanda24 - opened

ValueError: The checkpoint you are trying to load has model type deepseek_v32 but Transformers does not recognize this architecture.

❯ pip list | grep transformer
transformers 5.0.0.dev0

❯ git clone https://github.com/huggingface/transformers.git
❯ cd transformers
❯ pip install -e .

@eousphorosok ill try that. the guys over in the deepseek repo said Transormers didn't implement it so we need to use the custom Tranformers in their inference package

Only part of transformers I am using in my cpu inference code is the tokenizer from transformers import AutoTokenizer. For the model I am just using safetensors directly.

Sign up or log in to comment