“Could not complete request to HuggingFace API, Status Code: 400, Error: Can’t load tokenizer using from_pretrained, please update its configuration: Can’t load tokenizer for ‘Crow34/Chloe’. If you were trying to load it from ‘Models - Hugging Face’, make sure you don’t have a local directory with the same name. Otherwise, make sure ‘Crow34/Chloe’ is the correct path to a directory containing all relevant files for a GPT2TokenizerFast tokenizer.”
Output
Hope you guys can help
Are you trying to load from a checkpoint on your machine? If so, did you double-check the contents of the Crow34/Chloe folder? It should contain several files used by Huggingface to initialize the tokenizer (tokenizer_config.json, spiece.model, etc). If you don’t see those files in Crow34/Chloe, find the correct folder that contains those files.
Alternatively, if you’re simply trying to load a pretrained Huggingface model, you should change "Crow34/Chloe" in your code to a valid Huggingface checkpoint (e.g., "gpt2").