contacts-v1 tokenizer (5d68a24a899f)

Stable copy of timodonnell/contacts-v1-tokenizer at revision 5d68a24a899f, the exact tokenizer revision pinned by MarinFold #166.

Created so code that cannot reliably honor Hugging Face revision= can load the intended tokenizer directly from this repository's HEAD.

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "eczech/contacts-v1-tokenizer-5d68a24a899f"
)

Tokenizer artifacts are byte-for-byte copies of the linked source revision. Vocabulary: 2,845 tokens with IDs 0–2844. This README is the only modified file.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support