How to use bloomberg/KBIR with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, KLMForReplacementAndMaskedLM tokenizer = AutoTokenizer.from_pretrained("bloomberg/KBIR") model = KLMForReplacementAndMaskedLM.from_pretrained("bloomberg/KBIR", device_map="auto")
https://huggingface.co/bloomberg/KBIR/resolve/main/vocab.json
hf download hf://bloomberg/KBIR/vocab.json
curl -L -o vocab.json https://huggingface.co/bloomberg/KBIR/resolve/main/vocab.json
