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