How to use SoftALL/OBSIDIAN with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="SoftALL/OBSIDIAN")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("SoftALL/OBSIDIAN") model = AutoModelForSequenceClassification.from_pretrained("SoftALL/OBSIDIAN", device_map="auto")
https://huggingface.co/SoftALL/OBSIDIAN/resolve/b6bb8d09052d894ce5ae7f35c9dd855582e4ffb0/tokenizer.json
hf download hf://SoftALL/OBSIDIAN@b6bb8d09052d894ce5ae7f35c9dd855582e4ffb0/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/SoftALL/OBSIDIAN/resolve/b6bb8d09052d894ce5ae7f35c9dd855582e4ffb0/tokenizer.json
