How to use Feluda/Zephyr-7b-QnA with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="Feluda/Zephyr-7b-QnA")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Feluda/Zephyr-7b-QnA") model = AutoModelForCausalLM.from_pretrained("Feluda/Zephyr-7b-QnA", device_map="auto")
https://huggingface.co/Feluda/Zephyr-7b-QnA/resolve/main/tokenizer.json
hf download hf://Feluda/Zephyr-7b-QnA/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/Feluda/Zephyr-7b-QnA/resolve/main/tokenizer.json
