How to use nabilfaieaz/tinyllama-med-full 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="nabilfaieaz/tinyllama-med-full")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nabilfaieaz/tinyllama-med-full") model = AutoModelForCausalLM.from_pretrained("nabilfaieaz/tinyllama-med-full", device_map="auto")
How to use nabilfaieaz/tinyllama-med-full with PEFT:
Task type is invalid.
https://huggingface.co/nabilfaieaz/tinyllama-med-full/resolve/main/tokenizer.json
hf download hf://nabilfaieaz/tinyllama-med-full/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/nabilfaieaz/tinyllama-med-full/resolve/main/tokenizer.json
