How to use BEncoderRT/tinyllama-multitask-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T") model = PeftModel.from_pretrained(base_model, "BEncoderRT/tinyllama-multitask-lora")
https://huggingface.co/BEncoderRT/tinyllama-multitask-lora/resolve/4d03cb64a2ebe962b2194cc086e92e56a3bea29b/tokenizer.json
hf download hf://BEncoderRT/tinyllama-multitask-lora@4d03cb64a2ebe962b2194cc086e92e56a3bea29b/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/BEncoderRT/tinyllama-multitask-lora/resolve/4d03cb64a2ebe962b2194cc086e92e56a3bea29b/tokenizer.json
