| # Model summary | |
| Train flan-T5-large on alpaca dataset with LoRA | |
| # training | |
| * torch==2.0.0+cu117 | |
| * transformers==4.28.0.dev0 | |
| * 8 x V100 32G | |
| # How to use | |
| ```python | |
| import transformers | |
| from peft import PeftModel | |
| base_model = transformers.AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-large") | |
| peft_model = PeftModel.from_pretrained("zirui3/flan-t5-large-alpaca") | |
| inputs = tokenizer("Any instruction that you like.", return_tensors="pt") | |
| outputs = peft_model.generate(**inputs, max_length=128, do_sample=True) | |
| print(tokenizer.batch_decode(outputs, skip_special_tokens=True) | |
| ``` |