README.md

metadata

license: apache-2.0

Model Card for Jennny/flan-t5-base-summarization-bb

This repository contains the LoRA of flan-t5-base that has been fine-tuned on knkarthick/dialogsum dataset.

Usage

Use this adapter with peft library

# pip install peft transformers
import torch
from peft import PeftModel
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

base_model_id = "google/flan-t5-base"
peft_model_id = "Jennny/flan-t5-base-summarization-bb"

# Load tokenizer and models
tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForSeq2SeqLM.from_pretrained(
    base_model_id, torch_dtype=torch.bfloat16
).to(device)
model = PeftModel.from_pretrained(
    base_model_id,
    peft_model_id,
    torch_dtype=torch.bfloat16,
    is_trainable=False,
).to(device)