Modelpublic

snowfly/t5-3b-wmt16-ro-en

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes7downloads

Model Card

模型介绍

—使用模型：t5-3b
—使用数据：wmt16 ro-en（共数据610320，使用了其中2000）
—使用分布式工具：deepspeed
—显卡：一张RTX 4090,24G
—目标：训练模型在ro-en上的翻译能力

使用方法

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

t5_qa_model = AutoModelForSeq2SeqLM.from_pretrained("snowfly/t5-3b-wmt16-ro-en")
t5_tok = AutoTokenizer.from_pretrained("snowfly/t5-3b-wmt16-ro-en")

input_ids = t5_tok("When was Franklin D. Roosevelt born?",
                   return_tensors="pt").input_ids
gen_output = t5_qa_model.generate(input_ids)[0]

print(t5_tok.decode(gen_output, skip_special_tokens=True))