模型:
bigscience/mt0-base
我们提出了BLOOMZ & mT0,这是一组可以在几十种语言中零-shot跟踪人类指令的模型。我们在我们的跨语言任务混合(xP3)上对BLOOM&mT5预训练多语言模型进行微调,并发现我们得到的模型能够在未见过的任务和语言上实现跨语言泛化。
Multitask finetuned on 1239321 . Recommended for prompting in English. | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
Parameters | 300M | 580M | 1.2B | 3.7B | 13B | 560M | 1.1B | 1.7B | 3B | 7.1B | 176B |
Finetuned Model | 12310321 | 12311321 | 12312321 | 12313321 | 12314321 | 12315321 | 12316321 | 12317321 | 12318321 | 12319321 | 12320321 |
Multitask finetuned on 12321321 . Recommended for prompting in non-English. | |||||||||||
Finetuned Model | 12322321 | 12323321 | 12324321 | ||||||||
Multitask finetuned on 12325321 . Released for research purposes only. Strictly inferior to above models! | |||||||||||
Finetuned Model | 12326321 | 12327321 | 12328321 | ||||||||
Original pretrained checkpoints. Not recommended. | |||||||||||
Pretrained Model | 12329321 | 12330321 | 12331321 | 12332321 | 12333321 | 12334321 | 12335321 | 12336321 | 12337321 | 12338321 | 12339321 |
我们建议使用该模型执行用自然语言表达的任务。例如,给定提示“Translate to English: Je t’aime.”,该模型很可能会回答“I love you.”。我们论文中的一些提示思路:
欢迎在社区选项卡中分享您的生成结果!
# pip install -q transformers from transformers import AutoModelForSeq2SeqLM, AutoTokenizer checkpoint = "bigscience/mt0-base" tokenizer = AutoTokenizer.from_pretrained(checkpoint) model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint) inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt") outputs = model.generate(inputs) print(tokenizer.decode(outputs[0]))
# pip install -q transformers accelerate from transformers import AutoModelForSeq2SeqLM, AutoTokenizer checkpoint = "bigscience/mt0-base" tokenizer = AutoTokenizer.from_pretrained(checkpoint) model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint, torch_dtype="auto", device_map="auto") inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt").to("cuda") outputs = model.generate(inputs) print(tokenizer.decode(outputs[0]))
# pip install -q transformers accelerate bitsandbytes from transformers import AutoModelForSeq2SeqLM, AutoTokenizer checkpoint = "bigscience/mt0-base" tokenizer = AutoTokenizer.from_pretrained(checkpoint) model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint, device_map="auto", load_in_8bit=True) inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt").to("cuda") outputs = model.generate(inputs) print(tokenizer.decode(outputs[0]))
提示工程:性能可能会因提示而异。对于BLOOMZ模型,我们建议明确指示输入何时停止,以避免模型试图继续输入。例如,没有句号(.)结束的提示“Translate to English: Je t'aime”可能导致模型试图继续翻译法语句子。更好的提示示例是“Translate to English: Je t'aime.”,“Translate to English: Je t'aime. Translation:”,“What is "Je t'aime." in English?”等,在这些提示中,模型清楚知道何时应该回答。此外,我们建议尽可能向模型提供更多的上下文。例如,如果您希望它用泰卢固语回答,请告诉模型,例如“用泰卢固语用一句话解释神经网络中的反向传播是什么。 ”。
对于未见任务的零-shot结果,请参考我们的 paper & bigscience/evaluation-results 中的表7。侧边栏报告了最佳提示每个数据集配置的零-shot性能。
@misc{muennighoff2022crosslingual, title={Crosslingual Generalization through Multitask Finetuning}, author={Niklas Muennighoff and Thomas Wang and Lintang Sutawika and Adam Roberts and Stella Biderman and Teven Le Scao and M Saiful Bari and Sheng Shen and Zheng-Xin Yong and Hailey Schoelkopf and Xiangru Tang and Dragomir Radev and Alham Fikri Aji and Khalid Almubarak and Samuel Albanie and Zaid Alyafeai and Albert Webson and Edward Raff and Colin Raffel}, year={2022}, eprint={2211.01786}, archivePrefix={arXiv}, primaryClass={cs.CL} }