The BLOOM model is capable of following human instructions in dozens of languages. It is designed to continue text from a given prompt using vast amounts of text data and industrial-scale computational resources.
We recommend using the model to perform tasks expressed in natural language. For example, given the prompt "Translate to English: Je t’aime.", the model will most likely answer "I love you.". Some prompt ideas from the paper:
Suggest at least five related search terms to "Mạng neural nhân tạo".
Write a fairy tale about a troll saving a princess from a dangerous dragon. The fairy tale is a masterpiece that has achieved praise worldwide and its moral is "Heroes Come in All Shapes and Sizes". Story (in Spanish).
Explain in a sentence in Telugu what is backpropagation in neural networks.
BLOOM is the world's largest open multilingual language model with 176 billion parameters. It is trained to generate text in 46 natural languages and 13 programming languages. BLOOM can be used for text generation, multilingual tasks, or for language understanding models and applications.
The performance of BLOOM may vary depending on the prompt. We recommend making it very clear when the input stops to avoid the model trying to continue it.
For example, the prompt "Translate to English: Je t'aime" without the full stop (.) at the end, may result in the model trying to continue the French sentence.
Some better prompts to achieve the desired outcome include: "Translate to English: Je t'aime." or "What is "Je t'aime." in English?". These prompts make it clear on what the model should answer.
For optimal performance, we also recommend providing the model with as much context as possible. For example, if you want it to answer in Telugu, then tell the model, e.g "Explain in a sentence in Telugu what backpropogation is in neural networks.".
Hugging Face - BLOOM
Contact us with your foundation model usage requirements.