--- datasets: - bigscience/xP3 license: bigscience-bloom-rail-1.0 language: - ak - ar - as - bm - bn - ca - code - en - es - eu - fon - fr - gu - hi - id - ig - ki - kn - lg - ln - ml - mr - ne - nso - ny - or - pa - pt - rn - rw - sn - st - sw - ta - te - tn - ts - tum - tw - ur - vi - wo - xh - yo - zh - zu programming_language: - C - C++ - C# - Go - Java - JavaScript - Lua - PHP - Python - Ruby - Rust - Scala - TypeScript pipeline_tag: text-generation widget: - text: "一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。Would you rate the previous review as positive, neutral or negative?" example_title: "zh-en sentiment" - text: "一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评？" example_title: "zh-zh sentiment" - text: "Suggest at least five related search terms to \"Mạng neural nhân tạo\"." example_title: "vi-en query" - text: "Proposez au moins cinq mots clés concernant «Réseau de neurones artificiels»." example_title: "fr-fr query" - text: "Explain in a sentence in Telugu what is backpropagation in neural networks." example_title: "te-en qa" - text: "Why is the sky blue?" example_title: "en-en qa" - text: "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):" example_title: "es-en fable" - text: "Write a fable about wood elves living in a forest that is suddenly invaded by ogres. The fable is a masterpiece that has achieved praise worldwide and its moral is \"Violence is the last refuge of the incompetent\". Fable (in Hindi):" example_title: "hi-en fable" --- # Table of Contents 1. [Model Summary](#model=summary) 2. [Use](#use) 3. [Bias, Risks, and Limitations](#bias-risks-and-limitations) 4. [Training Details](#training-details) 5. [Evaluation](#evaluation) 6. [Environmental Impact](#environmental-impact) 7. [Citation](#citation) 9. [How To Get Started With the Model](#how-to-get-started-with-the-model) # Model Summary > We present BLOOMZ & mT0, a family of models capable of following human instructions in dozens of languages zero-shot. We finetune BLOOM & mT5 pretrained multilingual language models on our crosslingual task mixture (xP3) and find our resulting models capable of crosslingual generalization to unseen tasks & languages. - **Repository:** [bigscience-workshop/xmtf](https://github.com/bigscience-workshop/xmtf) - **Paper:** [TODO] - **Point of Contact:** [Niklas Muennighoff](mailto:niklas@hf.co) - **BLOOMZ & mT0 Model Family:** |Name|Explanation| |----|-----------| |[bloomz-560m](https://huggingface.co/bigscience/bloomz-560m)| 560M parameter multitask finetuned version of [bloom-560m](https://huggingface.co/bigscience/bloom-560m) on [xP3](https://huggingface.co/bigscience/xP3)| |[bloomz-1b1](https://huggingface.co/bigscience/bloomz-1b1)| 1.1B parameter multitask finetuned version of [bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) on [xP3](https://huggingface.co/bigscience/xP3)| |[bloomz-1b7](https://huggingface.co/bigscience/bloomz-1b7)| 1.7B parameter multitask finetuned version of [bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) on [xP3](https://huggingface.co/bigscience/xP3)| |[bloomz-3b](https://huggingface.co/bigscience/bloomz-3b)| 3B parameter multitask finetuned version of [bloom-3b](https://huggingface.co/bigscience/bloom-3b) on [xP3](https://huggingface.co/bigscience/xP3)| |[bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1)|7.1B parameter multitask finetuned version of [bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) on [xP3](https://huggingface.co/bigscience/xP3)| |[bloomz](https://huggingface.co/bigscience/bloomz)|176B parameter multitask finetuned version of [bloom](https://huggingface.co/bigscience/bloom) on [xP3](https://huggingface.co/bigscience/xP3)| ||| |[bloomz-7b1-mt](https://huggingface.co/bigscience/bloomz-7b1-mt)|7.1B parameter multitask finetuned version of [bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) on [xP3](https://huggingface.co/bigscience/xP3) & [xP3mt](https://huggingface.co/bigscience/xP3mt). **Better than [bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1) when prompting in non-English**| |[bloomz-mt](https://huggingface.co/bigscience/bloomz-mt)| 176B parameter multitask finetuned version of [bloom](https://huggingface.co/bigscience/bloom) on [xP3](https://huggingface.co/bigscience/xP3) & [xP3mt](https://huggingface.co/bigscience/xP3mt). **Better than [bloomz](https://huggingface.co/bigscience/bloomz) when prompting in non-English**| ||| |[bloomz-7b1-p3](https://huggingface.co/bigscience/bloomz-7b1)| 7.1B parameter multitask finetuned version of [bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) on [P3](https://huggingface.co/bigscience/P3). **Released for research purposes, performance is inferior to [bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1)**| |[bloomz-p3](https://huggingface.co/bigscience/bloomz)| 176B parameter multitask finetuned version of [bloom](https://huggingface.co/bigscience/bloom) on [P3](https://huggingface.co/bigscience/P3). **Released for research purposes, performance is inferior to [bloomz](https://huggingface.co/bigscience/bloomz)**| ||| ||| |[mt0-small](https://huggingface.co/bigscience/mt0-xxl)|300M parameter multitask finetuned version of [mt5-small](https://huggingface.co/google/mt5-small) on [xP3](https://huggingface.co/bigscience/xP3)| |[mt0-base](https://huggingface.co/bigscience/mt0-xxl)|580M parameter multitask finetuned version of [mt5-base](https://huggingface.co/google/mt5-base) on [xP3](https://huggingface.co/bigscience/xP3)| |[mt0-large](https://huggingface.co/bigscience/mt0-xxl)|1.2B parameter multitask finetuned version of [mt5-large](https://huggingface.co/google/mt5-large) on [xP3](https://huggingface.co/bigscience/xP3)| |[mt0-xl](https://huggingface.co/bigscience/mt0-xxl)|3.7B parameter multitask finetuned version of [mt5-xl](https://huggingface.co/google/mt5-xl) on [xP3](https://huggingface.co/bigscience/xP3)| |[mt0-xxl](https://huggingface.co/bigscience/mt0-xxl)|13B parameter multitask finetuned version of [mt5-xxl](https://huggingface.co/google/mt5-xxl) on [xP3](https://huggingface.co/bigscience/xP3)| ||| |[mt0-xxl-mt](https://huggingface.co/bigscience/mt0-xxl-mt)|13B parameter multitask finetuned version of [mt5-xxl](https://huggingface.co/google/mt5-xxl) on [xP3](https://huggingface.co/bigscience/xP3) & [xP3mt](https://huggingface.co/bigscience/xP3mt). **Better than [mt0-xxl](https://huggingface.co/bigscience/mt0-xxl) when prompting in non-English**| ||| |[mt0-xxl-p3](https://huggingface.co/bigscience/mt0-xxl-p3)| 13B parameter multitask finetuned version of [mt5-xxl](https://huggingface.co/google/mt5-xxl) on [P3](https://huggingface.co/bigscience/P3). **Released for research purposes, performance is inferior to [mt0-xxl](https://huggingface.co/bigscience/mt0-xxl)**| |----|-----------| # Intended uses You can use the models to perform inference on tasks by specifying your query in natural language, and the models will generate a prediction. For instance, you can ask *"Translate this to Chinese: Je t'aime."*, and the model will hopefully generate *"我爱你"*. # How to use Here is how to use the model in PyTorch: TODO: Better code with auto-precision? ```python from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-560m") model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-560m") inputs = tokenizer.encode("Is this review positive or negative? Review: this is the best cast iron skillet you will ever buy", return_tensors="pt") outputs = model.generate(inputs) print(tokenizer.decode(outputs[0])) ``` To use another checkpoint, replace the path in `AutoTokenizer` and `AutoModelForCausalLM`. **Note: 176B models are trained with bfloat16, while smaller models are trained with fp16. We recommend using the same precision type or fp32 at inference** # Limitations - Large model size may require large computational resources - High performance variance depending on the prompt # BibTeX entry and citation info ```bibtex TODO ```