Anthropic
Search results
The BLOOM model has been proposed with its various versions through the BigScience Workshop. BigScience is inspired by other open science initiatives where researchers have pooled their time and resources to collectively achieve a higher impact. The architecture of BLOOM is essentially similar to GPT3 (auto-regressive model for next token ...
- bigscience/bloom · Hugging Face
Model Details. BLOOM is an autoregressive Large Language...
- Introducing The World's Largest Open Multilingual Language ...
Today, we release BLOOM, the first multilingual LLM trained...
- Bloom Demo - a Hugging Face Space by huggingface
A "whatpu" is a small, furry animal native to Tanzania. An...
- Optimization story: Bloom inference - Hugging Face
Bloom is a 352GB (176B parameters in bf16) model, we need at...
- bigscience/bloom · Hugging Face
- Model Details
- Training
- Uses
- More Information
- Model Card Authors
BLOOM is an autoregressive Large Language Model (LLM), trained to continue text from a prompt on vast amounts of text data using industrial-scale computational resources. As such, it is able to output coherent text in 46 languages and 13 programming languages that is hardly distinguishable from text written by humans. BLOOM can also be instructed t...
This section provides information about the training data, the speed and size of training elements, and the environmental impact of training.It is useful for people who want to learn more about the model inputs and training footprint.
This section addresses questions around how the model is intended to be used, discusses the foreseeable users of the model (including those affected by the model), and describes uses that are considered out of scope or misuse of the model.It is useful for anyone considering using the model or who is affected by the model.
This section provides links to writing on dataset creation, technical specifications, lessons learned, and initial results.
Ordered roughly chronologically and by amount of time spent on creating this model card. Margaret Mitchell, Giada Pistilli, Yacine Jernite, Ezinwanne Ozoani, Marissa Gerchick, Nazneen Rajani, Sasha Luccioni, Irene Solaiman, Maraim Masoud, Somaieh Nikpoor, Carlos Muñoz Ferrandis, Stas Bekman, Christopher Akiki, Danish Contractor, David Lansky, Angel...
BLOOM is a 176 billion parameter LLM that can generate text in 46 natural and 13 programming languages. It is the result of a year-long collaboration of over 1000 researchers from 70+ countries and 250+ institutions, and it is available for download, study and use on Hugging Face.
Jul 12, 2022 · BLOOM is a 176 billion parameter LLM that can generate text in 46 natural and 13 programming languages. It is the result of a year-long collaboration of over 1000 researchers from 70+ countries and 250+ institutions, and is released under a Responsible AI License.
Nov 9, 2022 · BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 59 languages. It is a collaborative project of hundreds of researchers and is released under the Responsible AI License.
A "whatpu" is a small, furry animal native to Tanzania. An example of a sentence that uses the word whatpu is: We were traveling in Africa and we saw these very cute whatpus. To do a "farduddle" means to jump up and down really fast. An example of a sentence that uses the word farduddle is: 32. Sample. Sample 1.
People also ask
What is pretrainedconfig in Bloom?
What does bloom_Gelu_forward() do?
What is bloomforcausallm forward method?
Oct 12, 2022 · Bloom is a 352GB (176B parameters in bf16) model, we need at least that much GPU RAM to make it fit. We briefly explored offloading to CPU on smaller machines but the inference speed was orders of magnitude slower so we discarded it. Then we wanted to basically use the pipeline. So it's dogfooding and this is what the API uses under the hood ...
