whatmodel.sh / BLOOM 176B

BLOOM 176B

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

BLOOM 176B is an open-weights language model from BigScience, released July 2022. Its published size is 176.2B parameters and a 2k-token context window. Licence: bigscience-bloom-rail-1.0.

Catalogue identity notes

BigScience BLOOM pretrained base model (not BLOOMZ).

26.4±1.9#887 of 949 LLMsfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of BLOOM 176B, out of 1132 with a score, then more from BigScience.

#modelscorewhereRAMreleased
1062Qwen2.5 0.5B Instruct Alibaba27±2local~1.8GB2024-09
1063GPT-3 text-davinci-001 OpenAI26±3comparison only2022-01
1064BLOOM 176B BigScience26±2local~372GB2022-07
1065GPT4All-13B-Snoozy Nomic AI26±2local~56GB2023-04
1066OPT-13B (13 billion parameters) Meta26±1local~29GB2022-05
more from BigScience
1090BLOOM 7.1B BigScience21±1local~7.1GB2022-07
1106BLOOM 3B BigScience18±1local~4GB2022-07
1113BLOOM 1.7B BigScience14±1local~3.1GB2022-07

see all LLMs · find the ones that fit your machine

$ what it's good at

coding█··█·█·██··█ #1 of 6 * · 96% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
HumanEval lab15.5% ✎▄···▄·▄·█··▄ beats 5/5easy · avg 78%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%sharp
other tests1 not in a task · 2.0% of its score
testresultvs the others in its rundifficultycountswhy
COPA57.6% ✎▅·▃·▃··█▃··▃ beats 2/8easy · avg 92%▇ 2.0%at its level · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs ~352.49 GB · from huggingface.co/bigscience (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='bigscience/bloom', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/bigscience ↗

$ how the score was worked out · BLOOM: A 176B-Parameter Open-… 96%, From Test-Taking to Test-Maki… 2%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model — authors' own runs · lab-reported1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%CC BY 4.0
From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items (arXiv:2410.14897v1)1▇ 2%CC-BY-4.0
prior · pull toward the middle▇ 2%
weighted average= 26.4

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json