whatmodel.sh / BLOOM 1.1B

BLOOM 1.1B

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

BLOOM 1.1B is an open-weights language model from BigScience, released July 2022. Its published size is 1.07B parameters and a 2k-token context window. Licence: bigscience-bloom-rail-1.0.

Catalogue identity notes

BigScience BLOOM pretrained base model (not BLOOMZ).

10.6±1.4#706 of 719 LLMsfrom 11 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of BLOOM 1.1B, out of 828 with a score, then more from BigScience.

#modelscorewhereRAMreleased
812GPT-Neo 1.3B EleutherAI14±2local~7.1GB2021-03
813GPT-2 XL (1.5B) OpenAI11±1local~2.8GB2019-11
814BLOOM 1.1B BigScience11±1local~2.6GB2022-07
815Pythia 410M EleutherAI10±2local~1.8GB2023-02
816GPT-3 ada (API base model) OpenAI10±2comparison only2020-06
more from BigScience
790BLOOM 7.1B BigScience21±1local~7.1GB2022-07
803BLOOM 3B BigScience18±1local~4GB2022-07
810BLOOM 1.7B BigScience14±1local~3.1GB2022-07

see all LLMs · find the ones that fit your machine

$ what it's good at

coding█···█··█··██ #4 of 5 * · 15% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
HumanEval lab2.5% ✎▄···▄·▄·█··▄ beats 1/5easy · avg 78%▇▇▇▇▇▇ 15%sharp · too hard for it
other tests10 not in a task · 84% of its score
testresultvs the others in its rundifficultycountswhy
ARC Easy51.5% ✎▃·▅▃▃▅·██▃██ beats 5/19very easy · avg 90%▇▇▇▇▇▇▇▇ 21%at its level
SciQ83.3% ✎▂··▂▃▂▂▆▃▃█▂ beats 6/19very easy · avg 98%▇▇▇▇▇▇▇▇ 20%typical
PIQA67.2% ✎▂·▄▄·▄▂▆▂▄█▄ beats 6/19easy · avg 88%▇▇▇▇ 11%blunt · at its level
LAMBADA (OpenAI version), last-word accuracy42.6% ✎▃··▅▃▃▅▅▅███ beats 4/19very easy · avg 89%▇▇▇▇ 10%blunt · at its level
WinoGrande54.7% ✎▄····▄▆▃▄▆▆█ beats 7/19easy · avg 89%▇▇▇▇ 9.4%typical
Natural Questions (closed book)2.9% ✎▁·▁·▃▂▁▂·▅▂█ beats 2/28medium · avg 58%▇▇ 5.5%too hard for it
ARC Challenge23.6% ✎█··▁·▁▁·▁▂▁▂ beats 4/19medium · avg 72%▇▇ 4.9%sharp · too hard for it
TruthfulQA MC241.8% ✎▅▃█▆▁▂▅···▁▁ beats 13/31medium · avg 64%▇ 1.4%blunt · at its level
2 more tests
testresultvs the others in its rundifficultycountswhy
TriviaQA8.6% ✎▁··▁█▃▃▁▄▅▄█ beats 2/28easy · avg 79%▇ 1.3%noisy
HaluEval QA hallucination detection (accuracy)44.9% ✎█▁▁·▁▁·▁▁▁▁▁ beats 11/27medium · avg 70%▇ 0.2%sharp · too hard for it · noisy

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run BLOOM 1.1B · needs ~1 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/bloom-1b1-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/bloom-1b1-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run BLOOM 1.1B · needs ~1 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/bloom-1b1-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run BLOOM 1.1B · needs ~1 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/bloom-1b1-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~2.13 GB · from huggingface.co/bigscience (official)
    uv run --with torch --with 'transformers<5' python -c "from transformers import pipeline; print(pipeline('text-generation', model='bigscience/bloom-1b1')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/bigscience ↗

$ how the score was worked out · Pythia: A Suite for Analyzing… 76%, BLOOM: A 176B-Parameter Open-… 15%, Hallucinations Leaderboard re… 8%

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
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runs6▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 76%CC BY-SA 4.0
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model — authors' own runs · lab-reported1▇▇▇▇ 15%CC BY 4.0
Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)4▇▇ 8%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 10.6

$ 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