whatmodel.sh / BLOOM 7.1B

BLOOM 7.1B

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

BLOOM 7.1B is an open-weights language model from BigScience, released July 2022. Its published size is 7.07B parameters and a 2k-token context window. Licence: bigscience-bloom-rail-1.0.

Catalogue identity notes

BigScience BLOOM pretrained base model (not BLOOMZ).

21.0±0.9#684 of 719 LLMsfrom 19 benchmark results across 6 sources

$ how it compares

The LLMs ranked either side of BLOOM 7.1B, out of 828 with a score, then more from BigScience.

#modelscorewhereRAMreleased
788OpenAssistant SFT-4 Pythia 12B LAION (OpenAssistant)22±1local~9.5GB2023-04
789Pythia 2.8B EleutherAI21±1local~3.4GB2023-02
790BLOOM 7.1B BigScience21±1local~7.1GB2022-07
791OLMo 1B Allen Institute for AI21±2local~2.2GB2024-02
792Phi-1 (1.3B) Microsoft21±4local~2.4GB2023-09
more from BigScience
803BLOOM 3B BigScience18±1local~4GB2022-07
810BLOOM 1.7B BigScience14±1local~3.1GB2022-07
814BLOOM 1.1B BigScience11±1local~2.6GB2022-07

see all LLMs · find the ones that fit your machine

$ what it's good at

coding█···█··█··██ #1 of 5 * · 16% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
HumanEval lab7.7% ✎▄···▄·▄·█··▄ beats 4/5easy · avg 78%▇▇▇▇▇▇ 16%sharp
other tests18 not in a task · 84% of its score
testresultvs the others in its rundifficultycountswhy
ARC Challenge33.5% ✎▁·▁··▁▁▇▂█▆▃ beats 5/26easy · avg 85%▇▇▇▇▇▇▇▇▇ 23%sharp
WinoGrande64.6% ✎▁····▁··▁▂█▄ beats 11/26easy · avg 89%▇▇▇ 8.4%typical
BoolQ62.8% ✎▂▃▂▅▆▂▅▆█▂▂▂ beats 4/26easy · avg 91%▇▇▇ 7.9%at its level
SciQ90.1% ✎▁·▁·▁·▃▅▃█▄▁ beats 7/26very easy · avg 98%▇▇▇ 7.5%typical
ARC Easy57.4% ✎▁▁·▁▁▄▅▄█▅▁▃ beats 4/26easy · avg 88%▇▇▇ 6.9%at its level
HellaSwag62.3% ✎▃···▁▇▅█▇▃▁▁ beats 5/26very easy · avg 92%▇▇ 5.9%at its level
Natural Questions (closed book)8.1% ✎▁·▁·▁▂▁▃·▅▂█ beats 7/28medium · avg 58%▇▇ 4.9%typical
PIQA72.7% ✎▁·▁··▁▃▃█▅█▂ beats 3/26easy · avg 88%▇▇ 4.3%blunt · at its level
10 more tests
testresultvs the others in its rundifficultycountswhy
LAMBADA (OpenAI version), last-word accuracy57.6% ✎▁··▂▁▃▁▂▆█▅▃ beats 4/26very easy · avg 89%▇ 3.0%blunt · at its level
Factual knowledge recall, Premium2k exact match (10-shot)18.1% ✎▃▅▃··▅▃·█▃▃▅ beats 0/13easy · avg 67%▇ 2.7%typical
Factual knowledge recall, Premium2k exact match (zero-shot)3.2% ✎▅····▃▅·██·█ beats 0/13medium · avg 59%▇ 2.4%typical
Social IQA42.1% ✎▁···▁▃█▁▁▁·▁ beats 14/26medium · avg 59%▇ 1.8%blunt
OpenBookQA25.2% ✎█·▁▁▃·▁▃▅▇▃▄ beats 2/26medium · avg 53%▇ 1.7%too hard for it
TriviaQA26.3% ✎▁··▁█▃▃▃▄▅▄█ beats 12/28easy · avg 79%▇ 1.0%noisy
Open PT-LLM Leaderboard average (9 Portuguese tasks)28.9% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 27/276medium · avg 73%▇ 0.7%noisy
TruthfulQA MC238.9% ✎▅▃█▆▁▂▅···▁▁ beats 6/31medium · avg 64%▇ 0.6%blunt · at its level
COPA53.2% ✎▅·▃·▃··█▃··▃ beats 0/8easy · avg 92%▇ 0.4%at its level · noisy
HaluEval QA hallucination detection (accuracy)58.1% ✎█▁▁·▁▁·▁▃▁▁▁ beats 23/27medium · 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 7.1B · needs ~5.3 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/bloom-7b1-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/bloom-7b1-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 7.1B · needs ~5.3 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/bloom-7b1-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 7.1B · needs ~5.3 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/bloom-7b1-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~14.14 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-7b1', 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 · Stability AI — original Stabl… 71%, BLOOM: A 176B-Parameter Open-… 16%, Hallucinations Leaderboard re… 7% and 3 more

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
Stability AI — original StableLM zero-shot evaluation outputs10▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 71%Apache-2.0
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model — authors' own runs · lab-reported1▇▇▇▇▇ 16%CC BY 4.0
Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)4▇▇ 7%Apache-2.0
Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1)2▇▇ 5%CC-BY-4.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items (arXiv:2410.14897v1)1▇ 0%CC-BY-4.0
prior · pull toward the middle▇ 0%
weighted average= 21.0

$ 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