whatmodel.sh / Pythia 6.9B

Pythia 6.9B

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

Pythia 6.9B is an open-weights language model from EleutherAI, released February 2023. Its published size is 6.86B parameters and a 2k-token context window. Licence: apache-2.0.

Catalogue identity notes

Final (step 143000) checkpoint of the standard (non-deduplicated) Pythia model, repo main branch. Total parameter count from the Pythia model card.

23.4±0.7#681 of 719 LLMsfrom 27 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of Pythia 6.9B, out of 828 with a score, then more from EleutherAI.

#modelscorewhereRAMreleased
785StableLM-Base-Alpha 3B v2 Stability AI24±1local~13GB2023-08
786Qwen1.5 1.8B Chat Alibaba24±2local~2.7GB2024-01
787Pythia 6.9B EleutherAI23±1local~6.1GB2023-02
788OpenAssistant SFT-4 Pythia 12B LAION (OpenAssistant)22±1local~9.5GB2023-04
789Pythia 2.8B EleutherAI21±1local~3.4GB2023-02
more from EleutherAI
756GPT-NeoX-20B EleutherAI28±1local~14GB2022-02
777Pythia 12B EleutherAI25±1local~9.5GB2023-02
780GPT-J 6B EleutherAI25±1local~14GB2021-06

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests13 not in a task · 100% of its score
testresultvs the others in its rundifficultycountswhy
ARC Challenge +235.3% ✎▁·▁··▁▁▇▂█▆▃ beats 9/26easy · avg 85%▇▇▇▇▇▇▇▇▇▇▇ 28%sharp · several runs
WinoGrande +260.6% ✎▁····▁··▁▃█▄ beats 4/26easy · avg 89%▇▇▇▇▇▇ 15%several runs
ARC Easy +261.1% ✎▁▁·▁▁▄▅▄█▅▁▃ beats 7/26very easy · avg 90%▇▇▇▇▇ 12%at its level · several runs
SciQ +289.8% ✎▁·▁·▁·▃▅▃█▄▁ beats 5/26very easy · avg 98%▇▇▇▇ 10%several runs
BoolQ +164.0% ✎▂▃▂▅▆▂▅▆█▂▂▂ beats 5/26easy · avg 91%▇▇▇ 7.7%at its level · several runs
PIQA +275.1% ✎▁·▁··▁▁▃█▅█▂ beats 7/26easy · avg 88%▇▇▇ 7.0%blunt · at its level · several runs
HellaSwag +163.9% ✎▃···▁▇▅█▇▃▁▁ beats 7/26very easy · avg 92%▇▇▇ 6.7%at its level · several runs
OpenBookQA +125.8% ✎█·▃▁▃·▁▃▅▇▃▄ beats 6/26easy · avg 84%▇▇ 4.6%several runs
5 more tests
testresultvs the others in its rundifficultycountswhy
LAMBADA (OpenAI version), last-word accuracy +167.0% ✎▁··▂▁▁▁▂▆█▅▃ beats 9/26very easy · avg 89%▇▇ 4.0%blunt · at its level · several runs
Factual knowledge recall, Premium2k exact match (10-shot)21.7% ✎▃▅▃··▅▃·█▃▃▅ beats 2/13easy · avg 67%▇ 1.8%typical
Factual knowledge recall, Premium2k exact match (zero-shot)11.0% ✎▅····▃▅·██·█ beats 2/13medium · avg 59%▇ 1.8%typical
Social IQA40.7% ✎▁···▁▃█▁▁▁·▁ beats 3/26medium · avg 59%▇ 1.2%blunt
Open PT-LLM Leaderboard average (9 Portuguese tasks)29.0% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 6/276medium · avg 73%▇ 0.5%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 Pythia 6.9B · needs ~4.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/pythia-6.9b-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/pythia-6.9b-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 Pythia 6.9B · needs ~4.4 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/pythia-6.9b-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 Pythia 6.9B · needs ~4.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/pythia-6.9b-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~13.85 GB · from huggingface.co/EleutherAI (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='EleutherAI/pythia-6.9b', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/EleutherAI ↗

$ how the score was worked out · Stability AI — original Stabl… 48%, OLMo: Accelerating the Scienc… 25%, Pythia: A Suite for Analyzing… 23% and 2 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▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 48%Apache-2.0
OLMo: Accelerating the Science of Language Models — authors' own runs8▇▇▇▇▇▇▇▇ 25%CC BY 4.0
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runs · lab-reported6▇▇▇▇▇▇▇ 23%CC BY-SA 4.0
Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1)2▇ 4%CC-BY-4.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 23.4

$ 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