whatmodel.sh / Pythia 2.8B

Pythia 2.8B

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

Pythia 2.8B is an open-weights language model from EleutherAI, released February 2023. Its published size is 2.78B 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.

21.2±1.3#683 of 719 LLMsfrom 14 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Pythia 2.8B, out of 828 with a score, then more from EleutherAI.

#modelscorewhereRAMreleased
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
790BLOOM 7.1B BigScience21±1local~7.1GB2022-07
791OLMo 1B Allen Institute for AI21±2local~2.2GB2024-02
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 tests11 not in a task · 99% of its score
testresultvs the others in its rundifficultycountswhy
WinoGrande lab +159.4% ✎▄····▄▆▂▄▆▆█ beats 11/19easy · avg 89%▇▇▇▇▇▇▇▇▇ 22%several runs
ARC Easy lab64.4% ✎▃·▅▃▃▅·██▃██ beats 13/19very easy · avg 90%▇▇▇▇▇▇▇ 17%at its level
ARC Challenge lab29.5% ✎█··▁·▁▁·▃▂▁▂ beats 13/19medium · avg 72%▇▇▇▇▇ 12%sharp · too hard for it
PIQA lab +173.9% ✎▂·▄▄·▄▂▆▂▄█▄ beats 13/19easy · avg 88%▇▇▇▇▇ 11%blunt · at its level · several runs
SciQ lab88.2% ✎▂··▂▃▂▂▆▃▃█▂ beats 12/19very easy · avg 98%▇▇▇▇ 10%typical
LAMBADA (OpenAI version), last-word accuracy lab +164.7% ✎▃··▅▃▃▅▅▅███ beats 13/19very easy · avg 89%▇▇▇▇ 10%blunt · at its level · several runs
HellaSwag59.3% ✎▁▁▁▁▂▂▃▇█▆▅▃ beats 18/85very easy · avg 90%▇▇ 5.8%at its level · small run
MedQA (USMLE, 4 options)24.3% ✎▃▁··▄▁▁··▄▃█ beats 0/17easy · avg 76%▇▇ 4.6%sharp · too hard for it
3 more tests
testresultvs the others in its rundifficultycountswhy
MedMCQA27.2% ✎▂▃··▄▄▂▂·▄██ beats 1/17medium · avg 68%▇ 3.6%typical
Open PT-LLM Leaderboard average (9 Portuguese tasks)24.0% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 8/276medium · avg 73%▇ 1.4%noisy
PubMedQA64.0% ✎▂·▂▆·▄▂▄▄▂█▂ beats 5/17medium · avg 77%▇ 1.0%blunt · at its level

$ 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 2.8B · needs ~1.8 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/pythia-2.8b-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/pythia-2.8b-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 2.8B · needs ~1.8 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/pythia-2.8b-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 2.8B · needs ~1.8 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/pythia-2.8b-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~5.68 GB · from huggingface.co/EleutherAI (official)
    uv run --with torch --with 'transformers<5' python -c "from transformers import pipeline; print(pipeline('text-generation', model='EleutherAI/pythia-2.8b')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/EleutherAI ↗

$ how the score was worked out · Pythia: A Suite for Analyzing… 70%, RedPajama — original zero-sho… 19%, Open Medical-LLM Leaderboard… 9% and 1 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
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runs · lab-reported6▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 70%CC BY-SA 4.0
RedPajama — original zero-shot 3B comparison4▇▇▇▇▇▇ 19%CC BY 4.0
Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)3▇▇▇ 9%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 21.2

$ 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