whatmodel.sh / Pythia 1.4B
Pythia 1.4B
↗ share
+ contribute
Pythia 1.4B is an open-weights language model from EleutherAI, released February 2023. Its published size is 1.41B 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.
$ how it compares
The LLMs ranked either side of Pythia 1.4B, out of 828 with a score, then more from EleutherAI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 800 | GPT-Neo 2.7B | 18±1 | local | ||
| 801 |  GPT-3 babbage (API base model) | 18±1 | comparison only | ||
| 802 | Pythia 1.4B | 18±2 | local | ||
| 803 |  BLOOM 3B | 18±1 | local | ||
| 804 |  FastChat-T5 3B | 17±2 | local | ||
| more from EleutherAI | |||||
| 756 | GPT-NeoX-20B | 28±1 | local | ||
| 777 | Pythia 12B | 25±1 | local | ||
| 780 | GPT-J 6B | 25±1 | local | ||
$ what it's good at
other tests9 not in a task · 99% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| ARC Easy lab | 60.6% ✎ | ▃·▅▃▃▅·██▃██ beats 11/19 | 23% |
| SciQ lab | 86.5% ✎ | ▂··▂▃▂▂▆▃▃█▂ beats 11/19 | 16% |
| WinoGrande lab | 57.3% ✎ | ▄····▄▆▂▄▆▆█ beats 9/19 | 16% |
| PIQA lab | 71.1% ✎ | ▂·▄▄·▄▂▆▂▄█▄ beats 10/19 | 12% |
| ARC Challenge lab | 26.0% ✎ | █··▃·▁▁·▁▂▁▂ beats 10/19 | 12% |
| LAMBADA (OpenAI version), last-word accuracy lab | 61.6% ✎ | ▃··▅▃▃▅▅▅███ beats 11/19 | 10% |
| MedQA (USMLE, 4 options) | 27.5% ✎ | ▁▁··▄▁▁··▄▃█ beats 2/17 | 4.3% |
| MedMCQA | 31.5% ✎ | ▂▂··▄▄▂▂·▄██ beats 4/17 | 3.8% |
$ where to run it
llama.cpp · recommended
version
- 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 | shWindowsirm https://llama.app/install.ps1 | iex - Run Pythia 1.4B · needs ~0.9 GB · from huggingface.co/mradermacherchat in the terminal
llama cli -hf mradermacher/pythia-1.4b-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf mradermacher/pythia-1.4b-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Pythia 1.4B · needs ~0.9 GB · from huggingface.co/mradermacher
- Or download it in the terminal
lms get https://huggingface.co/mradermacher/pythia-1.4b-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
version
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run Pythia 1.4B · needs ~0.9 GB · from huggingface.co/mradermacherchat in the terminal
ollama run hf.co/mradermacher/pythia-1.4b-GGUF:Q4_K_M
Other ways to run it
- Run it as published · needs ~2.93 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-1.4b')('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… 90%, Open Medical-LLM Leaderboard… 10%
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
| source | results | share of the score |
|---|---|---|
 Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runs · lab-reported | 6 | 90% |
 Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results) | 3 | 10% |
| prior · pull toward the middle | 1% | |
| weighted average | = 17.8 |
$ improve this page
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