whatmodel.sh / Baize v2 13B

Baize v2 13B

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

Baize v2 13B is an open-weights language model from Project Baize, released May 2023. Licence: cc-by-nc-4.0.

Catalogue identity notes

Maker repo project-baize/baize-v2-13b @a3c4bbc: licence tag cc-by-nc-4.0. Released 2023-05: month the maker's Hugging Face repo was created (createdAt 2023-05-23).

31.6±2.4#846 of 949 LLMsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Baize v2 13B, out of 1132 with a score, then more from Project Baize.

#modelscorewhereRAMreleased
1015Qwen-7B (base) Alibaba32±1local~6.6GB2023-08
1016Phi-1.5 (1.3B) Microsoft32±1local~2.4GB2023-09
1017Baize v2 13B Project Baize32±2local~43GB2023-05
1018Falcon-H1 1.5B Instruct TII31±4local~2.4GB2025-05
1019Flan-T5 XL Google31±2local~14GB2022-10
more from Project Baize
1041Baize v2 7B Project Baize29±3local~16GB2023-05

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #448 of 466 * · 97% of its score · 2 tests

Beats Phi-2 (2.7B), Qwen1.5 4B Chat here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Granite 4.0 350M here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled7.0% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 14/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 68%too hard for it
AlpacaEval 1.0 win rate (vs text-davinci-003, GPT-4 judge)67.0% ✎▂▂·▆·▇▃▆█▆▄▂ beats 14/45very easy · avg 96%▇▇▇▇▇▇▇▇▇▇▇▇ 30%sharp · at its level · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs ~39.05 GB · from huggingface.co/project-baize (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='project-baize/baize-v2-13b', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/project-baize ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 97%

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
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%Apache-2.0
prior · pull toward the middle▇ 3%
weighted average= 31.6

$ 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