whatmodel.sh / Vicuna 13B v1.3

Vicuna 13B v1.3

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

Vicuna 13B v1.3 is an open-weights language model from LMSYS, released June 2023.

Catalogue identity notes

Maker repo lmsys/vicuna-13b-v1.3 @6566e9c: no licence tag on the card. Released 2023-06: month the maker's Hugging Face repo was created (createdAt 2023-06-18).

35.8±2.2#794 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 Vicuna 13B v1.3, out of 1132 with a score, then more from LMSYS.

#modelscorewhereRAMreleased
958WizardLM 13B V1.2 Microsoft36±1local~9.8GB2023-07
959Tulu 2 7B Allen Institute for AI36±2local~5.8GB2023-11
960Vicuna 13B v1.3 LMSYS36±2local~29GB2023-06
961xDAN-L1-Chat-RL-v1 xDAN-AI36±1local~6.1GB2023-12
962Llama 3 8B (base) Meta36±1local~6.6GB2024-04
more from LMSYS
888Vicuna 33B v1.3 LMSYS39±1local~23GB2023-06
949Vicuna 13B v1.5 LMSYS36±2local~9.8GB2023-08
979Vicuna 7B v1.5 16K LMSYS34±2local~5.8GB2023-07

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #423 of 466 * · 98% of its score · 2 tests

Beats Gemma 4 E2B, Code Llama 70B Instruct, Phi-3-mini-128k-instruct (Apr 2024) 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-controlled10.8% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 26/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 79%typical
AlpacaEval 1.0 win rate (vs text-davinci-003, GPT-4 judge)82.1% ✎▂▂·▆·▇▃▆█▆▄▂ beats 21/45very easy · avg 96%▇▇▇▇▇▇▇ 18%sharp · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs ~26.03 GB · from huggingface.co/lmsys (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='lmsys/vicuna-13b-v1.3', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/lmsys ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 98%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%Apache-2.0
prior · pull toward the middle▇ 2%
weighted average= 35.8

$ 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