whatmodel.sh / FastChat-T5 3B

FastChat-T5 3B

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

FastChat-T5 3B is an open-weights language model from LMSYS, released April 2023. Its published size is 3B parameters. Licence: apache-2.0.

Catalogue identity notes

Comparison-only. Arena entry 'fastchat-t5-3b' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'fastchat-t5-3b' as 'FastChat-T5-3B' (LMSYS, Apache 2.0), linking https://huggingface.co/lmsys/fastchat-t5-3b-v1.0. Maker repo lmsys/fastchat-t5-3b-v1.0 @0b1da23: licence tag apache-2.0. Parameters: card: 'fine-tuning Flan-t5-xl (3B parameters)'. Released 2023-04: month the maker's Hugging Face repo was created (createdAt 2023-04-27).

17.4±2.0#697 of 719 LLMsfrom 3 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of FastChat-T5 3B, out of 828 with a score, then more from LMSYS.

#modelscorewhereRAMreleased
802Pythia 1.4B EleutherAI18±2local~2.4GB2023-02
803BLOOM 3B BigScience18±1local~4GB2022-07
804FastChat-T5 3B LMSYS17±2local~8.5GB2023-04
805Dolly v2 12B Databricks17±2comparison only2023-04
806OPT-1.3B Meta16±1local~4.3GB2022-05
more from LMSYS
635Vicuna 33B v1.3 LMSYS39±1local~23GB2023-06
679Vicuna 13B v1.5 LMSYS36±2local~9.8GB2023-08
716Vicuna 7B v1.5 LMSYS33±1local~5.8GB2023-08

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▃▁▁▃▅▄▅█▆▆▇▃ #392 of 393 · 98% of its score · 3 tests

Trails Gemma 3 270M IT here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)879.0 ✎▃▁▂▁▃▇█▆▇▄▂▂ beats 4/95avg 1201▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%blunt
LMArena (text)992.5 ✎▃▁▁▂▃▃▃▆▆▇█▃ beats 3/379avg 1268▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%blunt
MT-Bench (GPT-4 single-answer grading, LMSYS runs) lab3.0400 MT-Bench score (1-10) ✎▆▂▂▆▆▄██▂▄▄▆ beats 2/28avg 8.819 MT-Bench score (1-10)▇▇▇▇▇▇▇▇▇▇▇▇ 30%sharp · noisy

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~6.71 GB, NVIDIA only · from github.com/lm-sys (official)
    pip3 install "fschat[model_worker,webui]" && python3 -m fastchat.serve.cli --model-path lmsys/fastchat-t5-3b-v1.0

Official weights and documentation: huggingface.co/lmsys ↗

$ how the score was worked out · Polyrating: A Cost-Effective… 34%, LMArena leaderboard dataset 34%, LMSYS Chatbot Arena leaderboa… 30%

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
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇▇▇▇▇▇▇▇▇ 34%CC-BY-4.0
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇ 34%CC BY 4.0
LMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard table · lab-reported1▇▇▇▇▇▇▇▇▇ 30%Apache-2.0
prior · pull toward the middle▇ 2%
weighted average= 17.4

$ 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