whatmodel.sh / RedPajama-INCITE 7B Base

RedPajama-INCITE 7B Base

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

RedPajama-INCITE 7B Base is an open-weights language model from Together, released June 2023. Its published size is 6.9B parameters and a 2k-token context window. Licence: apache-2.0.

Catalogue identity notes

Base model (not -Chat/-Instruct). The OLMo paper labels it 'RPJ-INCITE-7B'.

27.2±0.8#660 of 719 LLMsfrom 20 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of RedPajama-INCITE 7B Base, out of 828 with a score, then more from Together.

#modelscorewhereRAMreleased
759StarCoderBase 3B BigCode28±1local~3.4GB2023-06
760Granite 3.0 1B-A400M Instruct IBM27±1local~2.3GB2024-10
761RedPajama-INCITE 7B Base Together27±1local~16GB2023-06
762ChatGLM3-6B Zhipu AI (THUDM)27±2local~5.8GB2023-10
763Granite 4.0 H 350M IBM27±1local~1.7GB2025-10
more from Together
778RedPajama-INCITE Base 3B v1 Together25±3local~3.4GB2023-05

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests12 not in a task · 100% of its score
testresultvs the others in its rundifficultycountswhy
ARC Challenge +139.4% ✎▁·▁··▁▁▇▂█▆▃ beats 12/26easy · avg 85%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 37%sharp · several runs
WinoGrande +164.3% ✎▁····▁··▁▂█▄ beats 10/26easy · avg 89%▇▇▇▇▇ 14%at its level · several runs
BoolQ +170.8% ✎▂▃▂▅▆▂▅▆█▂▂▂ beats 14/26easy · avg 91%▇▇▇▇ 10%at its level · several runs
ARC Easy +169.2% ✎▁▁·▁▁▄▅▄█▅▁▃ beats 17/26easy · avg 88%▇▇▇ 8.2%at its level · several runs
HellaSwag +170.3% ✎▃···▁▇▅█▇▃▁▁ beats 13/26very easy · avg 92%▇▇▇ 7.7%at its level · several runs
SciQ +192.7% ✎▁·▁·▁·▃▅▃█▄▁ beats 13/26very easy · avg 98%▇▇▇ 7.2%several runs
OpenBookQA +129.0% ✎█·▁▁▃·▁▃▅▇▃▄ beats 11/26easy · avg 84%▇▇▇ 6.9%at its level · several runs
PIQA +177.1% ✎▁·▁··▁▁▃█▅█▂ beats 15/26easy · avg 88%▇▇ 4.9%blunt · at its level · several runs
4 more tests
testresultvs the others in its rundifficultycountswhy
LAMBADA (OpenAI version), last-word accuracy71.3% ✎▁··▂▁▁▁▂▆█▅▃ beats 19/26very easy · avg 89%▇ 2.0%blunt · at its level
Social IQA42.6% ✎▁···▁▃█▁▁▁·▁ beats 17/26medium · avg 59%▇ 1.7%blunt
Open PT-LLM Leaderboard average (9 Portuguese tasks)33.0% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 4/276medium · avg 73%▇ 0.8%noisy
TruthfulQA MC233.0% ✎█·█·█▄···▄·█ beats 0/9medium · avg 61%▇ 0.4%blunt · at its level

$ where to run it

Other ways to run it

  1. Run it as published · needs ~13.85 GB · from huggingface.co/togethercomputer
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='togethercomputer/RedPajama-INCITE-7B-Base', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/togethercomputer ↗

$ how the score was worked out · Stability AI — original Stabl… 66%, OLMo: Accelerating the Scienc… 33%, Open Portuguese LLM Leaderboa… 1%

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
Stability AI — original StableLM zero-shot evaluation outputs11▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 66%Apache-2.0
OLMo: Accelerating the Science of Language Models — authors' own runs8▇▇▇▇▇▇▇▇▇▇ 33%CC BY 4.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 27.2

$ 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