whatmodel.sh / Code Tulu 2 7B

Code Tulu 2 7B

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

Code Tulu 2 7B is an open-weights language model from Allen Institute for AI, released November 2023. Its published size is 7B parameters. Licence: AI2 ImpACT Low-risk; Llama 2 base terms.

Catalogue identity notes

Exact full-precision model evaluated in the Tulu 2 paper (arXiv:2311.10702v2). QLoRA ablations are separate and not imported.

Model information sources

Release date ↗ · Weights licence ↗

37.6±1.8#568 of 719 LLMsfrom 5 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Code Tulu 2 7B, out of 828 with a score, then more from Allen Institute for AI.

#modelscorewhereRAMreleased
659BioMistral-7B BioMistral38±3local~6.1GB2024-02
660Qwen3.5 0.8B Alibaba38±1local~2GB2026-03
661Code Tulu 2 7B Allen Institute for AI38±2local~16GB2023-11
662SOLAR 10.7B Instruct v1.0 Upstage37±1local~8.3GB2023-12
663Phi-3.5-vision-instruct Microsoft37±2local~10GB2024-08
more from Allen Institute for AI
493OLMo 2 13B Instruct (1124) Allen Institute for AI46±1local~9.6GB2024-12
516Tulu 2 70B Allen Institute for AI46±2local~28GB2023-11
557Code Tulu 2 34B Allen Institute for AI44±2local~72GB2023-11

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #380 of 458 * · 23% of its score · 1 test

Beats LFM2.5 8B-A1B, DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, WizardLM 13B V1.2, Falcon3 3B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Tulu 2: CodexEval pass@10 lab68.9% ✎▃▃▃·▆▃▃█▃▂▂▅ beats 15/25very easy · avg 86%▇▇▇▇▇▇▇▇▇ 23%sharp · at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #351 of 398 * · 14% of its score · 1 test

Beats Yi 34B Chat, Llama 3 8B Instruct, Command R (03-2024) here, though they rank higher overall. Trails Qwen3 0.6B, Tulu 2 DPO 7B, Gemma 7B (base) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K lab33.0% ✎▆▂▅█▅▅▃▆···▂ beats 9/25easy · avg 73%▇▇▇▇▇▇ 14%sharp · at its level
other tests3 not in a task · 62% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard lab49.1% ✎▁·····▂█▂▅·▁ beats 11/25easy · avg 77%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 41%sharp · at its level
MMLU lab43.7% ✎▁▁▃▃▄█▄▁█··▁ beats 5/25easy · avg 74%▇▇▇▇▇▇ 15%at its level
Tulu 2: TyDiQA gold passage, 1-shot F1 lab52.6% ✎▂··▁▃▂▂▂█▅▁▂ beats 16/25medium · avg 61%▇▇ 5.0%blunt · at its level

$ where to run it

Other ways to run it

  1. Run it as published · needs ~13.48 GB · from huggingface.co/allenai
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='allenai/codetulu-2-7b', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/allenai ↗

$ how the score was worked out · Tulu 2 — base and instruction… 99%

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
Tulu 2 — base and instruction-tuned evaluations · lab-reported5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 37.6

$ 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