whatmodel.sh / Tulu 2 7B

Tulu 2 7B

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

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 ↗

35.8±1.7#594 of 719 LLMsfrom 6 benchmark results across 2 sources

$ how it compares

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

#modelscorewhereRAMreleased
686Mistral 7B Instruct v0.2 Mistral36±1local~6GB2023-12
687WizardLM 13B V1.2 Microsoft36±1local~9.8GB2023-07
688Tulu 2 7B Allen Institute for AI36±2local~5.8GB2023-11
689xDAN-L1-Chat-RL-v1 xDAN-AI36±1local~6.1GB2023-12
690Llama 3 8B (base) Meta36±1local~6.6GB2024-04
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▁▁▃▃▆██▇▆▄▃▁ #444 of 458 * · 23% of its score · 1 test

Beats Molmo 7B-D (0924), DeepSeek R1 Distill Qwen 1.5B here, though they rank higher overall. Trails Falcon3 1B Instruct, Granite 3.0 1B-A400M Instruct, StarCoderBase 3B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Tulu 2: CodexEval pass@10 lab36.9% ✎▃▃▃·▆▃▃█▃▂▂▅ beats 4/25very easy · avg 86%▇▇▇▇▇▇▇▇▇ 23%sharp · at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #348 of 398 * · 13% of its score · 1 test

Beats Command R Plus (04-2024), Phi-3-mini-4k-instruct (June 2024 update), Yi 34B Chat 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 lab34.0% ✎▆▂▅█▅▅▃▆···▂ beats 10/25easy · avg 73%▇▇▇▇▇ 13%sharp · at its level
other tests4 not in a task · 62% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard lab48.5% ✎▁·····▂█▂▅·▁ beats 8/25easy · avg 77%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 38%sharp · at its level
MMLU lab50.4% ✎▁▁▃▃▄█▄▁█··▁ beats 9/25easy · avg 74%▇▇▇▇▇▇ 14%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)63.0% ✎▃▁▁▁▁▁▁▁▃█▅▁ beats 100/276medium · avg 73%▇▇ 5.3%at its level · noisy
Tulu 2: TyDiQA gold passage, 1-shot F1 lab46.4% ✎▂··▁▃▂▂▃█▅▁▂ beats 10/25medium · avg 61%▇▇ 4.9%blunt · at its level

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run Tulu 2 7B · needs ~4.1 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/tulu-2-7B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/tulu-2-7B-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Tulu 2 7B · needs ~4.1 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/tulu-2-7B-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Tulu 2 7B · needs ~4.1 GB · from huggingface.co/TheBloke
    chat in the terminal
    ollama run hf.co/TheBloke/tulu-2-7B-GGUF:Q4_K_M

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/tulu-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… 93%, Open Portuguese LLM Leaderboa… 5%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%CC BY 4.0
Open Portuguese LLM Leaderboard (archived)1▇▇ 5%Apache-2.0
prior · pull toward the middle▇ 1%
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