whatmodel.sh / tulu-2-dpo-70b-ExPO

tulu-2-dpo-70b-ExPO

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

tulu-2-dpo-70b-ExPO is an open-weights language model from Chujie Zheng (ExPO), released April 2024. Its published size is 68.98B parameters. Licence: other (ai2-impact-license-low-risk).

Catalogue identity notes

Maker repo chujiezheng/tulu-2-dpo-70b-ExPO @5b31067: licence tag other (ai2-impact-license-low-risk). 68,976,648,192 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-04: month the maker's Hugging Face repo was created (createdAt 2024-04-26).

44.6±1.8#595 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of tulu-2-dpo-70b-ExPO, out of 1132 with a score, then more from Chujie Zheng (ExPO).

#modelscorewhereRAMreleased
748Llama 3.1 8B Instruct Meta45±0api $0.22/M +local~6.2GB2024-07
749Command R Plus (04-2024) Cohere45±1local~43GB2024-04
750tulu-2-dpo-70b-ExPO Chujie Zheng (ExPO)45±2local~28GB2024-04
751Jais Adapted 70B Chat Inception (G42)45±4local~293GB2024-08
752Mistral NeMo Instruct (2407) Mistral44±1local~8.7GB2024-07
more from Chujie Zheng (ExPO)
548Llama-3-Instruct-8B-SimPO-ExPO Chujie Zheng (ExPO)51±1local~6.6GB2024-05
660Mistral7B-PairRM-SPPO-ExPO Chujie Zheng (ExPO)47±2local~6.1GB2024-05
730internlm2-chat-20b-ExPO Chujie Zheng (ExPO)45±2local~14GB2024-05

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #335 of 466 * · 99% of its score · 1 test

Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, OpenThinker3 7B here, though they rank higher overall. Trails Flan-T5 XXL, LFM2 700M, EXAONE 3.5 2.4B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled25.7% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 69/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%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-dpo-70b-ExPO · needs ~41.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/tulu-2-dpo-70b-ExPO-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/tulu-2-dpo-70b-ExPO-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-dpo-70b-ExPO · needs ~41.4 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-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-dpo-70b-ExPO · needs ~41.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~137.95 GB · from huggingface.co/chujiezheng (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='chujiezheng/tulu-2-dpo-70b-ExPO', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/chujiezheng ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 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
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 44.6

$ 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