whatmodel.sh / Mistral-ORPO-beta

Mistral-ORPO-beta

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

Mistral-ORPO-beta is an open-weights language model from KAIST AI, released March 2024. Its published size is 7.24B parameters. Licence: mit.

Catalogue identity notes

Maker repo kaist-ai/mistral-orpo-beta @1050739: licence tag mit. 7,241,732,096 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-03: month the maker's Hugging Face repo was created (createdAt 2024-03-12).

38.4±2.2#746 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 Mistral-ORPO-beta, out of 1132 with a score.

#modelscorewhereRAMreleased
908Meditron 70B EPFL LLM38±4local~32GB2023-11
909Jais Family 2p7b (2.7B) Chat Inception (G42)38±4local~14GB2024-08
910Mistral-ORPO-beta KAIST AI38±2local~6.2GB2024-03
911Falcon-180B-Chat TII38±2local~115GB2023-09
912CodeGemma 7B (v1.0) Google38±1local~7.1GB2024-03

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #398 of 466 * · 98% of its score · 1 test

Beats Gemma 4 E2B, Code Llama 70B Instruct, QwQ-32B-Preview here, though they rank higher overall. Trails Granite 4.0 H 350M, LFM2 350M, Gemma 3 1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled14.7% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 38/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%typical

$ 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 Mistral-ORPO-beta · needs ~4.5 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/mistral-orpo-beta-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/mistral-orpo-beta-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 Mistral-ORPO-beta · needs ~4.5 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/mistral-orpo-beta-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 Mistral-ORPO-beta · needs ~4.5 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/mistral-orpo-beta-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~14.48 GB · from huggingface.co/kaist-ai (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='kaist-ai/mistral-orpo-beta', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/kaist-ai ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 98%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%Apache-2.0
prior · pull toward the middle▇ 2%
weighted average= 38.4

$ 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