whatmodel.sh / Mistral7B-PairRM-SPPO

Mistral7B-PairRM-SPPO

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

Mistral7B-PairRM-SPPO is an open-weights language model from UCLA AGI (SPPO), released May 2024. Its published size is 7.24B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo UCLA-AGI/Mistral7B-PairRM-SPPO @abdc173: licence tag apache-2.0. 7,241,732,096 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-05: month the maker's Hugging Face repo was created (createdAt 2024-05-04).

46.6±1.7#538 of 949 LLMsfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Mistral7B-PairRM-SPPO, out of 1132 with a score, then more from UCLA AGI (SPPO).

#modelscorewhereRAMreleased
679PLLuM-8x7B-nc-chat (2412) PLLuM consortium (CYFRAGOVPL)47±4local~31GB2025-02
680Yi-1.5 9B Chat 16K 01.AI47±4local~7.1GB2024-05
681Mistral7B-PairRM-SPPO UCLA AGI (SPPO)47±2local~6.1GB2024-05
682EuroLLM 9B Instruct UTTER (EuroLLM)47±3local~6.9GB2024-11
683Hormoz-8B Mann-E47±5local~6.9GB2025-02
more from UCLA AGI (SPPO)
402Gemma-2-9B-It-SPPO-Iter3 UCLA AGI (SPPO)56±2local~7GB2024-06
577Llama-3-Instruct-8B-SPPO-Iter3 UCLA AGI (SPPO)50±2local~6.6GB2024-06

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #315 of 466 * · 93% of its score · 1 test

Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, Ministral 3 8B 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-controlled30.5% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 79/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%at its level
other tests1 not in a task · 5.5% of its score
testresultvs the others in its rundifficultycountswhy
Open PT-LLM Leaderboard average (9 Portuguese tasks)65.0% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 114/276medium · avg 73%▇▇ 5.5%at its level · noisy

$ 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 Mistral7B-PairRM-SPPO · needs ~4.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/Mistral7B-PairRM-SPPO-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/Mistral7B-PairRM-SPPO-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 Mistral7B-PairRM-SPPO · needs ~4.4 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/Mistral7B-PairRM-SPPO-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 Mistral7B-PairRM-SPPO · needs ~4.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/Mistral7B-PairRM-SPPO-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~14.48 GB · from huggingface.co/UCLA-AGI (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='UCLA-AGI/Mistral7B-PairRM-SPPO', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/UCLA-AGI ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 93%, Open Portuguese LLM Leaderboa… 6%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇▇ 6%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 46.6

$ 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