whatmodel.sh / Starling-LM-7B-beta-ExPO

Starling-LM-7B-beta-ExPO

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

Starling-LM-7B-beta-ExPO is an open-weights language model from Chujie Zheng (ExPO), released April 2024. Its published size is 7.24B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo chujiezheng/Starling-LM-7B-beta-ExPO @598b4a4: licence tag apache-2.0. 7,241,748,480 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).

44.2±1.6#604 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 Starling-LM-7B-beta-ExPO, out of 1132 with a score, then more from Chujie Zheng (ExPO).

#modelscorewhereRAMreleased
758Yi 1.5 9B Chat 01.AI44±1local~6.8GB2024-05
759Command R7B (12-2024) Cohere44±1local~6.2GB2024-12
760Starling-LM-7B-beta-ExPO Chujie Zheng (ExPO)44±2local~6.1GB2024-04
761Jais Family 13B Chat Inception (G42)44±3local~58GB2024-08
762Qwen2-Audio 7B Instruct Alibaba44±3local~6.5GB2024-07
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▁▁▁▄▆▅▆█▆▆▆▂ #334 of 466 * · 74% 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-controlled26.4% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 71/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 74%at its level
other tests1 not in a task · 25% of its score
testresultvs the others in its rundifficultycountswhy
WildBench v2 WB-Score (task macro)31.5594 WB-Score ✎▁·▁▁·▃█▄▇▆▅▆ beats 19/52avg 45.199 WB-Score▇▇▇▇▇▇▇▇▇▇ 25%sharp

$ 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 Starling-LM-7B-beta-ExPO · needs ~4.4 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/Starling-LM-7B-beta-ExPO-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/Starling-LM-7B-beta-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 Starling-LM-7B-beta-ExPO · needs ~4.4 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/Starling-LM-7B-beta-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 Starling-LM-7B-beta-ExPO · needs ~4.4 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/Starling-LM-7B-beta-ExPO-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~14.48 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/Starling-LM-7B-beta-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… 74%, WildBench v2 leaderboard data… 25%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 74%Apache-2.0
WildBench v2 leaderboard data (Ai2)1▇▇▇▇▇▇▇ 25%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 44.2

$ 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