whatmodel.sh / Ghost 7B Alpha

Ghost 7B Alpha

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

Ghost 7B Alpha is an open-weights language model from Ghost X, released April 2024. Its published size is 7.24B parameters. Licence: other (ghost-7b).

Catalogue identity notes

Maker repo ghost-x/ghost-7b-alpha @413f721: licence tag other (ghost-7b). 7,241,732,096 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-04: month the maker's Hugging Face repo was created (createdAt 2024-04-13).

31.8±1.8#628 of 719 LLMsfrom 5 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Ghost 7B Alpha, out of 828 with a score.

#modelscorewhereRAMreleased
723Mistral 7B Instruct v0.1 Mistral32±1local~6.1GB2023-09
724Qwen1.5 4B Chat Alibaba32±2local~4.1GB2024-02
725Ghost 7B Alpha Ghost X32±2local~6.1GB2024-04
726CodeGemma 2B (v1.0) Google32±1local~3.2GB2024-03
727Qwen-7B (base) Alibaba32±1local~6.6GB2023-08

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #378 of 393 * · 56% of its score · 2 tests

Beats Phi-2 (2.7B), Nous-Hermes-13b, Qwen1.5 4B Chat here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Granite 4.0 350M here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled6.9% ✎▁▂▃▃▆▆█▆▄▄▁▁ beats 13/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%too hard for it
AlpacaEval 1.0 win rate (vs text-davinci-003, GPT-4 judge)70.4% ✎▂▂·▆·▇▃▆█▆▄▂ beats 15/45very easy · avg 96%▇▇▇▇▇▇▇ 17%sharp · at its level · noisy
other tests3 not in a task · 42% of its score
testresultvs the others in its rundifficultycountswhy
MedQA (USMLE, 4 options)40.3% ✎▁▁··▄▁▁··▄▃█ beats 7/17easy · avg 76%▇▇▇▇▇▇▇▇▇▇ 25%sharp
MedMCQA38.1% ✎▂▂··▄▄▂▃·▄██ beats 7/17medium · avg 68%▇▇▇▇▇▇ 15%typical
PubMedQA69.2% ✎▂·▂▆·▄▂▄▄▂█▂ beats 9/17medium · avg 77%▇ 2.2%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 Ghost 7B Alpha · needs ~4.4 GB · from huggingface.co/ghost-x (official)
    chat in the terminal
    llama cli -hf ghost-x/ghost-7b-alpha-gguf:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf ghost-x/ghost-7b-alpha-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 Ghost 7B Alpha · needs ~4.4 GB · from huggingface.co/ghost-x (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/ghost-x/ghost-7b-alpha-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 Ghost 7B Alpha · needs ~4.4 GB · from huggingface.co/ghost-x (official)
    chat in the terminal
    ollama run hf.co/ghost-x/ghost-7b-alpha-gguf:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~14.48 GB · from huggingface.co/ghost-x (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='ghost-x/ghost-7b-alpha', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/ghost-x ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 56%, Open Medical-LLM Leaderboard… 42%

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)2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 56%Apache-2.0
Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)3▇▇▇▇▇▇▇▇▇▇▇▇▇ 42%Apache-2.0
prior · pull toward the middle▇ 2%
weighted average= 31.8

$ 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