CodeGemma.yaml

---
# Thank you for contributing!
# In filling out this yaml file, please follow the criteria as described here:
# https://osai-index.eu/contribute

# You're free to build on this work and reuse the data. It is licensed under CC-BY 4.0, with the
# stipulation that attribution should come in the form of a link to https://osai-index.eu/
# and a citation to the peer-reviewed paper in which the dataset & criteria were published:

# Liesenfeld, A. and Dingemanse, M., 2024. Rethinking open source generative AI: open-washing and the EU AI Act. In Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency (pp. 1774-1787).

# Organization tags:
# - National origin: United States
# - Contributor type: Non-academic (American Big Tech)

# Training compute:
# - Base model training compute: ~3.07e+23 FLOP +- 0.5 OoM (param count & dataset size) [Epoch AI]
# - End model training compute: unknown (likely negligible)

system:
    name: CodeGemma
    link: https://huggingface.co/google/codegemma-1.1-7b-it
    type: code
    performanceclass: full
    basemodelname: Gemma-7B
    endmodelname: CodeGemma-1.1-7B-IT
    endmodellicense: Gemma Terms of Use
    releasedate: 2024-07
    notes: Gemma-based coder model.

org:
    name: Google AI
    link: https://ai.google
    notes: Major technology company, operator of Google Search.

# availability:
datasources_basemodel:
    class: closed
    link: 
    notes: "All CodeGemma v1.0 models are further trained on 500 billion tokens of primarily English language data from web documents, mathematics, and code."

datasources_endmodel:
    class: closed
    link: 
    notes: "All CodeGemma v1.0 models are further trained on 500 billion tokens of primarily English language data from web documents, mathematics, and code."

weights_basemodel:
    class: partial
    link: 
    notes: Behind constent form

weights_endmodel:
    class: partial
    link: https://huggingface.co/google/codegemma-1.1-7b-it/tree/main
    notes: Behind constent form

trainingcode:
    class: closed
    link: 
    notes: 

# documentation:
code:
    class: closed
    link:  
    notes: 

hardware_architecture:
    class: closed
    link:  
    notes: 

preprint:
    class: open
    link: https://arxiv.org/abs/2406.11409
    notes: 

paper:
    class: closed
    link: 
    notes: 

modelcard:
    class: open
    link: https://huggingface.co/google/codegemma-1.1-7b-it
    notes: 

datasheet:
    class: closed
    link: 
    notes: 

# access:
licenses:
    class: closed
    link: "https://huggingface.co/google/codegemma-1.1-7b-it/tree/main"
    notes: "Weights: Gemma Terms of Use. Code: not released. Data: not disclosed."