main-database/CodeGen.yaml at preview · Language-Technology-Assessment/main-database · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
---
# 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 (Company)

# Training compute:
# - Base model training compute: >= 1.18e+22 FLOP (lower bound from 2x Chinchilla)
# - End model training compute: unknown (likely negligible)

system:
    name: CodeGen
    link: https://huggingface.co/Salesforce/codegen25-7b-instruct_P
    type: code
    performanceclass: full
    basemodelname: CodeGen25-7B-Multi-P
    endmodelname: CodeGen25-7B-Instruct-P
    endmodellicense: Unknown (research purposes only)
    releasedate: 2023-06
    notes: Autoregressive language model for code synthesis. Base model licensed under Apache 2.0.

org:
    name: Salesforce
    link: https://www.salesforceairesearch.com/
    notes: Major AI research company.

# availability:
datasources_basemodel:
    class: partial
    link: https://huggingface.co/datasets/bigcode/starcoderdata
    notes: Starcoderdata mentioned in modelcard and some more mentioned in paper

datasources_endmodel:
    class: closed
    link:
    notes: no information found

weights_basemodel:
    class: open
    link: https://huggingface.co/Salesforce/codegen25-7b-instruct_P/tree/main
    notes:

weights_endmodel:
    class: open
    link: https://huggingface.co/Salesforce/codegen25-7b-instruct_P/tree/main
    notes:

trainingcode:
    class: closed
    link:
    notes:

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

hardware_architecture:
    class: closed
    link:
    notes:

preprint:
    class: open
    link: https://arxiv.org/pdf/2305.02309
    notes: Preprint published on arXiv.

paper:
    class: closed
    link:
    notes: Preprint reported to be published as a conference paper at ICLR 2023 but not found

modelcard:
    class: closed
    link:
    notes:

datasheet:
    class: closed
    link:
    notes:

# access:
licenses:
    class: closed
    link: ["https://huggingface.co/Salesforce/codegen25-7b-instruct_P/tree/main", "https://huggingface.co/datasets/bigcode/starcoderdata"]
    notes: "Weights: Research purposes only. Code: Not released. Data: Apache-2.0 for partial data."