A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models.
IBM Granite
company
AI & ML interests
LLMs for language and code + Time series and geospatial foundation models
Organization Card
IBM ❤️ Open Source AI
IBM is building enterprise-focused foundation models to drive the future of business. The Granite family of foundation models span a variety of modalities, including language, code, and other modalities, such as time series.
We strongly believe in the power of collaboration and community-driven development to propel AI forward. As such, we will be hosting our latest open innovations on this IBM-Granite HuggingFace organization page. We hope that the AI community will find our efforts useful and that our models help fuel their research.
If you have any questions, please visit our discussions page.
Collections
6
A collection of models created by IBM for safeguarding language models.
-
ibm-granite/granite-guardian-3.0-8b
Text Generation • Updated • 372 • 24 -
ibm-granite/granite-guardian-3.0-2b
Text Generation • Updated • 1.04k • 14 -
ibm-granite/granite-guardian-hap-125m
Text Classification • Updated • 211 • 17 -
ibm-granite/granite-guardian-hap-38m
Text Classification • Updated • 18.3k • 28
models
49
ibm-granite/granite-guardian-3.0-8b
Text Generation
•
Updated
•
372
•
24
ibm-granite/granite-guardian-3.0-2b
Text Generation
•
Updated
•
1.04k
•
14
ibm-granite/granite-timeseries-ttm-r2
Time Series Forecasting
•
Updated
•
18.5k
•
10
ibm-granite/granite-3.0-2b-instruct
Text Generation
•
Updated
•
8.27k
•
28
ibm-granite/granite-3.0-8b-instruct
Text Generation
•
Updated
•
14.9k
•
132
ibm-granite/granite-3.0-1b-a400m-instruct
Text Generation
•
Updated
•
2.17k
•
16
ibm-granite/granite-3.0-3b-a800m-instruct
Text Generation
•
Updated
•
2.64k
•
14
ibm-granite/granite-3.0-1b-a400m-base
Text Generation
•
Updated
•
1.79k
•
5
ibm-granite/granite-3.0-3b-a800m-base
Text Generation
•
Updated
•
1.58k
•
4
ibm-granite/granite-3.0-2b-base
Text Generation
•
Updated
•
2.95k
•
16
datasets
None public yet