IBM Granite
Team
company
AI & ML interests
LLMs for language and code + Time series and geospatial foundation models
Recent Activity
View all activity
-
23
Multimodal RAG with Granite Vision
🚀RAG example using Granite [vision, embedding, instruct]
-
ibm-granite/granite-vision-3.2-2b
Image-to-Text • 3B • Updated • 4.25k • 101 -
ibm-granite/granite-vision-3.1-2b-preview
Image-to-Text • 3B • Updated • 2.7k • 103 -
ibm-granite/granite-vision-3.3-2b
3B • Updated • 12.6k • 22
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/granite-3.0-8b-instruct
Text Generation • 8B • Updated • 30.4k • 202 -
ibm-granite/granite-3.0-8b-base
Text Generation • 8B • Updated • 2.49k • 24 -
ibm-granite/granite-3.0-2b-instruct
Text Generation • 3B • Updated • 4.81k • 46 -
ibm-granite/granite-3.0-2b-base
Text Generation • 3B • Updated • 2.83k • 22
A series of code models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models.
-
Granite Code Models: A Family of Open Foundation Models for Code Intelligence
Paper • 2405.04324 • Published • 24 -
Scaling Granite Code Models to 128K Context
Paper • 2407.13739 • Published • 20 -
ibm-granite/granite-3b-code-base-2k
Text Generation • 3B • Updated • 3.1k • 37 -
ibm-granite/granite-3b-code-base-128k
Text Generation • 3B • Updated • 144 • 6
A collection of time series models trained by IBM licensed under Apache 2.0 license.
-
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
Paper • 2401.03955 • Published • 11 -
ibm-granite/granite-timeseries-ttm-r1
Time Series Forecasting • 0.0B • Updated • 213k • 307 -
ibm-granite/granite-timeseries-patchtst
Time Series Forecasting • 0.0B • Updated • 10.2k • 15 -
ibm-granite/granite-timeseries-patchtsmixer
Time Series Forecasting • 0.0B • Updated • 679 • 19
A series of geospatial models trained by IBM licensed under Apache 2.0 license.
This collection has a set of artifacts which are related to curating and evaluating datasets used for Granite models
Our latest language models licensed under Apache 2.0 license.
-
ibm-granite/granite-3.3-2b-base
Text Generation • 3B • Updated • 16k • 16 -
ibm-granite/granite-3.3-2b-instruct
Text Generation • 3B • Updated • 119k • 62 -
ibm-granite/granite-3.3-8b-base
Text Generation • 8B • Updated • 494k • 16 -
ibm-granite/granite-3.3-8b-instruct
Text Generation • 8B • Updated • 76.5k • 121
A series of language models with 128K context length trained by IBM licensed under Apache 2.0 license.
-
18
Granite 3.1 8b Instruct
📝Chat with IBM Granite 3.1 8b Instruct
-
ibm-granite/granite-3.1-8b-instruct
Text Generation • 8B • Updated • 39.8k • 162 -
ibm-granite/granite-3.1-8b-base
Text Generation • 8B • Updated • 7.31k • 23 -
ibm-granite/granite-3.1-2b-instruct
Text Generation • 3B • Updated • 11.5k • 52
-
ibm-granite/granite-embedding-125m-english
Sentence Similarity • 0.1B • Updated • 41.5k • 16 -
ibm-granite/granite-embedding-30m-english
Sentence Similarity • 0.0B • Updated • 198k • 13 -
ibm-granite/granite-embedding-107m-multilingual
Sentence Similarity • 0.1B • Updated • 15.9k • 29 -
ibm-granite/granite-embedding-278m-multilingual
Sentence Similarity • 0.3B • Updated • 44k • • 54
A collection of models created by IBM for safeguarding language models.
-
ibm-granite/granite-guardian-3.3-8b
Text Generation • 8B • Updated • 4k • 12 -
ibm-granite/granite-guardian-3.2-3b-a800m
Text Generation • 3B • Updated • 1.94k • 5 -
ibm-granite/granite-guardian-3.2-5b
Text Generation • 6B • Updated • 2.26k • 11 -
ibm-granite/granite-guardian-3.1-8b
Text Generation • 8B • Updated • 1.84k • 14
Experimental projects under consideration for the Granite family.
-
ibm-granite/granite-embedding-30m-sparse
Feature Extraction • 0.0B • Updated • 7.64k • 14 -
ibm-granite/granite-3.2-8b-instruct-preview
Text Generation • 8B • Updated • 1.2k • 69 -
ibm-granite/granite-uncertainty-3.0-8b-lora
Text Generation • Updated • 3 -
ibm-granite/granite-rag-3.0-8b-lora
Text Generation • Updated • 4
A collection of accelerators for the Granite LLM/Code family of models
GGUF-formatted versions of IBM Granite models. Licensed under the Apache 2.0 license.
-
ibm-granite/granite-3.3-2b-instruct-GGUF
Text Generation • 3B • Updated • 1.66k • 11 -
ibm-granite/granite-3.3-8b-instruct-GGUF
Text Generation • 8B • Updated • 4.89k • 25 -
ibm-research/granite-3.2-2b-instruct-GGUF
Text Generation • 3B • Updated • 463 • 9 -
ibm-research/granite-3.2-8b-instruct-GGUF
Text Generation • 8B • Updated • 727 • 7
Our latest language models licensed under Apache 2.0 license.
-
ibm-granite/granite-3.3-2b-base
Text Generation • 3B • Updated • 16k • 16 -
ibm-granite/granite-3.3-2b-instruct
Text Generation • 3B • Updated • 119k • 62 -
ibm-granite/granite-3.3-8b-base
Text Generation • 8B • Updated • 494k • 16 -
ibm-granite/granite-3.3-8b-instruct
Text Generation • 8B • Updated • 76.5k • 121
-
23
Multimodal RAG with Granite Vision
🚀RAG example using Granite [vision, embedding, instruct]
-
ibm-granite/granite-vision-3.2-2b
Image-to-Text • 3B • Updated • 4.25k • 101 -
ibm-granite/granite-vision-3.1-2b-preview
Image-to-Text • 3B • Updated • 2.7k • 103 -
ibm-granite/granite-vision-3.3-2b
3B • Updated • 12.6k • 22
A series of language models with 128K context length trained by IBM licensed under Apache 2.0 license.
-
18
Granite 3.1 8b Instruct
📝Chat with IBM Granite 3.1 8b Instruct
-
ibm-granite/granite-3.1-8b-instruct
Text Generation • 8B • Updated • 39.8k • 162 -
ibm-granite/granite-3.1-8b-base
Text Generation • 8B • Updated • 7.31k • 23 -
ibm-granite/granite-3.1-2b-instruct
Text Generation • 3B • Updated • 11.5k • 52
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/granite-3.0-8b-instruct
Text Generation • 8B • Updated • 30.4k • 202 -
ibm-granite/granite-3.0-8b-base
Text Generation • 8B • Updated • 2.49k • 24 -
ibm-granite/granite-3.0-2b-instruct
Text Generation • 3B • Updated • 4.81k • 46 -
ibm-granite/granite-3.0-2b-base
Text Generation • 3B • Updated • 2.83k • 22
-
ibm-granite/granite-embedding-125m-english
Sentence Similarity • 0.1B • Updated • 41.5k • 16 -
ibm-granite/granite-embedding-30m-english
Sentence Similarity • 0.0B • Updated • 198k • 13 -
ibm-granite/granite-embedding-107m-multilingual
Sentence Similarity • 0.1B • Updated • 15.9k • 29 -
ibm-granite/granite-embedding-278m-multilingual
Sentence Similarity • 0.3B • Updated • 44k • • 54
A series of code models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models.
-
Granite Code Models: A Family of Open Foundation Models for Code Intelligence
Paper • 2405.04324 • Published • 24 -
Scaling Granite Code Models to 128K Context
Paper • 2407.13739 • Published • 20 -
ibm-granite/granite-3b-code-base-2k
Text Generation • 3B • Updated • 3.1k • 37 -
ibm-granite/granite-3b-code-base-128k
Text Generation • 3B • Updated • 144 • 6
A collection of models created by IBM for safeguarding language models.
-
ibm-granite/granite-guardian-3.3-8b
Text Generation • 8B • Updated • 4k • 12 -
ibm-granite/granite-guardian-3.2-3b-a800m
Text Generation • 3B • Updated • 1.94k • 5 -
ibm-granite/granite-guardian-3.2-5b
Text Generation • 6B • Updated • 2.26k • 11 -
ibm-granite/granite-guardian-3.1-8b
Text Generation • 8B • Updated • 1.84k • 14
A collection of time series models trained by IBM licensed under Apache 2.0 license.
-
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
Paper • 2401.03955 • Published • 11 -
ibm-granite/granite-timeseries-ttm-r1
Time Series Forecasting • 0.0B • Updated • 213k • 307 -
ibm-granite/granite-timeseries-patchtst
Time Series Forecasting • 0.0B • Updated • 10.2k • 15 -
ibm-granite/granite-timeseries-patchtsmixer
Time Series Forecasting • 0.0B • Updated • 679 • 19
Experimental projects under consideration for the Granite family.
-
ibm-granite/granite-embedding-30m-sparse
Feature Extraction • 0.0B • Updated • 7.64k • 14 -
ibm-granite/granite-3.2-8b-instruct-preview
Text Generation • 8B • Updated • 1.2k • 69 -
ibm-granite/granite-uncertainty-3.0-8b-lora
Text Generation • Updated • 3 -
ibm-granite/granite-rag-3.0-8b-lora
Text Generation • Updated • 4
A series of geospatial models trained by IBM licensed under Apache 2.0 license.
A collection of accelerators for the Granite LLM/Code family of models
This collection has a set of artifacts which are related to curating and evaluating datasets used for Granite models
GGUF-formatted versions of IBM Granite models. Licensed under the Apache 2.0 license.
-
ibm-granite/granite-3.3-2b-instruct-GGUF
Text Generation • 3B • Updated • 1.66k • 11 -
ibm-granite/granite-3.3-8b-instruct-GGUF
Text Generation • 8B • Updated • 4.89k • 25 -
ibm-research/granite-3.2-2b-instruct-GGUF
Text Generation • 3B • Updated • 463 • 9 -
ibm-research/granite-3.2-8b-instruct-GGUF
Text Generation • 8B • Updated • 727 • 7