European Open Source AI Index
Menu
Database
News
Guides
About
Contribute
RedPajama
by Together Computer
About the model:
Open AI model developed as a collaboration between various open-source entities.
Model type:
Text
Model performance class:
Limited
Link to the model:
https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Chat
Base models:
RedPajama-INCITE-7B-Base
End model:
RedPajama-INCITE-7B-Chat
End model license:
Apache-2.0
About the organisation:
Together Computer, a cloud platform for generative AI.
Link to the organisation:
https://together.ai/
Model release date:
March 2023
Availability
Base Model Data
RedPajama-Data-1T made available on HuggingFace
https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T
End User Model Data
The model was trained on a large collection of diverse data, including Chain-of-Thought (CoT), Public Pool of Prompts (P3) dataset, Natural-Instructions (NI) dataset. Chat-tuning using Databricks-Dolly and OASST1.
https://huggingface.co/datasets/togethercomputer/RedPajama-Data-Instruct
https://huggingface.co/datasets/databricks/databricks-dolly-15k
https://huggingface.co/datasets/OpenAssistant/oasst1
Base Model Weights
Base is RedPajama-INCITE-7B-Base
https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base
End User Model Weights
Instruction-tuned version made available in parallel with base version.
https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Chat
Training Code
Code for datasets made available in exemplary ways; code for training and tuning harder to find.
https://github.com/togethercomputer/redpajama.cpp/tree/master/examples/redpajama
Documentation
Code Documentation
Code for base LLM and instruction tuning datasets beautifully documented; code specifying training and fine-tuning sparsely documented.
https://github.com/togethercomputer/redpajama.cpp/tree/master/examples/redpajama
Hardware Architecture
Architecture detailed on model card, crucial parts appear to be forked from GPT-NeoX
https://together.ai/blog/redpajama
Preprint
No preprint found.
Paper
No peer-reviewed paper found.
Modelcard
Model card and readme provide details on datasets and training procedure.
https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Chat
Datasheet
Base data sheet includes links to data and recipes to create from scratch. Other datasets are well-documented.
https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T
https://huggingface.co/datasets/togethercomputer/RedPajama-Data-Instruct
https://huggingface.co/datasets/databricks/databricks-dolly-15k
https://huggingface.co/datasets/OpenAssistant/oasst1
Access
Package
No separate package found.
API and Meta Prompts
Hosted inference API available through HuggingFace.
https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Instruct
Licenses
Models licensed under Apache 2.0, but note that the data itself is variably licensed and so imposes some limitations.
https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Instruct/blob/main/README.md
Is this information not up to date?
Contribute here ->
Supported by the Centre for Language Studies and the Dutch Research Council. Website design & development © 2024 by
BSTN
. This version of the index generated
10 March 2026
, website content last updated
11 March 2026
.