European Open Source AI Index
Menu
Database
News
Guides
About
Contribute
Yi
by 01.AI
About the model:
The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. Targeted as a bilingual language model and trained on 3T multilingual corpus.
Model type:
Text
Model performance class:
Full
Link to the model:
https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K
Base models:
Yi-34B
End model:
Yi-1.5-34B-Chat-16K
End model license:
Apache-2.0
About the organisation:
Chinese AI start-up.
Link to the organisation:
https://www.01.ai/
Model release date:
May 2024
Availability
Base Model Data
Training data for base model undocumented, though preprint mentions CommonCrawl as one source
End User Model Data
No end model data sources found.
Base Model Weights
Base model weights shared via HuggingFace
https://huggingface.co/01-ai/Yi-34B
End User Model Weights
Instruction-tuned weights shared via HuggingFace.
https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K
Training Code
repository contains some code for demos and for instruction tuning, but only sparse examples of code for initial training and model architecture
https://github.com/01-ai/Yi
Documentation
Code Documentation
Inference and fine-tuning code is documented, training code is not documented.
https://github.com/01-ai/Yi/
Hardware Architecture
Model architecture described in paper.
https://arxiv.org/pdf/2403.04652
Preprint
Preprint provides some info on pretraining data (CommonCrawl) but none on instruction tuning dataset.
https://arxiv.org/abs/2403.04652
Paper
No peer-reviewed paper found
Modelcard
Model card provides limited relevant information.
https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K
Datasheet
No data sheets found.
Access
Package
Model available on Ollama.
https://ollama.com/library/yi
API and Meta Prompts
Model is gated and commercially available.
https://platform.01.ai/docs
Licenses
Model licensed under Apache 2.0
https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K
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
.