license: mit
language:
- ko
pipeline_tag: text-generation
tags:
- KoRWKV
🚧 Note: this repo is under construction, current uploaded version is ~20% trained ckpt (with ~31Billion tokens) 🚧
Todo
- ⏳ Train 1.5B
- Todo: Train Bigger Models
KoRWKV Model Card
KoRWKV (1.5B) trained on Korean dataset with RWKVv4 Neo Architecture.
Model details
Researcher developing the model
Junbum Lee (aka Beomi)
Model date
KoRWKV was trained between 2022.05~
Model version
This is alpha version of the model.
Model type
Find more about RWKV at https://github.com/BlinkDL/RWKV-LM
License
MIT
Intended use
Primary intended uses
The primary use of KoRWKV is research on Korean Opensource large language models
Primary intended users
The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence.
Out-of-scope use cases
KoRWKV is a base, or foundational, model. As such, it should not be used on downstream applications without further risk evaluation and mitigation. In particular, our model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers.
Ethical considerations
Data
The data used to train the model is collected from various sources, mostly from the Web. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data.
Human life
The model is not intended to inform decisions about matters central to human life, and should not be used in such a way.
Risks and harms
Risks and harms of large language models include the generation of harmful, offensive or biased content. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard.
Use cases
KoRWKV is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.