license: cc-by-nc-4.0
What's Baize?
Baize is an open-source chat model fine-tuned with LoRA. It uses 100k dialogs generated by letting ChatGPT chat with itself. We also use Alpaca's data to improve its performance. This repo contains 13B model.
Why it's called Baize?
Baize (白泽) is a mythical creature in Chinese folklore, who speaks human languages and knows everything. This is exactly what we expect from a chat model.
Training Parameters
- Base Model: LLaMA-13B
- Training Epoch: 1
- Batch Size: 64
- Maximum Input Length: 512
- Learning Rate: 1e-4
- LoRA Rank: 8
- Updated Modules: All Linears
Training Dataset
- Standford Alpaca (51,942)
- Quora Dialogs (54,456):
- StackOverflow Dialogs (57,046)
More details can be found in the Baize GitHub
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.