The base model is bigscience/bloom-560m. It was finetuned using RLHF and the dataset and the model prompt is similar to the original model. This repo contains the merged fp16 model.

Legal Disclaimer: This model is bound by the usage restrictions of the original BLOOM model. And comes with no warranty or gurantees of any kind.

• license:
  • bigscience-bloom-rail-1.0 <br>
• datasets:
  • Anthropic/hh-rlhf <br>
• language:
  • en <br>
• reference: https://github.com/hiyouga/LLaMA-Efficient-Tuning/tree/main