UltraLM-13b / README.md
stingning's picture
Update README.md
2c732c2
metadata
datasets:
  - stingning/ultrachat

UltraLM-13b

This is UltraLM-13b delta weights, a chat language model trained upon UltraChat

Model Details

Model Description

The model is fine-tuned based on LLaMA-13b with a multi-turn chat-format template as below

User: instruction 1<eos_token>
Assistant: response 1<eos_token>
User: instruction 2<eos_token>
Assistant: response 2<eos_token>
...
  • License: UltraLM is based on LLaMA and should be used under LLaMA's model license.
  • Finetuned from model: LLaMA-13b
  • Finetuned on data: UltraChat

Model Sources

Uses

To use this model, you need to recover the full model from the delta weights and perform inference following the template below:

[Optional]User: system prompt<eos_token>
User: user input<eos_token>
Assistant: