Ultra Series
Collection
UltraLM, UltraRM and UltraCM.
•
8 items
•
Updated
•
5
This is UltraLM-13b delta weights, a chat language model trained upon UltraChat
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>
...
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: