Model Type | text generation, conversational |
|
Use Cases |
Primary Use Cases: | fictional conversation for entertainment purposes |
|
Limitations: | Not fine-tuned to be safe and harmless., May produce socially unacceptable, undesirable, or offensive text., Outputs might be factually wrong or misleading. |
|
|
Additional Notes | The model weights in the repository are XOR encoded due to licensing concerns and cannot be used as-is. Requires specific processes to convert the LLaMA weights to be usable. |
|
Input Output |
Input Format: | [CHARACTER]'s Persona: [A few sentences about the character you want the model to play] [DIALOGUE HISTORY] You: [User's input message here] [CHARACTER]: |
|
Accepted Modalities: | |
Output Format: | Conversational text until it emits an end-of-text token (`~~`) |
|
|