|
--- |
|
license: cc-by-nc-sa-4.0 |
|
datasets: |
|
- Xilabs/PIPPA-alpaca |
|
language: |
|
- en |
|
--- |
|
This is contains GGUF(v2) quantizations of the model [Xilabs/calypso-3b-alpha-v2](https://huggingface.co/Xilabs/calypso-3b-alpha-v2) |
|
|
|
Which is |
|
**Based on:** [openlm-research/open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2) |
|
|
|
Calypso 3B is a language model designed for one-on-one chat interactions with a character or persona. It has been finetuned on the PIPPA-Alpaca dataset and a private dataset of human-generated chats. The model is particularly suited for providing conversational responses in a variety of contexts, making it suitable for role-playing, or one-on-one chatting. |
|
|
|
## Intended Use |
|
|
|
Calypso 3B is intended to facilitate engaging and interactive one-on-one chat experiences. |
|
|
|
## Limitations and Ethical Considerations |
|
|
|
- **Safety Note:** Calypso 3B can produce content that may not be safe for all audiences. It may generate inappropriate, offensive, or sensitive content. User discretion is advised. |
|
|
|
- **Factual Accuracy:** The model's responses may not always be factually accurate. It should not be relied upon to provide accurate information, especially in critical or sensitive contexts. |
|
|
|
- **Bias and Fairness:** As with many language models, Calypso 3B might inadvertently exhibit biases present in the training data. Efforts have been made to mitigate this, but biases may still be present. |
|
|
