|
--- |
|
license: mit |
|
base_model: meta-llama/Meta-Llama-3.1-8B |
|
--- |
|
# NarrativAIV2 |
|
|
|
This model is a fine-tuned version of the LLaMA 3.1 language model, specifically trained on a curated dataset of interactive roleplaying scenarios. |
|
|
|
**Model Description** |
|
|
|
* **Base Model:** LLaMA 3.1 |
|
* **Training Data:** A diverse dataset of 977 fictional scenarios featuring engaging characters in various settings, emphasizing emotional depth and complex interactions. |
|
* **Fine-tuning Method:** This model was fine-tuned using supervised learning, focusing on continuing the given roleplay prompt in a consistent, immersive manner. |
|
|
|
**Limitations** |
|
|
|
* **Bias:** The model's responses may reflect biases present in the training data. |
|
* **Factual Accuracy:** The model is not designed to provide factual information and may generate inaccurate statements. |
|
* **Repetitive Responses:** Occasionally, the model may produce repetitive or predictable responses. |
|
|
|
**License** |
|
|
|
This model is released under the MIT license. |
