Update README.md

README.md

@@ -1,3 +1,35 @@
----
-license: mit
----
+---
+license: mit
+language:
+- en
+base_model:
+- meta-llama/Meta-Llama-3.1-8B
+---
+<img src="https://i.ibb.co/WWXXQ89/662e2c140acef96920e91b66-trace-1-1.png" alt="Mhm." width="300"/>
+
+# NarrativAI Reflection 
+
+**Model Name:** NarrativAI Reflection
+
+**Base Model:** Llama 3.1 8B
+
+
+**Model Description:** NarrativAI Reflection is a fine-tuned language model based on Llama 3.1 8B designed to generate internal monologue (pre-response thought, post-response reflection) and dialogue for roleplay actions.
+
+**Training Objective:** The model was fine-tuned on a dataset containing prompts describing fictional scenarios with characters and their emotional states, along with corresponding responses that include pre-response thoughts, dialogue/action, and post-response reflections. The objective is to enable the model to generate believable internal monologue and dialogue that reflects the character's personality, emotions, and the context of the scenario.
+
+**Intended Use:** NarrativAI Reflection is intended for creative writing and role-playing applications. 
+
+**Limitations:**
+
+* **Limited context:** The model's understanding of the scenario is based solely on the provided prompt. It may struggle with complex scenarios or require additional context to generate accurate responses.
+* **Bias and Stereotypes:** The training data may contain biases and stereotypes, which could be reflected in the model's generated text. 
+* **Lack of real-world knowledge:** The model's knowledge is limited to the information present in the training data. It may not be able to accurately reflect real-world situations or events.
+
+**Disclaimer:** 
+
+NarrativAI Reflection is a research project and should not be used in any application where its limitations could cause harm or misrepresent real-world situations. Users are solely responsible for the ethical and responsible use of the model.
+
+**Community Support:** [NarrativAI Discord](https://discord.gg/QDS4Nng6j6)
+
+<img src="https://media1.tenor.com/m/TE8p01zc7zgAAAAC/rich-amiri-rich-amiri-one-call.gif" alt="Mhm." width="800"/>