Create README.md

README.md

@@ -0,0 +1,47 @@
+---
+datasets:
+- erfanzar/UltraChat-Mixin
+language:
+- en
+- fr
+- es
+metrics:
+- accuracy
+pipeline_tag: text-generation
+tags:
+- code
+---
+
+# LinguaMatic
+
+LinguaMatic is an advanced AI model designed to handle a wide range of Natural Language Processing (NLP) tasks. With its powerful capabilities, LinguaMatic can assist with tasks such as text classification, sentiment analysis, language translation, question answering, and much more.
+   
+## EasyDel
+
+The model is finetuned Using a custom version of UltraChat on TPU-v4 POD using [EasyDel](https://github.com/erfanzar/EasyDeL)
+
+## Prompting Method
+
+LinguaMatic utilizes the OC prompting method to generate responses. This method, named after the friendly and intelligent llama, enhances the model's ability to engage in meaningful conversations. The `prompt_model` function provided below demonstrates how the llama2 prompting method is implemented:
+
+```python
+def os_chat_template(
+        message: str,
+        chat_history: Optional[List[str] | List[List[str]]] = None,
+        system_prompt: Optional[str] = None
+):
+    if chat_history is None:
+        chat_history = []
+    system = f"<|system|>\n{system_prompt}</s>" if system_prompt is not None else ""
+    ua = ""
+    for user_input, response in chat_history:
+        ua += f"<|user|>\n{user_input}</s>\n" + f"<|assistant|>\n{response}</s>\n"
+    return system + ua + f"<|user|>\n{message}</s>\n<|assistant|>\n"
+```
+
+The `prompt_model` function takes a `message` as input, along with the `chat_history` and `system_prompt`. It generates a formatted text that includes the system prompt, user inputs, and the current message. This approach allows LinguaMatic to maintain context and provide more coherent and context-aware responses.
+
+
+## Contributing
+
+We welcome contributions to enhance LinguaMatic's capabilities and improve its performance. If you encounter any issues or have suggestions for improvement, please feel free to submit a pull request or open an issue on [EasyDel](https://github.com/erfanzar/EasyDeL) GitHub repository.