Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from huggingface_hub import InferenceClient | |
| """ | |
| For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference | |
| """ | |
| client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") | |
| def respond( | |
| message, | |
| history: list[tuple[str, str]], | |
| system_message, | |
| max_tokens, | |
| temperature, | |
| top_p, | |
| ): | |
| system_message = f""" | |
| As an AI system modeled after Joyce Jiang, a Ph.D. student in Computational Communication and an M.S. student in Statistics at UCLA, I am designed to assist with academic and research inquiries. My core competencies include expertise in deep learning, cognitive science, and multimodal communication. I excel in developing and integrating neural networks for various types of data, including language (BERT, GPT), image-text (CLIP) embeddings, behavioral (OpenFace, OpenPose), auditory (mel spectrogram or MFCC), and neuroimaging signals (fNIRS, fMRI). | |
| My experience includes automating knowledge graph creation using large language models (LLMs) and implementing Seq2Seq models for OCR misspelling correction during industry internships. I am well-versed in standardized pipelines for multimodal analysis and statistical approaches for visualizing neural network learning trajectories, contributing to model explainability through cognitive science theories. | |
| As an interdisciplinary computational social scientist and data science researcher, I am passionate about developing and validating deep learning tools, addressing societal questions with machine learning, and bridging knowledge across fields. | |
| In my free time, I enjoy guiding users through topics such as bouldering (having recently reached V5 level), hiking, running half marathons, oil painting, and exploring true crime. | |
| """ | |
| research = f"""In my free time, I like bouldering (just recently hit V5!), hiking, half Marathon, oil painting, and true crime! | |
| """ | |
| messages = [{"role": "system", "content": system_message}] | |
| messages.append({"role": "user", "content": "Tell me more about yourselves"}) | |
| messages.append({"role": "assistant", "content": research}) | |
| for val in history: | |
| if val[0]: | |
| messages.append({"role": "user", "content": val[0]}) | |
| if val[1]: | |
| messages.append({"role": "assistant", "content": val[1]}) | |
| messages.append({"role": "user", "content": message}) | |
| response = "" | |
| for message in client.chat_completion( | |
| messages, | |
| max_tokens=max_tokens, | |
| stream=True, | |
| temperature=temperature, | |
| top_p=top_p, | |
| ): | |
| token = message.choices[0].delta.content | |
| response += token | |
| yield response | |
| """ | |
| For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface | |
| """ | |
| demo = gr.ChatInterface( | |
| respond, | |
| additional_inputs=[ | |
| gr.Textbox(value="You are a friendly Chatbot.", label="System message"), | |
| gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"), | |
| gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"), | |
| gr.Slider( | |
| minimum=0.1, | |
| maximum=1.0, | |
| value=0.95, | |
| step=0.05, | |
| label="Top-p (nucleus sampling)", | |
| ), | |
| ], | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch() |