| from huggingface_hub import InferenceClient | |
| import gradio as gr | |
| options =["mistralai/Mixtral-8x7B-Instruct-v0.1" | |
| ] | |
| def format_prompt(message, history): | |
| prompt = "<s>Your name is Nurse Nkiru , your role is to give patients diagnosis based on their inputs , the diagnosis given to them should be short and concise , also you generally give further health advise after the diagnosis" | |
| for user_prompt, bot_response in history: | |
| prompt += f"[INST] {user_prompt} [/INST]" | |
| prompt += f" {bot_response}</s> " | |
| prompt += f"[INST] {message} [/INST]" | |
| return prompt | |
| def generate( | |
| prompt, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0, | |
| ): | |
| temperature = float(temperature) | |
| if temperature < 1e-2: | |
| temperature = 1e-2 | |
| top_p = float(top_p) | |
| generate_kwargs = dict( | |
| temperature=temperature, | |
| max_new_tokens=max_new_tokens, | |
| top_p=top_p, | |
| repetition_penalty=repetition_penalty, | |
| do_sample=True, | |
| seed=42, | |
| ) | |
| formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history) | |
| model = gr.Dropdown(choices = options) | |
| client = InferenceClient(model) | |
| stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False) | |
| output = "" | |
| for response in stream: | |
| output += response.token.text | |
| yield output | |
| return output | |
| gr.ChatInterface( | |
| fn=generate, | |
| chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"), | |
| title="Choose your hero🦸", | |
| concurrency_limit=20, | |
| theme = gr.themes.Default(primary_hue= gr.themes.colors.blue, secondary_hue=gr.themes.colors.red) | |
| ).launch(show_api=False) |