from huggingface_hub import InferenceClient import gradio as gr client = InferenceClient( "mistralai/Mixtral-8x7B-Instruct-v0.1" ) def format_prompt(message, history): prompt = """Your name is Chatter ,you are a uk immigration chatbot, your role is to give clients uk immigration advise based on their inputs , the diagnosis given to them should be short and concise , you were created by Royalty, also you generally give further immigration advise after the dia they input theìr immigration questions, if you are asked a question that is outside the domain of the uk immigration field like writing code or poems, refuse by saying you are a uk immigration chatbot who only gives immigration advice and then stop immediately, now reply the following input""" for user_prompt, bot_response in history: prompt += f"[INST] {user_prompt} [/INST]" prompt += f" {bot_response} " prompt += f"[INST] {message} [/INST]" return prompt def generate( prompt, history, temperature=0.1, 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"{prompt}", history) 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 additional_inputs=[ gr.Slider( label="Temperature", value=0.1, minimum=0.0, maximum=1.0, step=0.1, interactive=True, info="Higher values produce more diverse outputs", ), gr.Slider( label="Max new tokens", value=256, minimum=0, maximum=1048, step=64, interactive=True, info="The maximum numbers of new tokens", ), gr.Slider( label="Top-p (nucleus sampling)", value=0.90, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens", ), gr.Slider( label="Repetition penalty", value=1.2, minimum=1.0, maximum=2.0, step=0.05, interactive=True, info="Penalize repeated tokens", ) ] examples=[["A cement truck fell on my parents , what do I do?", None, None, None, None, None, ], ["How can i prevent myself from dying from a concussion , if i ever find myself in one", None, None, None, None, None,], ["What nutrition advice do you have for a woman after pregnancy.", None, None, None, None, None,], ] gr.ChatInterface( fn=generate, chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"), additional_inputs=additional_inputs, title="UK Immigration Chatbot ⚖️ ", examples=examples, concurrency_limit=20, theme = gr.themes.Default(primary_hue= gr.themes.colors.red, secondary_hue=gr.themes.colors.pink) ).launch(show_api=False)