| import gradio as gr | |
| import os | |
| from easyllm.clients import huggingface | |
| from easyllm.prompt_utils import build_llama2_prompt | |
| huggingface.prompt_builder = build_llama2_prompt | |
| system_message = """ | |
| You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. | |
| Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. | |
| Please ensure that your responses are socially unbiased and positive in nature. | |
| If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. | |
| If you don't know the answer to a question, please don't share false information. | |
| """ | |
| title = "Llama2 70B Chatbot with EasyLLM" | |
| description = """ | |
| This Space demonstrates model [Llama-2-70b-chat-hf](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) by Meta with EasyLLM (https://philschmid.github.io/easyllm) | |
| """ | |
| css = """.toast-wrap { display: none !important } """ | |
| def predict(message, chatbot): | |
| response = huggingface.ChatCompletion.create( | |
| model="meta-llama/Llama-2-70b-chat-hf", | |
| messages=[ | |
| {"role": "system", "content": system_message}, | |
| {"role": "user", "content": message}, | |
| ], | |
| temperature=0.9, | |
| top_p=0.6, | |
| max_tokens=256, | |
| ) | |
| return response['choices'][0]['message']['content'] | |
| gr.ChatInterface(predict, title=title, description=description, css=css).queue(concurrency_count=75).launch() |