app.py

# 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,
# ):
#     messages = [{"role": "system", "content": system_message}]

#     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()
#!pip install transfomers
import gradio as gr
from huggingface_hub import InferenceClient
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "aaditya/Llama3-OpenBioLLM-70B"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", load_in_8bit=True)

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
    outputs = model.generate(**inputs, max_new_tokens=200)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

interface = gr.Interface(fn=generate_text, inputs="text", outputs="text")
interface.launch()