app.py

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import gradio as gr

torch.random.manual_seed(0)

model = AutoModelForCausalLM.from_pretrained(
    "microsoft/Phi-3-mini-128k-instruct", 
    device_map="auto", 
    torch_dtype="auto", 
    trust_remote_code=True,
    low_cpu_mem_usage=True,
)
tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")

messages = [
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)

generation_args = {
    "max_new_tokens": 256,
    "return_full_text": False,
    "temperature": 0.2,
    "do_sample": True,
}
def phi3_fun(message,chat_history):
  messages=[
    {"role": "user", "content": message},
]
  output = pipe(messages, **generation_args)
  respond = output[0]['generated_text']
  return respond

title = "Phi-3 "
examples = [
    'How are You?',
    "talk about your self",
]
gr.ChatInterface(
    fn=phi3_fun,
    title =title,
    examples = examples
).launch(debug=True)
# demo = gr.Interface(fn=phi3_fun, inputs="text", outputs="text",title =title,
#     examples = examples)
# demo.launch()

# output = pipe(messages, **generation_args)
# print(output[0]['generated_text'])