app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "cognitivecomputations/dolphin-2.8-mistral-7b-v02"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

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

iface = gr.Interface(
    fn=generate_text,
    inputs="text",
    outputs="text",
    title="Dolphin Mistral Demo",
    description="Enter a prompt and get a generated response."
)

iface.launch()