Create app.py

app.py

@@ -0,0 +1,30 @@
+import gradio as gr
+from transformers import AutoTokenizer, pipeline
+import torch
+
+# Initialize the model and tokenizer
+model_name = "Wtzwho/Prometh-MOEM-V.01"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+text_generation_pipeline = pipeline(
+    "text-generation",
+    model=model_name,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+def generate_text(user_input):
+    messages = [{"role": "user", "content": user_input}]
+    prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    outputs = text_generation_pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+    return outputs[0]["generated_text"]
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=generate_text,
+    inputs=gr.inputs.Textbox(lines=2, placeholder="Type your question here..."),
+    outputs=gr.outputs.Textbox(),
+    title="Prometh-MOEM Text Generation",
+    description="A text generation model that understands your queries and generates concise, informative responses."
+)
+
+# Run the interface
+iface.launch()