Create app.py

app.py

@@ -0,0 +1,56 @@
+
+
+
+
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import torch
+import space
+
+def load_model(model_name):
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = AutoModelForCausalLM.from_pretrained(
+        model_name,
+        device_map=device,
+        torch_dtype="auto",
+        trust_remote_code=True,
+    )
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    generator = pipeline(
+        "text-generation",
+        model=model,
+        tokenizer=tokenizer,
+        return_full_text=False,
+        max_new_tokens=500,
+        do_sample=False
+    )
+    return generator
+
+@spaces.GPU
+def generate_text(prompt, model_name):
+    generator = load_model(model_name)
+    messages = [{"role": "user", "content": prompt}]
+    output = generator(messages)
+    return output[0]["generated_text"]
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
+        gr.Dropdown(
+            choices=["Qwen/Qwen2.5-1.5B-Instruct","microsoft/Phi-3-mini-4k-instruct", "ALLaM-AI/ALLaM-7B-Instruct-preview"],
+            label="Choose Model",
+            value="ALLaM-AI/ALLaM-7B-Instruct-preview"
+        )
+    ],
+    outputs=gr.Textbox(label="Generated Text"),
+    title="Text Generator",
+    description="Enter a prompt and generate text using one of the available models.",
+    examples=[
+        ["Tell me a funny joke about chickens.", "microsoft/Phi-3-mini-4k-instruct"],
+        ["أخبرني نكتة مضحكة عن الدجاج.", "ALLaM-AI/ALLaM-7B-Instruct-preview"]
+    ]
+)
+
+demo.launch()