Create app.py

app.py

@@ -0,0 +1,20 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "olacode55/zimble-llama2"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def generate(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.7, do_sample=True)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+demo = gr.Interface(fn=generate, inputs="text", outputs="text", title="Zimble LLaMA 2 Text Generator")
+demo.launch()