Create app.py

app.py

@@ -0,0 +1,29 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load the model and tokenizer
+model_name = "huihui-ai/Llama-3.2-3B-Instruct-abliterated"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",
+    low_cpu_mem_usage=True
+)
+
+# Define the text generation function
+def generate_text(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    outputs = model.generate(inputs["input_ids"], max_length=100)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=generate_text,
+    inputs=gr.Textbox(lines=5, placeholder="Enter your prompt here..."),
+    outputs="text",
+    title="Llama 3.2 3B Instruct Abliterated",
+    description="An uncensored language model. Enter your prompt to receive a response."
+)
+
+if __name__ == "__main__":
+    iface.launch()