Create app.py

app.py

@@ -0,0 +1,28 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+import gradio as gr
+
+base_model_id = "unsloth/llama-3-8b-bnb-4bit"
+adapter_model_id = "Amiyendra/llama3-legal-assistant"
+
+tokenizer = AutoTokenizer.from_pretrained(base_model_id)
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_id,
+    device_map="auto",
+    torch_dtype=torch.float16,
+)
+
+
+model = PeftModel.from_pretrained(base_model, adapter_model_id)
+model.eval()
+
+
+def generate(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_new_tokens=512)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+
+gr.Interface(fn=generate, inputs="text", outputs="text", title="LLaMA 3 Legal Assistant").launch()