Create app.py

app.py

@@ -0,0 +1,22 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import torch
+import gradio as gr
+
+
+
+model = AutoModelForCausalLM.from_pretrained("AmiyendraOP/llama3-legal-finetuned", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("AmiyendraOP/llama3-legal-finetuned")
+
+
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
+
+
+
+def chat(prompt):
+    response = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7)[0]["generated_text"]
+    return response
+
+
+
+gr.Interface(fn=chat, inputs="text", outputs="text", title="LLaMA 3 Legal Chatbot").launch()