Update app.py

app.py

@@ -2,21 +2,27 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
 import gradio as gr
 
+model_id = "AmiyendraOP/llama3-legal-finetuned"
 
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
 
-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)
-
+# Set device properly
+device = 0 if torch.cuda.is_available() else -1
 
+# Use pipeline for text generation
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device=device)
 
+# Define chat function
 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()
+# Launch Gradio app
+gr.Interface(
+    fn=chat,
+    inputs=gr.Textbox(lines=4, placeholder="Enter legal question...", label="Your Question"),
+    outputs=gr.Textbox(label="Response"),
+    title="LLaMA 3 Legal Chatbot (Fine-tuned)",
+).launch()