updated the code

app.py

@@ -1,26 +1,36 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
+import pandas as pd
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
 
-# Load Model & Tokenizer
+# Load Llama-2 Model & Tokenizer
 model_name = "meta-llama/Llama-2-7b-chat-hf"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(
     model_name, torch_dtype=torch.float16, device_map="auto"
 )
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
-# Function to generate responses
-def chat_with_llama(input_text):
-    inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
-    output = model.generate(**inputs, max_new_tokens=200)
-    return tokenizer.decode(output[0], skip_special_tokens=True)
+# Function to analyze CSV data
+def analyze_csv(file):
+    df = pd.read_csv(file.name)  # Read uploaded CSV
+    benchmark_text = df.to_string()  # Convert DataFrame to text
+    
+    prompt = f"Analyze the following benchmark scores and recommend the best model:\n\n{benchmark_text}"
+    
+    # Generate response using Llama-2
+    output = pipe(prompt, max_length=500, do_sample=True, temperature=0.7)
+    analysis_result = output[0]['generated_text']
+    
+    return analysis_result  # Return the analysis
 
-# Gradio UI
+# Gradio Interface for CSV Upload and Analysis
 iface = gr.Interface(
-    fn=chat_with_llama, 
-    inputs="text", 
+    fn=analyze_csv,
+    inputs=gr.File(label="Upload CSV File"),
     outputs="text",
-    title="Llama-2 Chatbot"
+    title="Llama-2 CSV Benchmark Analyzer",
+    description="Upload a CSV file with benchmark scores, and Llama-2 will analyze and recommend the best model."
 )
 
 iface.launch()