Update app.py

app.py

@@ -1,18 +1,42 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+import torch
 
-# Charger le modèle et le tokenizer
-model_name = "jondurbin/airoboros-gpt-3.5-turbo-100k-7b"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+# Load the tokenizer and model
+model_name = "openai-community/gpt2-large"
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+model = GPT2LMHeadModel.from_pretrained(model_name)
 
-# Fonction pour générer des réponses
-def generate_response(input_text):
-    inputs = tokenizer.encode(input_text, return_tensors="pt")
-    outputs = model.generate(inputs, max_length=150)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
+# Put model in eval mode and use GPU if available
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+model.eval()
 
-# Interface Gradio
-iface = gr.Interface(fn=generate_response, inputs="text", outputs="text", title="GPT-3.5 Turbo Chatbot")
-iface.launch()
+# Text generation function
+def generate_text(prompt, max_length=100, temperature=0.7):
+    inputs = tokenizer(prompt, return_tensors="pt").to(device)
+    outputs = model.generate(
+        inputs["input_ids"],
+        max_length=max_length,
+        temperature=temperature,
+        top_k=50,
+        top_p=0.95,
+        do_sample=True,
+        num_return_sequences=1
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Gradio interface
+interface = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.Textbox(lines=4, label="Enter Prompt"),
+        gr.Slider(minimum=50, maximum=300, step=10, value=100, label="Max Length"),
+        gr.Slider(minimum=0.1, maximum=1.5, step=0.1, value=0.7, label="Temperature")
+    ],
+    outputs="text",
+    title="GPT-2 Large Text Generator",
+    description="Powered by the openai-community/gpt2-large model."
+)
+
+interface.launch()