Create app.py

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+tokenizer = GPT2Tokenizer.from_pretrained("microsoft/DialoGPT-medium")
+model = GPT2LMHeadModel.from_pretrained("microsoft/DialoGPT-medium")
+import torch
+from datasets import load_dataset
+from transformers import GPT2LMHeadModel, GPT2Tokenizer, Trainer, TrainingArguments
+dataset = load_dataset("text", data_files="SAMANXA.txt")
+tokenizer = GPT2Tokenizer.from_pretrained("microsoft/DialoGPT-medium")
+model = GPT2LMHeadModel.from_pretrained("microsoft/DialoGPT-medium")
+def tokenize_function(examples):
+    return tokenizer(examples["text"], truncation=True)
+
+tokenized_datasets = dataset.map(tokenize_function, batched=True)
+training_args = TrainingArguments(
+    output_dir="./results",
+    num_train_epochs=3,
+    per_device_train_batch_size=16,
+    per_device_eval_batch_size=64,
+    warmup_steps=500,
+    weight_decay=0.01,
+    logging_dir="./logs",
+)
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_datasets["train"],
+)
+
+trainer.train()
+def generate_response(message):
+    inputs = tokenizer.encode(message + tokenizer.eos_token, return_tensors='pt')
+    outputs = model.generate(inputs, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(outputs[:, inputs.shape[-1]:][0], skip_special_tokens=True)
+    
+    return response
+
+def generate_response(message):
+    if message == "hello SAMANGPT":
+        return "MOOOOIIIIN"
+    
+    inputs = tokenizer.encode(message + tokenizer.eos_token, return_tensors='pt')
+    outputs = model.generate(inputs, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(outputs[:, inputs.shape[-1]:][0], skip_special_tokens=True)
+    
+    return response
+iface = gr.Interface(fn=generate_response, inputs="text", outputs="text")
+iface.launch()