Update app.py

app.py

@@ -1,64 +1,55 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
+from datasets import load_dataset
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, Trainer, TrainingArguments
+
+# Load your dataset
+dataset = load_dataset("vidu8/ch01")
+
+# Load tokenizer and model
+model_name = "t5-small"  # lightweight and fast
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Prepare dataset
+def preprocess(example):
+    inputs = "chat: " + example["input_text"]
+    targets = example["target_text"]
+    model_inputs = tokenizer(inputs, max_length=128, truncation=True)
+    labels = tokenizer(targets, max_length=128, truncation=True)
+    model_inputs["labels"] = labels["input_ids"]
+    return model_inputs
+
+train_dataset = dataset["train"].map(preprocess, batched=False)
+
+# Load model
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+# Set training arguments
+training_args = TrainingArguments(
+    output_dir="./results",
+    num_train_epochs=3,
+    per_device_train_batch_size=4,
+    logging_steps=10,
+    save_steps=100,
+    save_total_limit=1,
+    evaluation_strategy="no",
+)
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+# Define Trainer
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=train_dataset,
 )
 
+# Train
+trainer.train()
+
+# Gradio interface
+def chat(input_text):
+    inputs = tokenizer("chat: " + input_text, return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=50)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
 
-if __name__ == "__main__":
-    demo.launch()
+iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="Simple Chatbot")
+iface.launch()