app.py

import gradio as gr
from huggingface_hub import InferenceClient
from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers  import Trainer, TrainingArguments

model_name = "HuggingFaceH4/zephyr-7b-beta"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

dataset = load_dataset("json", data_files="data.json", split = "train")

# Tokenize the dataset
def preprocess_function(examples):
    inputs = [example['input'] for example in examples]
    targets = [examples['output'] for example in examples]
    model_inputs = tokenizer(inputs, padding=True, truncation=True)
    labels = tokenizer(targets, padding=True, truncation=True).input_ids
    model_inputs['labels'] = labels
    return model_inputs

tokenized_datasets = dataset.map(preprocess_function, batched = True)

training_args = TrainingArguments(
    output_dir = "./results",
    evaluation_strategy = "epoch",
    learning_rate = 2e-5,
    per_device_train_batch_size = 3,
    weight_decay = 0.01,
)

trainer = Trainer(
    model = model,
    args = training_args,
    train_dataset = tokenized_datasets["train"],
    eval_dataset = tokenized_datasets["validation"],
)

#  Start fine-tuning
trainer.train()

trainer.evaluate()

model.save_pretrained("./fine_tuned_model")
tokenizer.save_pretrained("./fine_tuned_model")


client = InferenceClient("./fine_tuned_model")


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

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)",
        # ),
    ],
)


if __name__ == "__main__":
    demo.launch()