app.py

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


"""
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)",
        ),
    ],
)


if __name__ == "__main__":
    demo.launch()
    
from datasets import load_dataset

ds = load_dataset("AI-MO/NuminaMath-CoT")
from datasets import load_dataset

from datasets import load_dataset
import gradio as gr

def show_data():
    # 加载数据集
    dataset = load_dataset("AI-MO/NuminaMath-CoT")
    train_data = dataset["train"][:5]
    return train_data

# 使用 Gradio 界面显示测试数据
demo = gr.Interface(fn=show_data, inputs=None, outputs="text", title="数据集测试")
demo.launch()

from transformers import AutoModelForCausalLM, AutoTokenizer, Trainer, TrainingArguments

# 加载预训练模型和分词器
model_name = "gpt2"
tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side="left")
model = AutoModelForCausalLM.from_pretrained(model_name)

# 数据集预处理
def tokenize_function(examples):
    return tokenizer(examples["text"], padding="max_length", truncation=True)

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

# 微调训练参数
training_args = TrainingArguments(
    output_dir="./results",
    evaluation_strategy="epoch",
    learning_rate=5e-5,
    per_device_train_batch_size=4,
    num_train_epochs=3,
    weight_decay=0.01,
)

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

trainer.train()