import streamlit as st

st.markdown(
    """
    <style>
div.stButton > button:first-child {
    background-color: #ffd0d0;
}

div.stButton > button:active {
    background-color: #ff6262;
}

.st-emotion-cache-6qob1r {
    position: relative;
    height: 100%;
    width: 100%;
    background-color: black;
    overflow: overlay;
}

   div[data-testid="stStatusWidget"] div button {
        display: none;
        }

    .reportview-container {
            margin-top: -2em;
        }
        #MainMenu {visibility: hidden;}
        .stDeployButton {display:none;}
        footer {visibility: hidden;}
        #stDecoration {display:none;}
    button[title="View fullscreen"]{
    visibility: hidden;}
        </style>
""",
    unsafe_allow_html=True,
)

# Define the questions and answers
faq_data = {
    "What is a language model, and how does it work?": "Language models (LM) are a type of artificial intelligence (AI) that delve into the vast world of text data. By analyzing massive amounts of written information, they develop an understanding of how language works. This empowers them to predict the next word in a sequence, translate languages, and even generate creative text formats.",
    "How can I train my own language model?": "Yes, you can train your own language model (LM), but it requires effort and resources.It's a complex process. Consider starting small, exploring resources, and understanding the time commitment involved. There are also pre-trained, accessible LLMs available for exploration before venturing into training your own.",
    "What are the key considerations when fine-tuning a language model for a specific task?": "Fine-tuning a pre-trained language model for a specific task is common practice. Addressing considerations such as dataset selection, hyperparameter tuning, and evaluation metrics can assist users in achieving optimal performance.",
    "How do I evaluate the performance of my custom language model?": "Evaluating the performance of a custom language model involves various metrics and techniques. Explaining metrics such as perplexity, accuracy, and F1 score, as well as methodologies like cross-validation, can aid users in assessing their model's effectiveness.",
    "What are some common challenges in training custom language models?": "Training language models can be challenging due to issues such as overfitting, data scarcity, and computational resources. Identifying these challenges and offering strategies to mitigate them can help users navigate the training process more effectively.",
    "Can I use transfer learning with my own language model?": "Transfer learning, particularly using pre-trained language models as a starting point, is a popular approach in natural language processing. Discussing transfer learning techniques and their applicability to custom language models can provide valuable insights to users.",
    "How can I optimize the performance of my language model for inference?": "Optimizing language model inference for efficiency and speed is essential, especially in real-time applications. Providing tips on model quantization, pruning, and deployment strategies can assist users in optimizing their models for inference.",
    "What are some ethical considerations when developing and deploying custom language models?": "Ethical considerations, such as bias, fairness, and privacy, are increasingly important in language model development. Addressing these concerns and advocating for responsible AI practices can help users build and deploy their models ethically.",
    "How do I handle out-of-domain or adversarial inputs with my language model?": "Language models may encounter inputs that deviate from their training data distribution, leading to performance degradation or vulnerabilities. Offering techniques for handling out-of-domain or adversarial inputs, such as robustness testing and adversarial training, can assist users in improving their model's robustness.",
    "What resources and tools are available for building and deploying custom language models?": "Providing a curated list of resources, including libraries, frameworks, datasets, and tutorials, can empower users to explore and leverage the latest advancements in language model development and deployment."
}

st.title("Language Model FAQ")

# Display each question-answer pair in a dropdown expander
for question, answer in faq_data.items():
    with st.expander(question):
        st.write(answer)