import altair as alt
import numpy as np
import pandas as pd
import streamlit as st

import streamlit as st

st.set_page_config(page_title="Post-Training Techniques for LLMs", layout="centered")

st.title("🔧 Beyond Pretraining: Post-Training Techniques for LLMs")
st.subheader("Distillation, Preference Optimization, and RLHF — Visualized")

st.markdown("""
This Streamlit app hosts a visual guide to help navigate post-training strategies for language models, with real-world examples like **SmolLM3**, **Tulu**, and **DeepSeek-R1**.

📎 Download the full slide deck:
👉 [Click here to download (PDF)](https://huggingface.co/spaces/bird-of-paradise/post-training-techniques-guide/blob/main/src/Post%20Training%20Techniques.pdf)

---

🧠 **Topics covered:**
- Tradeoffs between SFT, DPO/APO/GRPO, PPO
- Subjective vs Rule-based rewards
- How real open-source models chose their strategy

Made with ❤️ by Jen Wei
""")

# Optional: Slide preview
st.image("src/Post_Training_Techniques_preview_2.png", caption="Slide 1: Tradeoffs between Optimization Paths", use_container_width=True)