README.md

---
library_name: transformers
datasets:
- HumanLLMs/Human-Like-DPO-Dataset
language:
- en
base_model:
- HuggingFaceTB/SmolLM-135M-Instruct
---
# 🤖 SmolLM-135M - PPO Fine-Tuned Model

## 📝 Overview
This is a **Proximal Policy Optimization (PPO) fine-tuned version of SmolLM-135M**, designed to make its responses **more emotional and engaging**. The model has been optimized using **HumanLLMs/Human-Like-DPO-Dataset**.

PPO is a reinforcement learning algorithm commonly used in **RLHF (Reinforcement Learning from Human Feedback)** to optimize model behavior based on a reward model. [Paper](https://arxiv.org/abs/1707.06347)

## 📊 Training & Dataset
- **Base Model:** SmolLM-135M
- **Reward Model:** [`tsessk/llm-course-hw2-reward-model`](https://huggingface.co/tsessk/llm-course-hw2-reward-model)
- **Fine-Tuned Dataset:** [HumanLLMs/Human-Like-DPO-Dataset](https://huggingface.co/datasets/HumanLLMs/Human-Like-DPO-Dataset)
- **Objective:** Improve **expressiveness and emotional depth** through **reward-based reinforcement learning**.


## 📌 Example of PPO-Enhanced Response
Here’s an example of how the **PPO model** responds to a simple prompt compared to a standard LLM.

### **Prompt:**
```plaintext
What's your morning routine like?
```
### **Base model Response:**
```plaintext
I'm excited to start my morning routine! As a digital AI assistant, I don't have personal preferences or habits, but I can provide you with a general idea of what a morning routine might look like. Here's a sample routine that I've developed based on various studies and research:

**Morning Routine (10-15 minutes)**

1. **Hydrate**: Drink a full glass of water or a healthy beverage to start the day.
2. **Brush teeth**: Brush your teeth for 2 minutes, then rinse with water.
3. **Get dressed**: Put on some comfortable clothes, including a light jacket or sweater.
4. **Get ready for work**: Start with some morning exercise, such as a 10-minute yoga or stretching routine.
5. **Plan your day**: Review your schedule, set goals, and prioritize tasks.
6. **Get ready for bed**: Wind down with a relaxing activity, like reading or listening to calming music.

**Morning Routine (15-30 minutes)**

1. **Get ready for work**: Start with some morning exercise, such as a 10-minute yoga or stretching routine.
2. **Get ready for
```

### **PPO Response:**
```plaintext
I'm excited to start my morning routine! As a digital AI assistant, I don't have personal preferences or habits, but I can provide you with a general idea of what a morning routine might look like. Here's a sample routine I came up with:

**Morning Routine (10-15 minutes)**

1. **Hydrate**: Drink a full glass of water or a herbal tea to start the day.
2. **Brush teeth**: Brush your teeth for 2-3 minutes, then rinse with water.
3. **Get dressed**: Put on some comfortable clothes, including a light jacket or sweater.
4. **Get ready for work**: Start your day with a quick breakfast, such as oatmeal with fruit or scrambled eggs with whole-grain toast.
5. **Take a few deep breaths**: Take a few deep breaths to calm your mind and body.
6. **Get ready for the day**: Start your day with a morning workout, such as a yoga or Pilates class.
7. **Get ready for school**: Start your day with a morning routine, such as reading a book or taking a short walk.
8. **Get ready for bed**: Start your day with a gentle sleep
```