Update README.md

README.md

@@ -7,53 +7,25 @@ tags:
 - generated_from_trainer
 - trl
 - reward-trainer
-licence: license
 ---
 
-# Model Card for llm-course-hw2-reward-model
+# 🏆 Model Card for llm-course-hw2-reward-model  
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct) on the [HumanLLMs/Human-Like-DPO-Dataset](https://huggingface.co/datasets/HumanLLMs/Human-Like-DPO-Dataset) dataset.
-It has been trained using [TRL](https://github.com/huggingface/trl).
+This model is a **fine-tuned reward model** based on [HuggingFaceTB/SmolLM-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct), trained on the **[HumanLLMs/Human-Like-DPO-Dataset](https://huggingface.co/datasets/HumanLLMs/Human-Like-DPO-Dataset)** dataset.  
+It has been trained using **[TRL](https://github.com/huggingface/trl)** to **evaluate and rank responses based on human preferences**, playing a crucial role in **RLHF (Reinforcement Learning from Human Feedback)** for models like **SmolLM-135M-PPO**.
 
-## Quick start
-
-```python
-from transformers import pipeline
-
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="tsessk/llm-course-hw2-reward-model", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
-
-## Training procedure
-
- 
-
-
-This model was trained with Reward.
-
-### Framework versions
-
-- TRL: 0.15.2
-- Transformers: 4.48.3
-- Pytorch: 2.5.1+cu124
-- Datasets: 3.3.2
-- Tokenizers: 0.21.0
-
-## Citations
+---
 
+## 📝 Overview
+- **Base Model:** SmolLM-135M-Instruct
+- **Fine-Tuned Dataset:** [HumanLLMs/Human-Like-DPO-Dataset](https://huggingface.co/datasets/HumanLLMs/Human-Like-DPO-Dataset)
+- **Objective:** Learn to assign **higher scores** to more engaging, structured, and emotional responses.
+- **Use Case:** Used in **PPO-based RLHF training** to reinforce **human-like response quality**.
 
+### **Training Method**
+- The model was fine-tuned using **Direct Preference Comparisons**:
+  - Each sample contains a **chosen response** (preferred) and a **rejected response**.
+  - The model **learns to assign higher rewards** to the chosen response and **lower rewards** to the rejected one.
+- This reward function was used in **PPO fine-tuning** to optimize response generation.
 
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```
+---