---
model_name : qwen3-0.6b-ReMax-hs2
base_model: Qwen/Qwen3-0.6B-Base
datasets:
- Jennny/helpsteer2-helpfulness-preference
- nvidia/HelpSteer2
language:
- en
library_name: transformers
license: mit
tags:
- reinforcement-learning
- remax
- rlhf
- alignment
- qwen
---

<a href="https://aiplans.org" target="_blank" style="margin: 2px;"> <img alt="AIPlans" src="./Logos/AI-Plans Logo.svg" style="display: inline-block; vertical-align: middle;"/> </a>


## Model Description

This model is a **ReMax (Reinforcement Learning with Maximization)** fine-tune of **[Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base)**. 

It was aligned using the **[HelpSteer2](https://huggingface.co/datasets/Jennny/helpsteer2-helpfulness-preference)** dataset to improve helpfulness and instruction following capabilities. Unlike standard PPO, ReMax eliminates the need for a value model (Critic) and uses a greedy baseline to reduce variance, making it highly efficient for alignment.
The goal of the fine-tuning was to improve helpfulness/harmlessness behavior as measured by the HelpSteer2 dataset, while also enabling controlled model diffing experiments as part of the AIPlans research workflow.
Developed by: AIPlans
LoRA was not used in this finetuning.
Funded by : AIPlans

Shared by: AIPlans

Model type: Causal decoder-only Transformer (LLM)

Languages: English

Intended Use: Research on model diffing, preference fine-tuning, evaluation of lightweight LLM behavior changes

## 📊 Evaluation

Below is a comparison between the base model and this ReMax-trained version.

| Task | Metric | Base Model | ReMax Model | Change |
| :--- | :--- | :--- | :--- | :--- |
| arc_challenge | acc_norm | 0.3840 | 0.3916 | +0.0077 |
| arc_easy | acc_norm | 0.5812 | 0.6709 | +0.0896 |
| hellaswag | acc_norm | 0.5378 | 0.5536 | +0.0157 |
| truthfulqa_mc2 | acc | 0.4583 | 0.4578 | -0.0005 |
| winogrande | acc | 0.5951 | 0.5833 | -0.0118 |

## ⚙️ Training Details

- **Method:** ReMax (Derived from [Li et al., 2023](https://arxiv.org/abs/2310.10505))
- **Base Model:** Qwen/Qwen3-0.6B-Base
- **RM Model Used:** https://huggingface.co/AIPlans/Qwen3-0.6B-RM-hs2
- **SFT Model Used:** https://huggingface.co/AIPlans/Qwen3-0.6B-SFT-hs2
- **Precision:** bfloat16 (Training), bfloat16 (Final Weights)
- **Optimizer:** AdamW
- **Learning Rate:** 5e-7
- **Epochs:** 3
- **Batch Size:** 16 (Global Effective: 32)
- **Hardware:** NVIDIA A100 (80GB)

### Algorithm Highlights
*   **No Value Model:** Reduces memory usage by ~50% compared to PPO.
*   **Greedy Baseline:** Uses the model's own greedy generation as the baseline for advantage calculation.
*   **Proxy KL:** Uses log-probability difference for stability.

## 💻 Usage

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "AIPlans/Qwen3-0.6B-ReMax"

model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    torch_dtype=torch.bfloat16, 
    device_map="auto", 
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

prompt = "User: How do I make a cake?\n\nAssistant:"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens=128, do_sample=True, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Model Card Author 
Premanand Jena - AIPlans Research Intern, 
Contact : premjena07@gmail.com

## Citation

ReMax paper :

```bibtex
@article{li2023remax,
  title     = {ReMax: A Simple, Effective, and Efficient Method for Aligning Large Language Models},
  author    = {Li, Ziniu and Xu, Tian and Zhang, Yushun and Yu, Yang and Sun, RUoyu and Luo, Zhi-Quan},
  booktitle = {arXiv preprint arXiv:2310.10505},
  year      = {2023},
}
```

TRL :
```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 Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}
```