---
library_name: transformers
license: apache-2.0
datasets:
- Mehdi-Zogh/MNLP_M2_dpo_dataset
language:
- en
metrics:
- accuracy
base_model:
- Qwen/Qwen3-0.6B-Base
pipeline_tag: question-answering
---

# Model Card for Qwen3-0.6B-MNLP-DPO

This model is a Direct Preference Optimization (DPO) fine-tuned version of [Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) using the [`Mehdi-Zogh/MNLP_M2_dpo_dataset`](https://huggingface.co/datasets/Mehdi-Zogh/MNLP_M2_dpo_dataset). The goal was to improve the alignment of the base model's outputs with human preferences for educational assistance use cases.

---

## Model Details

### Model Description

This model was fine-tuned via the DPO (Direct Preference Optimization) algorithm on top of Qwen3-0.6B-Base. The dataset used for preference learning consists of query-response pairs with annotated preference labels, aiming to teach the model to generate more helpful, appropriate, and preferred responses in instructional contexts.

- **Developed by:** Mehdi Zoghlami
- **Model type:** Causal Language Model
- **Language(s):** English
- **License:** Apache 2.0
- **Finetuned from model:** [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base)
- **Dataset:** [Mehdi-Zogh/MNLP_M2_dpo_dataset](https://huggingface.co/datasets/Mehdi-Zogh/MNLP_M2_dpo_dataset)

---

## Uses

### Direct Use

This model is trained to be an AI tutor that is specialized in course content at EPFL.

### Downstream Use

It can serve as a base model for further alignment, personalization, or integration into interactive educational platforms or tutoring systems.

### Out-of-Scope Use

- Not recommended for use in high-stakes settings.
- Not intended for use outside the English language.
- Not intended for generating factual or up-to-date information (base model was not trained for retrieval-based tasks).

---

## Get Started with the Model

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Mehdi-Zogh/MNLP_M2_dpo_model"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "explain gradient descent in simple terms."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

```


## Training Details

### Training Data

The training data is the [Mehdi-Zogh/MNLP_M2_dpo_dataset](https://huggingface.co/datasets/Mehdi-Zogh/MNLP_M2_dpo_dataset), which contains instructional prompts with ranked preferred and rejected completions. The dataset is specifically designed for alignment research using preference optimization methods.


### Training Procedure

The model was fine-tuned using `trl`'s `DPOTrainer`


#### Training Hyperparameters


| Hyperparameter              | Value            |
|----------------------------|------------------|
| Learning rate              | 1e-5             |
| Epochs                     | 3                |
| Per-device train batch size| 1                |
| Per-device eval batch size | 1                |
| Gradient accumulation steps| 4                |
| Precision                  | bf16             |
| Early stopping patience    | 3                |



## Evaluation

320 samples out of the dataset were used for validation.

### Testing Data, Factors & Metrics

#### Testing Data

The model was tested on [zechen-nlp/MNLP_dpo_demo](https://huggingface.co/datasets/zechen-nlp/MNLP_dpo_demo)


#### Metrics

- **Accuracy of Preference:** Measures how often the model ranks the preferred response above the rejected one in held-out validation pairs.
- This is a standard metric in DPO training to evaluate how well the model aligns with human preferences.

### Results

- The model achieved a **preference accuracy of 84% ± 5.2%** on the test set.
- This indicates strong alignment between the model's outputs and the preferred responses provided in the dataset.