---
library_name: transformers
license: gemma
license_link: https://ai.google.dev/gemma/terms
pipeline_tag: text-generation
tags:
- math
- reasoning
- computational-graph
- bangla
- low-resource
- distractor-aware
- grpo
- reinforcement-learning
- small-model
base_model:
- google/gemma-3-4b-it
language:
- bn
- en
datasets:
- dipta007/dagger
- dipta007/DistractMath-Bn
---

# DAGGER-4B-GRPO

<a href="https://arxiv.org/abs/2601.06853" target="_blank">
    <img alt="arXiv" src="https://img.shields.io/badge/arXiv-2601.06853-b31b1b" style="display: inline-block; vertical-align: middle;"/>
</a>
<a href="https://github.com/dipta007/dagger" target="_blank">
    <img alt="GitHub" src="https://img.shields.io/badge/GitHub-Code-black" style="display: inline-block; vertical-align: middle;"/>
</a>

## Model Description

**DAGGER-4B-GRPO** is trained with GRPO directly from the base Gemma-3-4B model without SFT initialization. This ablation model demonstrates the critical importance of SFT initialization for smaller models.

## Model Overview

| Attribute | Value |
|-----------|-------|
| Base Model | Gemma-3-4B-Instruct |
| Training | GRPO (from base) |
| Parameters | 4B |
| LoRA Rank | 64 |

## Performance

| Dataset | Original | +Distractor |
|---------|----------|-------------|
| MGSM | 29.2 | 13.1 |
| MSVAMP | 57.1 | 29.3 |

### Critical Finding: SFT Initialization Effect

| Initialization | MGSM | MGSM (+D) | MSVAMP (+D) |
|---------------|------|-----------|-------------|
| Base → GRPO | 29.2 | 13.1 | 29.3 |
| **SFT → GRPO** | **54.8** | **31.4** | **42.9** |

**Key Insight**: For 4B models, GRPO without SFT struggles to learn reliable graph generation. SFT provides essential scaffolding:
- **+25.6 points** on MGSM
- **+18.3 points** on MGSM (+Distractor)
- **+13.6 points** on MSVAMP (+Distractor)

This effect is more pronounced in smaller models than in 12B variants.

## Quickstart

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "dipta007/dagger-4B_GRPO"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

USER_PROMPT_TEMPLATE = """You are an expert Bengali Math Reasoner. Your task is to solve mathematical problems by constructing a "Computational Graph".

### Graph Rules:
- `id`: Unique identifier (e.g., "n1", "n2").
- `val`: The raw number extracted from text (for input nodes).
- `op`: The operation (`add`, `sub`, `mul`, `div`, `round`, `sqrt`, `floor`, `sum`, `mean`, `ratio_split`). Use `const` for input numbers.
- `args`: List of input node IDs.
- `distractor`: Boolean (`true` / `false`). Set to `true` if the node is NOT used in the final calculation path.
- `label`: Label for the node.

### Available Operations:
- Input: `const` (Use this for all numbers found in text or constants).
- Arithmetic: `add`, `sub`, `mul`, `div`, `abs` (absolute difference).
- Logic/Stats: `sum`, `mean`, `min` (minimum), `max` (maximum).
- Rounding: `round` (nearest int), `floor` (round down), `ceil` (round up).
- Advanced: `sqrt`, `pow`, `mod` (remainder), `gcd`, `lcm`.
- Output: `identity` ("final_result" points to the answer node)

Only output a JSON graph representing the solution, nothing else. Nodes must be topologically sorted, and there must be exactly one "final_result" node that represents the final answer. One example is provided below.

### Example:
Question:
মিনার কাছে ১২২১৯৫ টা কলম আছে। রাজুর কাছে ২৫০৮৪ টা কলম আছে। মিনা রাজুর কাছে ১১২৬ টি কলম চাইল। রাজু ১০০০ টি কলম দিতে রাজি হল, কিন্তু পরে আর দিলেনা। প্রতিটি কলমের দাম ৪৫.৬ টাকা। মিনা যদি কলমগুলো বিক্রি করতে চায়, সে কত টাকা পাবে?

Output:
```json
{{
  "nodes": [
    {{"id": "n1", "op": "const", "val": 122195, "distractor": false, "label": "মিনার কলম"}},
    {{"id": "n2", "op": "const", "val": 25084, "distractor": true, "label": "রাজুর কলম"}},
    {{"id": "n3", "op": "const", "val": 1126, "distractor": true, "label": "মিনা রাজুর কাছে চাইল"}},
    {{"id": "n4", "op": "const", "val": 1000, "distractor": true, "label": "রাজু দিতে রাজি হল"}},
    {{"id": "n5", "op": "const", "val": 45.6, "distractor": false, "label": "প্রতিটি কলমের দাম"}},
    {{"id": "total_money", "op": "mul", "args": ["n1", "n5"], "distractor": false, "label": "মিনার মোট টাকা"}},
    {{"id": "final_result", "op": "identity", "args": ["total_money"], "distractor": false, "label": "চূড়ান্ত উত্তর"}}
  ]
}}```

### Your Task:

Question:
{question}

Output:
"""

question = "রজারের 5টি টেনিস বল আছে। সে আরও 2 ক্যান টেনিস বল কিনেছে। প্রতিটি ক্যানে 3টি করে টেনিস বল আছে। তার কাছে এখন কতগুলি টেনিস বল আছে?"
prompt = USER_PROMPT_TEMPLATE.format(question=question)

messages = [
  {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate
outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.7, top_p=0.8)
response = tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True)

print(response)
```

## Training Configuration

| Parameter | Value |
|-----------|-------|
| Base Model | Gemma-3-4B-Instruct (no SFT) |
| LoRA Rank / Alpha | 64 / 128 |
| Global Batch Size | 32 |
| Generations per Prompt | 8 |
| Loss Type | BNPO |

## When to Use This Model

- **Ablation studies**: Understanding SFT contribution for smaller models
- **Research**: Studying capacity requirements for GRPO-only training
- **NOT recommended for production**: Use dagger-4B_SFT_GRPO instead

## Limitations

- **Low accuracy**: Struggles to generate valid computational graphs
- **High failure rate**: Often produces malformed JSON or incorrect structures
- **Poor distractor handling**: Collapses to 13.1% on augmented MGSM

## Recommendation

For 4B models, always use SFT initialization before GRPO:
- [dagger-4B_SFT_GRPO](https://huggingface.co/dipta007/dagger-4B_SFT_GRPO) provides +18 points improvement

## Related Models

| Model | Training | MGSM (+D) |
|-------|----------|-----------|
| **dagger-4B_GRPO** | Base → GRPO | 13.1 |
| [dagger-4B_SFT](https://huggingface.co/dipta007/dagger-4B_SFT) | SFT | 25.1 |
| [dagger-4B_SFT_GRPO](https://huggingface.co/dipta007/dagger-4B_SFT_GRPO) | SFT → GRPO | **31.4** |

## Citation

```bibtex
@misc{nazi2026dagdaggerdistractorawaregraphgeneration,
      title={{\dag}DAGGER: Distractor-Aware Graph Generation for Executable Reasoning in Math Problems}, 
      author={Zabir Al Nazi and Shubhashis Roy Dipta and Sudipta Kar},
      year={2026},
      eprint={2601.06853},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2601.06853}, 
}
```