---
license: apache-2.0
base_model: Qwen/Qwen2.5-72B-Instruct
tags:
  - math
  - reasoning
  - qwen2
  - lora
  - peft
  - numina
library_name: peft
pipeline_tag: text-generation
datasets:
  - AI-MO/NuminaMath-CoT
---

# Elle-72B-Math-v2

## Model Description

Elle-72B-Math-v2 is a LoRA adapter fine-tuned on [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) for mathematical reasoning using the NuminaMath-CoT dataset.

## Model Details

- **Base Model**: Qwen/Qwen2.5-72B-Instruct
- **Adapter Type**: LoRA
- **LoRA Rank**: 64
- **LoRA Alpha**: 128
- **Target Modules**: All linear layers
- **Training Data**: NuminaMath-CoT

## Training

Fine-tuned using:
- Chain-of-thought mathematical reasoning examples
- Step-by-step problem decomposition
- Multiple solution strategies (algebraic, numerical, symbolic)

## Usage

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-72B-Instruct",
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)
model = PeftModel.from_pretrained(base_model, "aphoticshaman/elle-72b-math-v2")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-72B-Instruct")
```

## License

Apache 2.0