Elle-72B-Math-v2

Model Description

Elle-72B-Math-v2 is a LoRA adapter fine-tuned on 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

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