llama-3.1-8b-instruct-limo-lora

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct model. The fine-tuning was performed using Low-Rank Adaptation (LoRA) on the LIMO dataset to enhance the model's reasoning capabilities, based on the work in the paper: LIMO: Less is More for Reasoning.

This repo contains the merged model weights. The LoRA adapter version can be found from here.

Model description

• Base Model: meta-llama/Llama-3.1-8B-Instruct
• Fine-Tuning Dataset: GAIR/LIMO
• Fine-Tuning Method: Low-Rank Adaptation (LoRA)
• Library Used: peft
• License: Apache 2.0

Usage

To utilize this model for text generation tasks, follow the steps below:

Installation

Ensure you have the necessary libraries installed:

pip install torch transformers

Generating Text

from transformers import AutoModelForCausalLM, AutoTokenizer
  
model_name = "t83714/llama-3.1-8b-instruct-limo"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How much is (2+5)x5/7"

# Tokenize the input
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

# Generate the output
output = model.generate(**inputs, max_length=8000)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-06
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 15

Framework versions

• PEFT 0.12.0
• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0

Acknowledgment

This model is trained based on the work of Ye et al. (2025). If you use this model, please also consider citing their paper:

@misc{ye2025limoreasoning,
      title={LIMO: Less is More for Reasoning}, 
      author={Yixin Ye and Zhen Huang and Yang Xiao and Ethan Chern and Shijie Xia and Pengfei Liu},
      year={2025},
      eprint={2502.03387},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2502.03387}, 
}