HTL-CodeLlama-7B

How Do Humans Write Code? Large Models Do It the Same Way Too

Paper: https://arxiv.org/pdf/2402.15729

Code: https://github.com/seamoke/Human-Think-Language

Introduction

For this model, please sure your transformers>=4.39.2.

We introduce HTL, a model which utilizes the complete reasoning process of CoT to enhance PoT. This model was secondarily fine-tuned based on MAmmoTH-Coder-7B

Evaluation

The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results:

Prompt Format

If you want to do HTL:

Below is an instruction that describes a task. Write a response that appropriately completes the request.
I'd like you to solve this problem in 3 steps:
1.Answer the question in plain language without writing any code.\n
2.Output one line of *\n.
3.Write program code based on the solution process in step 1 to solve the problem.\n
### Instruction:
{query}
Let's write a program.
### Response:"

Citation

If you use the models, data, or code from this project, please cite the original paper:

@article{li2024humans,
  title={How Do Humans Write Code? Large Models Do It the Same Way Too},
  author={Li, Long},
  journal={arXiv preprint arXiv:2402.15729},
  year={2024}
}