toolevalxm/llama3.1-8b_spec

Annoy LLaMA Spec Model

This model is part of the Annoy project for code reasoning and execution specification.

Model Description

This model has been fine-tuned for speculative execution reasoning tasks. It excels at predicting code execution outcomes and reasoning about program behavior.

Training

The model was trained using the Annoy methodology on the PythonEdu-Rs dataset. The training process involved:

• Stage 1: Speculative reasoning foundation
• Stage 2: Multi-turn revision refinement (Annoy++)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("toolevalxm/llama3.1-8b_spec")
tokenizer = AutoTokenizer.from_pretrained("toolevalxm/llama3.1-8b_spec")

Citation

If you use this model, please cite our paper.

Base Model

This model is fine-tuned from meta-llama/Llama-3.1-8B.

BibTeX Citation

@article{grattafiori2024llama,
      title={The Llama 3 Herd of Models},
      author={Grattafiori, Aaron and Dubey, Abhimanyu and Jauhri, Abhinav and Pandey, Abhinav and Kadian, Abhishek and Al-Dahle, Ahmad and Letman, Aiesha and Mathur, Akhil and Schelten, Alan and Vaughan, Alex and others},
      journal={arXiv preprint arXiv:2407.21783},
      year={2024}
}