Add BibTeX citation section for base model
Browse files
README.md
CHANGED
|
@@ -1,5 +1,41 @@
|
|
| 1 |
-
# Annoy Qwen Coder Spec Model
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
**Base Model**
|
| 4 |
|
| 5 |
-
This model is fine-tuned from Qwen/Qwen2.5-Coder-7B.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Annoy Qwen Coder Spec Model
|
| 2 |
+
|
| 3 |
+
This model is part of the Annoy project for code reasoning and execution specification.
|
| 4 |
+
|
| 5 |
+
## Model Description
|
| 6 |
+
|
| 7 |
+
This model has been fine-tuned for speculative execution reasoning tasks on code. It can predict input/output pairs and verify execution trajectories.
|
| 8 |
+
|
| 9 |
+
## Training
|
| 10 |
+
|
| 11 |
+
The model was trained using the Annoy methodology on the PythonEdu-Rs dataset. Training was conducted in two stages:
|
| 12 |
+
- Stage 1: Initial speculative reasoning training
|
| 13 |
+
- Stage 2: Refinement with verified predictions
|
| 14 |
+
|
| 15 |
+
## Usage
|
| 16 |
+
|
| 17 |
+
```python
|
| 18 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 19 |
+
|
| 20 |
+
model = AutoModelForCausalLM.from_pretrained("toolevalxm/qwen2.5-7b-coder_spec")
|
| 21 |
+
tokenizer = AutoTokenizer.from_pretrained("toolevalxm/qwen2.5-7b-coder_spec")
|
| 22 |
+
```
|
| 23 |
+
|
| 24 |
+
## Citation
|
| 25 |
+
|
| 26 |
+
If you use this model, please cite our paper.
|
| 27 |
|
| 28 |
**Base Model**
|
| 29 |
|
| 30 |
+
This model is fine-tuned from Qwen/Qwen2.5-Coder-7B.
|
| 31 |
+
|
| 32 |
+
## BibTeX Citation
|
| 33 |
+
|
| 34 |
+
```bibtex
|
| 35 |
+
@article{hui2024qwen2,
|
| 36 |
+
title={Qwen2. 5-Coder Technical Report},
|
| 37 |
+
author={Hui, Binyuan and Yang, Jian and Cui, Zeyu and Yang, Jiaxi and Liu, Dayiheng and Zhang, Lei and Liu, Tianyu and Zhang, Jiajun and Yu, Bowen and Dang, Kai and others},
|
| 38 |
+
journal={arXiv preprint arXiv:2409.12186},
|
| 39 |
+
year={2024}
|
| 40 |
+
}
|
| 41 |
+
```
|