rootacess commited on
Commit
3cc31ab
·
verified ·
1 Parent(s): 1865eba

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -9
README.md CHANGED
@@ -97,12 +97,16 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
97
  ```
98
  ## Evaluation and Performance
99
 
100
- | Models | HUMANEVALEDIT | CANITEDIT | AIDER | POLYGLOT |
101
  |--------|---------------|-----------|-------|----------|
102
  | QwenCoder-2.5-3B | 73.2 | 37.1 | 36.8 | - |
103
  | QwenCoder-2.5-3B-LoRA | 64.6 | 36.2 | 35.8 | - |
104
  | QwenCoder-2.5-3B-SFT | 76.2 | 32.4 | 30.1 | - |
105
  | **NextCoder-3B** | 75.6 | 42.4 | 37.6 | - |
 
 
 
 
106
  | QwenCoder-2.5-14B | 87.8 | 58.1 | 66.9 | 9.3 |
107
  | QwenCoder-2.5-14B-LoRA | 78.0 | 50.9 | 66.2 | 5.3 |
108
  | QwenCoder-2.5-14B-SFT | 79.9 | 42.4 | 36.8 | 3.1 |
@@ -119,13 +123,11 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
119
  ## Citation
120
 
121
  ```bibtex
122
- @misc{aggarwal2025robustlearningdiversecode,
123
- title={Robust Learning of Diverse Code Edits},
124
- author={Tushar Aggarwal and Swayam Singh and Abhijeet Awasthi and Aditya Kanade and Nagarajan Natarajan},
125
- year={2025},
126
- eprint={2503.03656},
127
- archivePrefix={arXiv},
128
- primaryClass={cs.SE},
129
- url={https://arxiv.org/abs/2503.03656},
130
  }
131
  ```
 
97
  ```
98
  ## Evaluation and Performance
99
 
100
+ | Models | HUMANEVALFIX | CANITEDIT | AIDER | POLYGLOT |
101
  |--------|---------------|-----------|-------|----------|
102
  | QwenCoder-2.5-3B | 73.2 | 37.1 | 36.8 | - |
103
  | QwenCoder-2.5-3B-LoRA | 64.6 | 36.2 | 35.8 | - |
104
  | QwenCoder-2.5-3B-SFT | 76.2 | 32.4 | 30.1 | - |
105
  | **NextCoder-3B** | 75.6 | 42.4 | 37.6 | - |
106
+ | QwenCoder-2.5-7B | 73.8 | 48.1 | 59.4 | - |
107
+ | QwenCoder-2.5-7B-LoRA | 70.7 | 44.3 | 40.6 | - |
108
+ | QwenCoder-2.5-7B-SFT | 70.1 | 36.7 | 48.9 | - |
109
+ | **NextCoder-7B** | 81.1 | 50.5 | 65.7 | - |
110
  | QwenCoder-2.5-14B | 87.8 | 58.1 | 66.9 | 9.3 |
111
  | QwenCoder-2.5-14B-LoRA | 78.0 | 50.9 | 66.2 | 5.3 |
112
  | QwenCoder-2.5-14B-SFT | 79.9 | 42.4 | 36.8 | 3.1 |
 
123
  ## Citation
124
 
125
  ```bibtex
126
+ @inproceedings{aggarwal2025nextcoder,
127
+ author = {Aggarwal, Tushar and Singh, Swayam and Awasthi, Abhijeet and Kanade, Aditya and Natarajan, Nagarajan},
128
+ title = {NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits},
129
+ booktitle = {International Conference on Machine Learning},
130
+ year = {2025},
131
+ url = {https://www.microsoft.com/en-us/research/publication/nextcoder-robust-adaptation-of-code-lms-to-diverse-code-edits/},
 
 
132
  }
133
  ```