Update code_eval_octopack.py

code_eval_octopack.py

@@ -11,10 +11,8 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""The CodeEval metric estimates the pass@k metric for code synthesis.
-This is an evaluation harness for the HumanEval problem solving dataset
-described in the paper "Evaluating Large Language Models Trained on Code"
-(https://arxiv.org/abs/2107.03374)."""
+"""This metric implements code evaluation with execution across multiple languages as used in the paper 
+"OctoPack: Instruction Tuning Code Large Language Models" (https://arxiv.org/abs/2308.07124)."""
 
 import itertools
 import os
@@ -30,35 +28,17 @@ from .execute import check_correctness
 
 
 _CITATION = """\
-@misc{chen2021evaluating,
-      title={Evaluating Large Language Models Trained on Code},
-      author={Mark Chen and Jerry Tworek and Heewoo Jun and Qiming Yuan \
-and Henrique Ponde de Oliveira Pinto and Jared Kaplan and Harri Edwards \
-and Yuri Burda and Nicholas Joseph and Greg Brockman and Alex Ray \
-and Raul Puri and Gretchen Krueger and Michael Petrov and Heidy Khlaaf \
-and Girish Sastry and Pamela Mishkin and Brooke Chan and Scott Gray \
-and Nick Ryder and Mikhail Pavlov and Alethea Power and Lukasz Kaiser \
-and Mohammad Bavarian and Clemens Winter and Philippe Tillet \
-and Felipe Petroski Such and Dave Cummings and Matthias Plappert \
-and Fotios Chantzis and Elizabeth Barnes and Ariel Herbert-Voss \
-and William Hebgen Guss and Alex Nichol and Alex Paino and Nikolas Tezak \
-and Jie Tang and Igor Babuschkin and Suchir Balaji and Shantanu Jain \
-and William Saunders and Christopher Hesse and Andrew N. Carr \
-and Jan Leike and Josh Achiam and Vedant Misra and Evan Morikawa \
-and Alec Radford and Matthew Knight and Miles Brundage and Mira Murati \
-and Katie Mayer and Peter Welinder and Bob McGrew and Dario Amodei \
-and Sam McCandlish and Ilya Sutskever and Wojciech Zaremba},
-      year={2021},
-      eprint={2107.03374},
-      archivePrefix={arXiv},
-      primaryClass={cs.LG}
+@article{muennighoff2023octopack,
+      title={OctoPack: Instruction Tuning Code Large Language Models}, 
+      author={Niklas Muennighoff and Qian Liu and Armel Zebaze and Qinkai Zheng and Binyuan Hui and Terry Yue Zhuo and Swayam Singh and Xiangru Tang and Leandro von Werra and Shayne Longpre},
+      journal={arXiv preprint arXiv:2308.07124},
+      year={2023}
 }
 """
 
 _DESCRIPTION = """\
-This metric implements the evaluation harness for the HumanEval problem solving dataset
-described in the paper "Evaluating Large Language Models Trained on Code"
-(https://arxiv.org/abs/2107.03374).
+This metric implements code evaluation with execution across multiple languages as used in the paper 
+"OctoPack: Instruction Tuning Code Large Language Models" (https://arxiv.org/abs/2308.07124).
 """
 
 
@@ -110,8 +90,6 @@ with:
 
 _LICENSE = """The MIT License
 
-Copyright (c) OpenAI (https://openai.com)
-
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
 in the Software without restriction, including without limitation the rights