bin123apple/AutoCoder
We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.
PythonApache-2.0
Issues
- 3
Impossible to install
#9 opened by Network-Sec - 5
Community Group
#10 opened by chmod777john - 2
Some problems about two-stage data synthesis
#13 opened by zhoucz97 - 10
What information is left out during inference from the output of model.generate()?
#11 opened by KevinH48264 - 1
Support datagen on any arbirtrary github repo
#7 opened by jonathanpv - 0
Grzesiek
#8 opened by Wawrzyn1985 - 1
Source code for dataset collection
#5 opened by rpand002 - 2
AEIV-Instruct dataset
#6 opened by ethanc8 - 1
Sharing conda environment with host
#4 opened by matbee-eth - 4
- 2
模型的训练数据有可能开源吗
#2 opened by xxyp - 4
模型加载及Windows环境测试情况反馈
#1 opened by wikeeyang