📙Paper: CodeT5Mix A Pretrained Mixture of Encoder-decoder Transformers for Code Understanding and Generation 📚Publisher: arxiv 🏠Author Affiliation: Anonymous 🔑Public: ✅ (promise) 🌐Archit...

🗂️Benchmark Name: HumanEval-X 📚Publisher: other 🏠Author Affiliation: Tsinghua University 🔗URL: https://github.com/THUDM/CodeGeeX/blob/main/codegeex/benchmark/README.md Number of Instance...

📙Paper: CodeGeeX 📚Publisher: other 🏠Author Affiliation: Tsinghua University 🔑Public: ✅ (Required Application) 🌐Architecture Encoder-Decoder Decoder-Only 📏Model...

🗂️Benchmark Name: MultiPL-MBPP 📚Publisher: Arxiv 🔗URL: https://github.com/nuprl/MultiPL-E/tree/main/datasets Number of Instances: 974 per programming language Problem Description’s Natur...

🗂️Benchmark Name: MultiPL-HumanEval 📚Publisher: Arxiv 🔗URL: https://github.com/nuprl/MultiPL-E/tree/main/datasets Number of Instances: 164 per programming language Problem Description’s ...

🗂️Benchmark Name: HumanEval-Infilling 📚Publisher: arxiv 🏠Author Affiliation: OpenAI 🔗URL: https://www.github.com/openai/human-eval-infilling Number of Instances: 164 Problem Descriptio...

📙Paper: CERT Continual Pre-Training on Sketches for Library-Oriented Code Generation 📚Publisher: IJCAI 🏠Author Affiliation: Microsoft 🔑Public: ✅ 🌐Architecture Encoder-Decoder ...

🗂️Benchmark Name: PandasEval 📚Publisher: IJCAI 🏠Author Affiliation: Microsoft 🔗URL: https://github.com/microsoft/PyCodeGPT/tree/main/cert/pandas-numpy-eval Number of Instances: 101 Pro...

🗂️Benchmark Name: NumpyEval 📚Publisher: IJCAI 🏠Author Affiliation: Microsoft 🔗URL: https://github.com/microsoft/PyCodeGPT/tree/main/cert/pandas-numpy-eval Number of Instances: 101 Prob...

📙Paper: Efficient Training of Language Models to Fill in the Middle 📚Publisher: arxiv 🏠Author Affiliation: OpenAI 🔑Public: ❌ 🌐Architecture Encoder-Decoder Decoder-Only ...