Search Results - RepositoryStats

70

820

apache-2.0

15

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.

llm nlp humaneval code-generation text-generation code-interpreter nlp-machine-learning

Created 2024-05-13

52 commits to main branch, last one 5 months ago

can-ai-code the-crypt-keeper

32

547

mit

12

Self-evaluating interview for AI coders

ai llm ggml humaneval langchain llama-cpp transformers

Created 2023-05-27

746 commits to main branch, last one 13 days ago

SkyCode-AI-CodeX-GPT3 SkyWorkAIGC

21

393

mit

4

SkyCode是一个多语言开源编程大模型，采用GPT3模型结构，支持Java, JavaScript, C, C++, Python, Go, shell等多种主流编程语言，并能理解中文注释。模型可以对代码进行补全，拥有强大解题能力，使您从编程中解放出来，专心于解决更重要的问题。| SkyCode is an open source programming model, which adopts...

go gpt3 java codex gpt-3 shell openai python gpt-neo deepmind alphacode humaneval polycoder codeparrot javascript

Created 2022-12-14

19 commits to main branch, last one about a year ago

code-eval abacaj

36

387

mit

11

Run evaluation on LLMs using human-eval benchmark

humaneval wizardcoder

Created 2023-07-01

76 commits to main branch, last one about a year ago

COBOLEval zorse-project

2

26

mit

2

Evaluate LLM-generated COBOL

llm cobol humaneval evaluation

Created 2024-03-20

4 commits to main branch, last one 7 months ago