OctoPack: Instruction Tuning Code Large Language Models (github.com) 1 points by wsxiaoys 2y ago ↗ HN
[–] wsxiaoys 2y ago ↗ Paper: https://arxiv.org/abs/2308.07124Highlights: This paper demonstrates the instruct fine-tuning code for Language Model Models (LLMs) using public Github commit data. The proposed method achieves the highest HumanEval pass@1 accuracy among permissive licensed LLM models.
1 comment
[ 5.3 ms ] story [ 6.9 ms ] threadHighlights: This paper demonstrates the instruct fine-tuning code for Language Model Models (LLMs) using public Github commit data. The proposed method achieves the highest HumanEval pass@1 accuracy among permissive licensed LLM models.