Wizardcoder: Empowering code large language models with evol-instruct
… To ensure a thorough assessment of the functional correctness of LLM-synthesized code, …
+: Open code large language models for code understanding and generation. CoRR, abs/…
+: Open code large language models for code understanding and generation. CoRR, abs/…
Enhancing network management using code generated by large language models
… Additionally, we demonstrate that adding complementary program synthesis methods
could further enhance code quality. Finally, we demonstrate that our approach is cost-effective, …
could further enhance code quality. Finally, we demonstrate that our approach is cost-effective, …
DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning
… Code Large Language Models (Code LLMs) have demonstrated outstanding performance
… teacher models to synthesize instruction data to finetune small language models (Mitra et al.…
… teacher models to synthesize instruction data to finetune small language models (Mitra et al.…
Qwen2 technical report
… family of large language models and large multimodal modles… automated alignment
strategies to synthesize data at scale. … open-weight models, including Mixtral-8x22B (Jiang et al., …
strategies to synthesize data at scale. … open-weight models, including Mixtral-8x22B (Jiang et al., …
CodeShell Technical Report
… large language models mark a pivotal breakthrough in artificial intelligence. They are specifically
crafted to understand and generate programming languages… synthesis. In The Eleventh …
crafted to understand and generate programming languages… synthesis. In The Eleventh …
Pangu-coder2: Boosting large language models for code with ranking feedback
…, B Geng, A Fu, M Zeng, A Yu, J Ji, J Zhao… - arXiv preprint arXiv …, 2023 - arxiv.org
… The core idea of our approach is to guide a model towards producing higher-quality code,
by utilizing the test signals and human preferences jointly as feedback to rank responses. …
by utilizing the test signals and human preferences jointly as feedback to rank responses. …
Towards ai-assisted synthesis of verified dafny methods
… 3.3 Pilot Study and LLM Selection Program synthesis in a veri cation-aware language … the
potential of large language models (GPT-4 and PaLM-2 ) to synthesize method speci cations …
potential of large language models (GPT-4 and PaLM-2 ) to synthesize method speci cations …
Nemotron-4 15B Technical Report
…, J Maki, M Martinez, J You, J Kamalu… - arXiv preprint arXiv …, 2024 - arxiv.org
… We introduce Nemotron-4 15B, a 15-billion-parameter large multilingual language model …
,b; Yang et al., 2023; Jiang et al., 2023) in language model pre-training have been inspired by …
,b; Yang et al., 2023; Jiang et al., 2023) in language model pre-training have been inspired by …
Instructcoder: Instruction tuning large language models for code editing
… of deep learning models, partly due to data scarcity. In this work, we explore the use of Large
Language Models (LLMs) to … The study of Code Synthesis has led to exciting applications (…
Language Models (LLMs) to … The study of Code Synthesis has led to exciting applications (…
Multiple-Choice Questions are Efficient and Robust LLM Evaluators
… One advantage of multiple-choice questions is that they enable the evaluation of any language
model on any subject, by simply comparing the output logits of the tokens “A”, “B”, “C”, “D”…
model on any subject, by simply comparing the output logits of the tokens “A”, “B”, “C”, “D”…