Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 5 of 5 for “"DeepSeek-Coder"”.
-
Bidirectional Generation of Behavior-Driven Development Artifacts Using Fine-Tuning and Retrieval-Augmented Generation
… It compares fine-tuning (CodeT5+ and Qwen2.5-Coder) with Retrieval-Augmented Generation (RAG) (Meta-Llama-3.1-8B, DeepSeek-Coder) across a curated dataset of 2,100 aligned pairs. Results demonstrate that generation quality is heavily influenced by task direction and context management. …
-
The Impact of Adversarial In-Context Examples on Code Generation Models
… pro generování kódu, včetně CodeGen, CodeLlama a DeepSeek-Coder. Výsledky ukazují, že krátké komentáře mohou snížit správnost generovaného kódu, zejména u úloh na úrovni funkcí. Úlohy na úrovni tříd jsou ovlivněny méně konzistentně, avšak komentáře zaměřené na následování příkladů a koordinaci …
-
Multi-Agent Large Language Model as AD/ADAS System Engineer
… five open-source LLMs, Codellama:7B, Mistral:7B, DeepSeek-Coder-v2:7B, Gemma3:4B, and Qwen2.5-Coder:7B, the pipeline shows a clear ability to generate correct source code for the simpler functions, while proving far less effective for the more advanced functions. Finally, we discuss the challenges …
-
Parameter-efficient fine-tuning for software engineering : a systematic study of low-resource and multilingual knowledge transfer
… transfer for code translation on modern decoder-only Code-LLMs, including CodeLlama, DeepSeek-Coder, and Qwen2.5-Coder. Fusion-based approaches are compared against LoRA and Compacter. The results indicate that LoRA remains a consistently strong baseline, while integrating Compacter within …