Fine-tuning DeepSeek-Coder on a new 122k synthetic HPC instruction dataset yields open-source models that reach 34.1 pass@1 on ParEval parallel code generation, besting other open baselines but trailing GPT-4.
Survey reveals ai’s impact on the developer experience,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages
Fine-tuning DeepSeek-Coder on a new 122k synthetic HPC instruction dataset yields open-source models that reach 34.1 pass@1 on ParEval parallel code generation, besting other open baselines but trailing GPT-4.