SWE-Llama are variants of the CodeLlama model fine-tuned on software engineering tasks extracted from real-world GitHub issues and pull requests. They were introduced and evaluated on the SWE-bench benchmark.
143 Pulls Updated 7 months ago
Updated 7 months ago
7 months ago
3b232b43d071 · 14GB
model
archllama
·
parameters13B
·
quantizationQ8_0
14GB
Readme
SWE-Llama are variants of the CodeLlama model fine-tuned on software engineering tasks extracted from real-world GitHub issues and pull requests. They were introduced and evaluated on the SWE-bench benchmark.
References: