To what extent does specializing Code Llama for Python impact its zero-shot functional correctness on non-Pyth
Description
We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks. We provide multiple flavors to cover a wide range of applications: foundation models (Code Llama), Python specializations (Code Llama - Python), and instruction-following models (Code Llama - Instruct) with 7B, 13B, 34B and 70B parameters each. All models are trained on sequences of 16k tokens and show improvements on inputs with up
Research goal: To what extent does specializing Code Llama for Python impact its zero-shot functional correctness on non-Python languages within the HumanEval dataset across 7B, 34B, and 70B model sizes?
Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.3/10.
Notes
Files
paper.pdf
Files
(85.6 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:0ea0f9510b3e1983f5da189a33434317
|
85.6 kB | Preview Download |