How does the instruction-following capability (Code Llama - Instruct) of different model sizes (7B vs 34B vs 7

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: How does the instruction-following capability (Code Llama - Instruct) of different model sizes (7B vs 34B vs 70B) impact zero-shot performance on the HumanEval benchmark, as measured by pass@1 accuracy and functional correctness?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.5/10.