Quantifying the Capabilities of LLMs across Scale and Precision

Understand

Scale is often attributed as one of the factors that cause an increase in the performance of LLMs, resulting in models with billion and trillion parameters.

• One of the limitations of such large models is the high computational requirements that limit their usage, deployment, and debugging in resource-constrained scenarios.
• Two commonly used alternatives to bypass these limitations are to use the smaller versions of LLMs (e.g.
• Llama 7B instead of Llama 70B) and lower the memory requirements by using quantization.