LLM Evaluation
2025
- Evaluation of IBM Granite Models for Code-Generation Tasks on HumanEvalX
- Computação@UFCG Leads Brazil’s Contributions to the HELM-Stanford Framework in Partnership with IBM
- LLMs Inference API on IBM Power9 Server
- Building an API for LLM inferences on IBM Power9 servers
- Setting Up the Conda and PyTorch on IBM Power9 Servers
- Setting Up the OS, NVIDIA Drivers, CUDA, and cuDNN on IBM Power 9 Servers
- Evaluating Small-Scale LLMs (up to 8B) on PT-BR Benchmarks
- Performing CPU Inference on Power10
- Introduction