Quantized LLaMA models reach 46% accuracy on Portuguese ENEM questions and 49% on English translations when run on standard home PCs.
Memory-efficient fine-tuning of compressed large language models via sub-4-bit integer quantization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmarking quantized LLaMa-based models on the Brazilian Secondary School Exam
Quantized LLaMA models reach 46% accuracy on Portuguese ENEM questions and 49% on English translations when run on standard home PCs.