2001.07

,

Divergent Token Metrics: Measuring degradation to prune away LLM components – and optimize quantization

2001.07

,

Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity

2001.07

,

ARAGOG: Advanced RAG Output Grading

2001.07

,

QLLM: ACCURATE AND EFFICIENT LOW-BITWIDTH QUANTIZATION FOR LARGE LANGUAGE MODELS

2001.07

,

OMNIQUANT: OMNIDIRECTIONALLY CALIBRATED QUANTIZATION FOR LARGE LANGUAGE MODELS