RWKVQuant quantizes RWKV models to about 3.275 bits per weight with under 1% average accuracy loss by mixing scalar and vector quantization chosen by an entropy-and-moment proxy.
OpenReview, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
RWKVQuant quantizes RWKV models to about 3.275 bits per weight with under 1% average accuracy loss by mixing scalar and vector quantization chosen by an entropy-and-moment proxy.