FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
Paper • 2502.14856 • Published • 8
FR-Spec
Released ckpt for arxiv.org/abs/2502.14856
-
-
thunlp/LLaMA3-Instruct-8B-FR-Spec
Text Generation • Updated • 993 • 3 -
thunlp/Qwen2-7B-Instruct-FR-Spec
Text Generation • Updated • 2 • 1 -
thunlp/LLaMA3.2-Instruct-1B-FR-Spec
Text Generation • 0.3B • Updated • 2 -
openbmb/MiniCPM4-8B-Eagle-FRSpec
Text Generation • Updated • 183 • 9 -
openbmb/MiniCPM4-8B-Eagle-FRSpec-QAT-cpmcu
Text Generation • Updated • 75 • 11