A single 15B supernet checkpoint supports runtime switching between attention mixer placements for multiple decode speed presets while retaining 77-96% quality relative to the teacher model.
Fast inference from transformers via speculative decoding
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Chronos pretrains transformer models on tokenized time series to deliver strong zero-shot forecasting across diverse domains.
LPSR raises 8B-model accuracy on MATH-500 from 28.8% to 44.0% by detecting error-indicating phase shifts in the residual stream and correcting via KV-cache rollback plus steering vectors, outperforming prompted self-correction and even a 70B model.
Math-Shepherd is an automatically trained process reward model that scores solution steps to verify and reinforce LLMs, lifting Mistral-7B from 77.9% to 89.1% on GSM8K and 28.6% to 43.5% on MATH.
RAFT aligns generative models by ranking samples with a reward model and fine-tuning only on the top-ranked outputs, reporting gains on reward scores and automated metrics for LLMs and diffusion models.
citing papers explorer
-
Super Apriel: One Checkpoint, Many Speeds
A single 15B supernet checkpoint supports runtime switching between attention mixer placements for multiple decode speed presets while retaining 77-96% quality relative to the teacher model.
-
Chronos: Learning the Language of Time Series
Chronos pretrains transformer models on tokenized time series to deliver strong zero-shot forecasting across diverse domains.
-
Latent Phase-Shift Rollback: Inference-Time Error Correction via Residual Stream Monitoring and KV-Cache Steering
LPSR raises 8B-model accuracy on MATH-500 from 28.8% to 44.0% by detecting error-indicating phase shifts in the residual stream and correcting via KV-cache rollback plus steering vectors, outperforming prompted self-correction and even a 70B model.
-
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Math-Shepherd is an automatically trained process reward model that scores solution steps to verify and reinforce LLMs, lifting Mistral-7B from 77.9% to 89.1% on GSM8K and 28.6% to 43.5% on MATH.
-
RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
RAFT aligns generative models by ranking samples with a reward model and fine-tuning only on the top-ranked outputs, reporting gains on reward scores and automated metrics for LLMs and diffusion models.