Stars
[Preprint] An inference-time decoding strategy with adaptive foresight sampling
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
TruthfulQA: Measuring How Models Imitate Human Falsehoods
Stanford NLP Python library for Representation Finetuning (ReFT)
Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation
A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (p…