xkpengl

CoNLI_hallucination

CoNLI: a plug-and-play framework for ungrounded hallucination detection and reduction

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

factor

Code and data for the FACTOR paper

flash-attention

Fast and memory-efficient exact attention

HuggingFace-Download-Accelerator

利用HuggingFace的官方下载工具从镜像网站进行高速下载。

ic-mlc-MiniCPM

mlc-MiniCPM

MiniCPM on Android platform.

nixtla

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

qllm-eval

Code Repository of Evaluating Quantized Large Language Models

Time-LLM

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

xkpengl/nixtla

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

xkpengl/timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

xkpengl/Time-LLM

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

xkpengl/ic-mlc-MiniCPM

xkpengl/mlc-MiniCPM

MiniCPM on Android platform.

xkpengl/HuggingFace-Download-Accelerator

利用HuggingFace的官方下载工具从镜像网站进行高速下载。

xkpengl/flash-attention

Fast and memory-efficient exact attention

xkpengl/qllm-eval

Code Repository of Evaluating Quantized Large Language Models

xkpengl/DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

xkpengl/factor

Code and data for the FACTOR paper

xkpengl/CoNLI_hallucination

CoNLI: a plug-and-play framework for ungrounded hallucination detection and reduction