LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.
MIT License
Large-scale pretraining for dialogue
This repository contains resources for accessing the official benchmarks, codes, and checkpoints ...
Dedicated to building industrial foundation models for universal data intelligence across industr...
ProbTS is a benchmarking toolkit for time series forecasting.
[CVPR 2023] Official Implementation of X-Decoder for generalized decoding for pixel, image and la...
MASS: Masked Sequence to Sequence Pre-training for Language Generation
Grounded Language-Image Pre-training
General technology for enabling AI capabilities w/ LLMs and MLLMs
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
An efficient implementation of the popular sequence models for text generation, summarization, an...
To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention,...
The implementation of DeBERTa
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabil...
CodeBERT