Junyang Lin's Projects
Code of a novel model for NMT
SOTA Weight-only Quantization Algorithm for LLMs
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
Go ahead and axolotl questions
Google AI 2018 BERT pytorch implementation
PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
Toolkit for Elevater Benchmark
Towards Knowledge-Based Personalized Product Description Generation in E-commerce
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
LLM inference in C/C++
Examples in the MLX framework
Official repository of OFA. Paper: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
š OpenDevin: Code Less, Make More
Python for Linguists ā a Gentle Introduction to Programming
Tensors and Dynamic neural networks in Python with strong GPU acceleration
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
Code for the article "Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification" (EMNLP 2018)
Enhanced fork of SWE-bench, tailored for OpenDevin's ecosystem.
š¤ Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
UniLM AI - Large-scale Self-supervised Pre-training across Tasks, Languages, and Modalities
A high-throughput and memory-efficient inference and serving engine for LLMs