entropy-guided-attention-llm

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

AI Code Completions

This repository contains demos I made with the Transformers library by HuggingFace.

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

Chinese version of GPT2 training code, using BERT tokenizer.

[NeurIPS 2024 Best Paper][GPT beats diffusion?] [scaling laws in visual generation?] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合

An unnecessarily tiny implementation of GPT-2 in NumPy.

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo