BlinkDL / RWKV-LMLinks
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.
☆13,935Updated this week
Alternatives and similar repositories for RWKV-LM
Users that are interested in RWKV-LM are comparing it to the libraries listed below
Sorting:
- ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.☆9,500Updated last week
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆30,141Updated last year
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,362Updated 10 months ago
- Instruct-tune LLaMA on consumer hardware☆18,952Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,642Updated last year
- Fast and memory-efficient exact attention☆19,275Updated this week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,079Updated 2 months ago
- GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)☆7,688Updated 2 years ago
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,893Updated last year
- Accessible large language models via k-bit quantization for PyTorch.☆7,533Updated this week
- An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.☆8,459Updated 3 weeks ago
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆12,603Updated 8 months ago
- Tensor library for machine learning☆13,086Updated last week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆19,447Updated this week
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆9,900Updated last week
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,518Updated 2 years ago
- Instruction Tuning with GPT-4☆4,327Updated 2 years ago
- Train transformer language models with reinforcement learning.☆15,330Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,049Updated 3 months ago
- Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)☆25,732Updated last year
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆39,899Updated last week
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,806Updated 8 months ago
- A collection of libraries to optimise AI model performances☆8,368Updated last year
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,030Updated last year
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆23,428Updated last year
- An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries☆7,289Updated last month
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆43,960Updated 8 months ago
- Example models using DeepSpeed☆6,644Updated 2 weeks ago
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,457Updated 2 months ago
- Inference code for Llama models☆58,685Updated 7 months ago