BlinkDL / RWKV-LM
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.
☆13,429Updated last week
Alternatives and similar repositories for RWKV-LM:
Users that are interested in RWKV-LM are comparing it to the libraries listed below
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,345Updated 9 months ago
- ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.☆9,469Updated 2 months ago
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,290Updated 5 months ago
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆29,902Updated 8 months ago
- Instruct-tune LLaMA on consumer hardware☆18,866Updated 8 months ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆17,913Updated this week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,043Updated 6 months ago
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆38,213Updated last week
- GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)☆7,675Updated last year
- An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.☆8,389Updated this week
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆11,614Updated 3 months ago
- Tensor library for machine learning☆12,206Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆6,868Updated this week
- Fast and memory-efficient exact attention☆16,587Updated last week
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,362Updated 7 months ago
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,352Updated 10 months ago
- Inference Llama 2 in one file of pure C☆18,246Updated 7 months ago
- Making large AI models cheaper, faster and more accessible☆40,690Updated this week
- Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)☆25,616Updated 6 months ago
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆37,675Updated this week
- StableLM: Stability AI Language Models☆15,832Updated 11 months ago
- Large Language Model Text Generation Inference☆9,941Updated this week
- Train transformer language models with reinforcement learning.☆12,890Updated this week
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,465Updated last year
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,837Updated 8 months ago
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,840Updated last year
- Inference code for Llama models☆57,944Updated 2 months ago
- Repo for external large-scale work☆6,524Updated 11 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆42,924Updated this week
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,683Updated 3 months ago