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.
☆13,788Updated 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 2 months ago
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,345Updated 8 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,550Updated last year
- Fast and memory-efficient exact attention☆18,340Updated this week
- GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)☆7,682Updated last year
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆19,028Updated last week
- Universal LLM Deployment Engine with ML Compilation☆20,950Updated this week
- Large Language Model Text Generation Inference☆10,311Updated last week
- Accessible large language models via k-bit quantization for PyTorch.☆7,212Updated last week
- A collection of libraries to optimise AI model performances☆8,372Updated 11 months ago
- Instruct-tune LLaMA on consumer hardware☆18,921Updated 11 months ago
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆12,224Updated 6 months ago
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,884Updated last year
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,071Updated 2 weeks ago
- Tensor library for machine learning☆12,808Updated this week
- Train transformer language models with reinforcement learning.☆14,513Updated last week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,631Updated last year
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆9,696Updated last week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆52,204Updated this week
- Python bindings for llama.cpp☆9,335Updated last week
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆30,065Updated 11 months ago
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆38,850Updated last month
- Instruction Tuning with GPT-4☆4,312Updated 2 years ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,891Updated 3 months ago
- An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries☆7,256Updated 2 weeks ago
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,428Updated last month
- Inference Llama 2 in one file of pure C☆18,543Updated 11 months ago
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,505Updated last year
- 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading☆9,710Updated 10 months ago
- Example models using DeepSpeed☆6,567Updated last week