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.
☆13,272Updated last week
Alternatives and similar repositories for RWKV-LM:
Users that are interested in RWKV-LM are comparing it to the libraries listed below
- ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.☆9,462Updated last month
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,271Updated 8 months ago
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,266Updated 4 months ago
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆29,864Updated 7 months ago
- Instruct-tune LLaMA on consumer hardware☆18,818Updated 7 months ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆17,640Updated this week
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆11,422Updated 2 months ago
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆13,671Updated 2 weeks ago
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,036Updated 6 months ago
- Fast and memory-efficient exact attention☆16,117Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆38,036Updated this week
- StableLM: Stability AI Language Models☆15,834Updated 10 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆9,138Updated this week
- Tensor library for machine learning☆12,013Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆6,756Updated this week
- 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading☆9,482Updated 5 months ago
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,453Updated last year
- Train transformer language models with reinforcement learning.☆12,185Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆37,208Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆40,442Updated this week
- An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.☆8,367Updated this week
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,821Updated 11 months ago
- GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)☆7,680Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆39,865Updated 2 months ago
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,350Updated 7 months ago
- Instruction Tuning with GPT-4☆4,276Updated last year
- A collection of libraries to optimise AI model performances☆8,375Updated 7 months ago
- Aligning pretrained language models with instruction data generated by themselves.☆4,298Updated last year
- Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM☆7,764Updated 2 weeks ago
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,665Updated 2 months ago