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.
☆13,281Updated 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.☆9,464Updated last month
- Instruct-tune LLaMA on consumer hardware☆18,829Updated 7 months ago
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,266Updated 4 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,288Updated 9 months ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆17,688Updated this week
- Universal LLM Deployment Engine with ML Compilation☆20,143Updated this week
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆29,876Updated 7 months ago
- Train transformer language models with reinforcement learning.☆12,330Updated this week
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,354Updated 7 months ago
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆38,048Updated last week
- Tensor library for machine learning☆12,051Updated this week
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,457Updated last year
- StableLM: Stability AI Language Models☆15,836Updated 11 months ago
- GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)☆7,679Updated last year
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,037Updated 6 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆6,769Updated this week
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,825Updated 11 months ago
- 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading☆9,492Updated 6 months ago
- An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.☆8,369Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆40,799Updated this week
- Locally run an Instruction-Tuned Chat-Style LLM☆10,237Updated last year
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,670Updated 3 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆9,153Updated this week
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆11,450Updated 2 months ago
- Fast and memory-efficient exact attention☆16,156Updated this week
- LlamaIndex is the leading framework for building LLM-powered agents over your data.☆39,727Updated this week
- Large Language Model Text Generation Inference☆9,859Updated this week
- Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)☆25,599Updated 6 months ago
- A collection of libraries to optimise AI model performances☆8,375Updated 7 months ago
- A guidance language for controlling large language models.☆19,837Updated this week