BlinkDL / RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
☆12,397Updated 2 weeks ago
Related projects: ⓘ
- ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.☆9,386Updated 2 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆9,906Updated 3 months ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆15,839Updated this week
- Instruct-tune LLaMA on consumer hardware☆18,537Updated last month
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,133Updated last month
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆10,327Updated last month
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆36,446Updated this week
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆29,346Updated 2 months ago
- Universal LLM Deployment Engine with ML Compilation☆18,642Updated this week
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,194Updated last month
- A high-throughput and memory-efficient inference and serving engine for LLMs☆26,822Updated this week
- Fast and memory-efficient exact attention☆13,401Updated this week
- GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)☆7,654Updated last year
- ImageBind One Embedding Space to Bind Them All☆8,221Updated last month
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆34,719Updated this week
- Tensor library for machine learning☆10,846Updated last week
- StableLM: Stability AI Language Models☆15,842Updated 5 months ago
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆19,294Updated last month
- A collection of libraries to optimise AI model performances☆8,373Updated last month
- Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)☆25,294Updated 2 weeks ago
- Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform☆10,812Updated last year
- Inference Llama 2 in one file of pure C☆17,153Updated last month
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆5,958Updated last week
- An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.☆8,212Updated last week
- Train transformer language models with reinforcement learning.☆9,288Updated this week
- Example models using DeepSpeed☆5,987Updated this week
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,339Updated last year
- Large Language Model Text Generation Inference☆8,762Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆7,620Updated 4 months ago
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆11,796Updated last month