Blealtan / RWKV-LM-LoRALinks
RWKV is a 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.
☆412Updated 2 years ago
Alternatives and similar repositories for RWKV-LM-LoRA
Users that are interested in RWKV-LM-LoRA are comparing it to the libraries listed below
Sorting:
- A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependenci…☆313Updated last year
- ☆81Updated last year
- 📖 — Notebooks related to RWKV☆58Updated 2 years ago
- This project is established for real-time training of the RWKV model.☆50Updated last year
- ☆535Updated last year
- Train llama with lora on one 4090 and merge weight of lora to work as stanford alpaca.☆52Updated 2 years ago
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆147Updated last year
- ChatGPT-like Web UI for RWKVstic☆100Updated 2 years ago
- Framework agnostic python runtime for RWKV models☆146Updated 2 years ago
- ☆460Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆132Updated last year
- Script and instruction how to fine-tune large RWKV model on your data for Alpaca dataset☆31Updated 2 years ago
- INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model☆1,540Updated 5 months ago
- Plain pytorch implementation of LLaMA☆188Updated 2 years ago
- ☆140Updated 2 weeks ago
- A QQ Chatbot based on RWKV (W.I.P.)☆80Updated last year
- Simple, hackable and fast implementation for training/finetuning medium-sized LLaMA-based models☆177Updated this week
- Python bindings for llama.cpp☆199Updated 2 years ago
- Enhancing LangChain prompts to work better with RWKV models☆34Updated 2 years ago
- The all-in-one RWKV runtime box with embed, RAG, AI agents, and more.☆575Updated last week
- This repo contains the data preparation, tokenization, training and inference code for BLOOMChat. BLOOMChat is a 176 billion parameter mu…☆585Updated last year
- 4 bits quantization of LLaMa using GPTQ☆130Updated 2 years ago
- Quick Start LLaMA models with multiple methods, and fine-tune 7B/65B with One-Click.☆353Updated last year
- Open Multilingual Chatbot for Everyone☆1,273Updated 2 months ago
- 8-bit CUDA functions for PyTorch in Windows 10☆70Updated 2 years ago
- Instruct-tune LLaMA on consumer hardware☆73Updated 2 years ago
- The paddle implementation of meta's LLaMA.☆45Updated 2 years ago
- Inference code for facebook LLaMA models with Wrapyfi support☆129Updated 2 years ago
- fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backe…☆413Updated 2 years ago
- Fine-tuning RWKV-World model☆26Updated 2 years ago