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.
RWKV is a powerful AI model architecture designed for language and multimodal tasks. It efficiently processes information to generate text or handle various data types, offering a unique blend of performance and resource efficiency. It is primarily used by AI practitioners and researchers who build and train large language models or similar AI systems.
14,414 stars. Actively maintained with 2 commits in the last 30 days.
Use this if you are an AI developer or researcher looking to train large language models with improved efficiency and constant memory usage, especially on resource-constrained hardware.
Not ideal if you are an end-user simply looking to chat with an existing AI model without custom training or fine-tuning.
Stars
14,414
Forks
997
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 05, 2026
Commits (30d)
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/BlinkDL/RWKV-LM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related models
ModelCloud/GPTQModel
LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD...
intel/auto-round
🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality...
pytorch/ao
PyTorch native quantization and sparsity for training and inference
bodaay/HuggingFaceModelDownloader
Simple go utility to download HuggingFace Models and Datasets
NVIDIA/kvpress
LLM KV cache compression made easy