harrisonvanderbyl/rwkvstic
Framework agnostic python runtime for RWKV models
This tool helps AI practitioners and researchers use RWKV-V4 language models efficiently. You input a pre-trained RWKV model file and a text prompt, and it generates a coherent text output. It's designed for anyone working with large language models who needs flexible deployment across various hardware and software configurations.
147 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to run RWKV-V4 language models and require flexibility in choosing your deep learning backend (like PyTorch, JAX, TensorFlow) or specific hardware configurations like GPU memory optimization.
Not ideal if you are looking for a pre-packaged application for general text generation without needing to manage model loading or technical backend details.
Stars
147
Forks
16
Language
Python
License
MIT
Category
Last pushed
Aug 24, 2023
Commits (30d)
0
Dependencies
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/harrisonvanderbyl/rwkvstic"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras-team/keras
Deep Learning for humans
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)