Mamba is a PyTorch sequence-modeling architecture built on selective state space models, offering a linear-time alternative to Transformers for language and other sequence tasks.
18.9K1.8KPythonApache-2.0Updated 3 months ago
#transformer-alternative
Curated GitHub repositories related to transformer-alternative, with AI summaries and key stats.
Mamba is a PyTorch sequence-modeling architecture built on selective state space models, offering a linear-time alternative to Transformers for language and other sequence tasks.
Official training and reference code for RWKV, an RNN-style language model architecture that can also be trained in parallel like a GPT transformer.