RL

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.

14.5k 1.0k +0/wk
GitHub
attention-mechanism chatgpt deep-learning gpt gpt-2 gpt-3 language-model linear-attention lstm pytorch rnn rwkv
Trend 3

Star & Fork Trend (47 data points)

Stars
Forks

Multi-Source Signals

Growth Velocity

BlinkDL/RWKV-LM has +0 stars this period . 7-day velocity: 0.0%.

Deep analysis is being generated for this repository.

Signal-backed technical analysis will be available soon.

Metric RWKV-LM unstructured vosk-api ggml
Stars 14.5k 14.4k14.5k14.4k
Forks 1.0k 1.2k1.7k1.5k
Weekly Growth +0 +8+5+3
Language Python HTMLJupyter NotebookC++
Sources 1 111
License Apache-2.0 Apache-2.0Apache-2.0MIT

Capability Radar vs unstructured

RWKV-LM
unstructured
Maintenance Activity 98

Last code push 10 days ago.

Community Engagement 35

Fork-to-star ratio: 6.9%. Lower fork ratio may indicate passive usage.

Issue Burden 70

Issue data not yet available.

Growth Momentum 30

No measurable growth in the current period (first-day cold start expected).

License Clarity 95

Licensed under Apache-2.0. Permissive — safe for commercial use.

Risk scores are computed from real-time repository data. Higher scores indicate healthier metrics.