-
RWKV-LM
RWKV is an 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.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
It once said 100 times faster and 100 times less (V)RAM here. However, it now says that RWKV-14B can be run with only 3 GB of VRAM, which is regardless a massive improvement, because a 14B model normally requires about 30 GB of VRAM or thereabouts.
NOTE:
The number of mentions on this list indicates mentions on common posts plus user suggested alternatives.
Hence, a higher number means a more popular project.
Related posts
-
How the RWKV language model works
-
[P] Raven 7B & 14B 🐦(RWKV finetuned on Alpaca+CodeAlpaca+Guanaco) and Gradio Demo for Raven 7B
-
[D] Totally Open Alternatives to ChatGPT
-
[R] RWKV 14B ctx8192 is a zero-shot instruction-follower without finetuning, 23 token/s on 3090 after latest optimization (16G VRAM is enough, and you can stream layers to save more VRAM)
-
[P] RWKV 14B is a strong chatbot despite only trained on Pile (16G VRAM for 14B ctx4096 INT8, more optimizations incoming)