Blealtan/RWKV-LM-LoRA
RWKV is a 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.
PythonApache-2.0
Stargazers
- 1500231819
- alpkabacTurkey
- alreadydoneHeidelberg / Shenzhen
- AnimeIsSatan
- axonaxis
- BladeSun
- boyjunqiang
- ckoshka
- cxumolLooking for a job
- darkskygit@toeverything
- dumpmemory
- Ehplodor
- exat500g
- fengyunzaidushi
- Fire-
- gzchenjiajunGUANGZHOU.GUANGDONG
- hibikaze-git
- hunterfrerich
- johnpaulbin
- joshuawarner32San Francisco
- Just4UziHIT SZ
- justinbuzzni
- korakoe
- LiliumSancta
- linonetwoVerseTensor
- ManyStrongWords
- Murugurugan
- ofirnk
- reslovedBritish Columbia, Canada
- scottjmaddoxAustin, TX
- sequoiar@InstantWebP2P @AIWorkspace @Co-Simulation @5GApp
- Takonan
- tiendung
- tradingaddict
- xiaol
- zhufengyunPeking University