RCEpic
turboderp/exllama
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
- Owner
- turboderp (personal account)
- Stars
- Stars: 2,946
- Forks
- Forks: 219
- Language
- Python
- License
- MIT
- Created
- 2023
- Tier
- RC (2,000 to 4,999 ★) What this tier means
Nearby in Python
All Python repos- Taiko2k/TauonStars: 2,946PythonRC
- Endermanch/MalwareDatabaseStars: 2,946PythonRC
- memodb-io/memobaseStars: 2,946PythonRC
- jamesmawm/High-Frequency-Trading-Model-with-IBStars: 2,945PythonRC