issues
search
turboderp
/
exllamav2
A fast inference library for running LLMs locally on modern consumer-class GPUs
MIT License
3.54k
stars
274
forks
source link
feat: frequency and presence penalty
#241
Closed
AlpinDale
closed
9 months ago
AlpinDale
commented
9 months ago
The implementation is based on the
OpenAI specification
.
The implementation is based on the OpenAI specification.