File size: 365 Bytes
360720e 658f4e2 360720e c45e7a5 360720e |
1 2 3 4 5 6 7 8 9 |
## Model Info
Merge of ChanSung's [Alpaca-LoRA-65B-elina](https://huggingface.co/LLMs/Alpaca-LoRA-65B-elina)
GGML quantizations of various types and sizes (4 and 5-bit). Compatible with koboldcpp and llamacpp (as of 5/5/2023).
**Update 5/20/2023:** The files that work with recent versions are currently just the q4_0 and q5_1 files.
## Benchmarks
Coming soon... |