| inference: false | |
| Original model: https://huggingface.co/dvruette/llama-13b-pretrained-dropout | |
| 4/13/23: Added new q4_0 quantization using https://github.com/ggerganov/llama.cpp/pull/896. (Edited to write the model with ftype 2 so it won't be incorrectly identified as 4 - mostly q4_1 some f16.) |