mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-03-09 16:49:20 +01:00
instead of `int` (while `int` option still being supported) This allows the following usage: `./quantize ggml-model-f16.bin ggml-model-q4_0.bin q4_0` instead of: `./quantize ggml-model-f16.bin ggml-model-q4_0.bin 2` |
||
|---|---|---|
| .. | ||
| full.Dockerfile | ||
| main.Dockerfile | ||
| tools.sh | ||