Files
ollama37/server/create.go
Bruce MacDonald ad035ad595 convert: quantize from safetensors needs kv (#10675)
When creating a quantized model from safetensors we
need the array KV values to be loaded.Changing this
value to -1 loads the KV values on the returned
layer to be used and saved during quantization.
2025-05-12 12:04:20 -07:00

18 KiB