From ddee3a2237346e104984abca211412c902f830ba Mon Sep 17 00:00:00 2001 From: Ed Addario Date: Mon, 30 Jun 2025 19:03:53 +0100 Subject: [PATCH] Layer-wise & pruned quantization Q8_0 --- Dolphin-Mistral-24B-Venice-Edition-pruned-Q8_0.gguf | 3 +++ 1 file changed, 3 insertions(+) create mode 100644 Dolphin-Mistral-24B-Venice-Edition-pruned-Q8_0.gguf diff --git a/Dolphin-Mistral-24B-Venice-Edition-pruned-Q8_0.gguf b/Dolphin-Mistral-24B-Venice-Edition-pruned-Q8_0.gguf new file mode 100644 index 0000000..f5d08ba --- /dev/null +++ b/Dolphin-Mistral-24B-Venice-Edition-pruned-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e735a0efaf45354e9cb9d7b38e4309a4d7c528a741fc0d1a0cb4ab817181b9 +size 21883573504