Llama 2 7B Chat models

Quantized to 2 bit & 4 bit using ggml

llama-2-7b-chat-ggml-model-q2_k.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a743d7af0e6f9bb543c5f39d2c7cc332730c0762a664effab256f457663615b
+size 2866807424

llama-2-7b-chat-ggml-model-q4_k_m.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:909f370ae839bb22624e5f6d4ddb27b726b7124cc767dc3ec4a62064b13a2545
+size 4080714368