removing gguf and adding relevant ggml model file

llama-2-7b.Q4_K_M.gguf → llama-2-7b-chat.ggmlv3.q4_K_M.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4567208c2221da5a9f2ded6cc26ce58dd47d0410902c3f57a4a3ed104ce51b0b
-size 4081004224
+oid sha256:0652a35e3d8cde0632e03a97924b51adf3945b22c7e000da1d21e81e52ac75e5
+size 4080714368