adding ggml q4 bit

ggml-model-q4_0.bin → 30B/alpaca-ggml-q4_0.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bcd1bb30e679c939f367be11b030fe20b3eb9a3606b9bc4106420f1827b6ae4
-size 20333638921
+oid sha256:04c4366dfa3048fa510dd5feb66f576ec2b4597fb163f4d6b0e3e1d19392a15f
+size 20333766925

30B/params.json

@@ -0,0 +1 @@
+{"dim": 6656, "multiple_of": 256, "n_heads": 52, "n_layers": 62, "norm_eps": 1e-06, "vocab_size": -1}

llama-30b-4bit.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1ba35063e377b1db79210b9edcc016a8666a4e1d5cc5da2cb1e305363d53d3
+size 16955102050

llama-30b-hf/tokenizer_config.json

@@ -1 +1 @@
-{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LLaMATokenizer", "unk_token": ""}
+{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LlamaTokenizer", "unk_token": ""}