add 2-bit llama model

config.json

@@ -0,0 +1,19 @@
+{
+  "architectures": ["LlamaForCausalLM"],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "intermediate_size": 11008,
+  "initializer_range": 0.02,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "torch_dtype": "float16",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ac29638ed96a1f3da3da1618b6ac83bcfd3d933bdb9673b89b7242898b5a52
+size 2410179115

special_tokens_map.json

@@ -0,0 +1 @@
+{}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": ""
+}