new tokenizer

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "<s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "<s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "special_tokens_map_file": "/home/sgugger/tmp/llama/llama-7b-tmp/tokenizer/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>"
+}