From 482263cf87d193903df86bab88b7edd384222637 Mon Sep 17 00:00:00 2001
From: Aleksey Korshuk <AlekseyKorshuk@users.noreply.huggingface.co>
Date: Wed, 5 Apr 2023 03:30:25 +0000
Subject: [PATCH] Upload tokenizer

---
 special_tokens_map.json | 6 ++++++
 tokenizer.model         | 3 +++
 tokenizer_config.json   | 9 +++++++++
 3 files changed, 18 insertions(+)
 create mode 100644 special_tokens_map.json
 create mode 100644 tokenizer.model
 create mode 100644 tokenizer_config.json

diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..318f913
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..6c00c74
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..44bf596
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,9 @@
+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 2048,
+  "padding_side": "right",
+  "special_tokens_map_file": "models/decapoda-research_llama-7b-hf/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": ""
+}