From 4a99934005d52ea68e148e800171ec6fc4c2faf4 Mon Sep 17 00:00:00 2001
From: Ray <wuyongyu@users.noreply.huggingface.co>
Date: Mon, 28 Aug 2023 14:57:01 +0000
Subject: [PATCH] Upload tokenizer_config.json with huggingface_hub

---
 tokenizer_config.json | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 tokenizer_config.json

diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..7d11019
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}