Upload tokenizer

2023-04-05 03:30:25 +00:00
parent d268cdbb0d
commit 482263cf87
3 changed files with 18 additions and 0 deletions
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
--- a/tokenizer_config.json
+++ 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": ""
+}