Upload 3 files
Browse files- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +10 -0
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfb237bc9775f26026a02cade1a19c6e4530e70e8b4dc35d979029252eda09ba
|
| 3 |
+
size 247500
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": "<unk>",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"pad_token": "<pad>"
|
| 6 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "SeamlessM4TTokenizer",
|
| 3 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 4 |
+
"unk_token": "<unk>",
|
| 5 |
+
"bos_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"sp_model_kwargs": {},
|
| 9 |
+
"clean_up_tokenization_spaces": true
|
| 10 |
+
}
|