add tokenizer config on mt task
Browse files- mt/multi/transformer.large.fast.mtpg/en/merges.txt +1 -0
- mt/multi/transformer.large.fast.mtpg/en/special_tokens_map.json +1 -0
- mt/multi/transformer.large.fast.mtpg/en/tokenizer.json +0 -0
- mt/multi/transformer.large.fast.mtpg/en/tokenizer_config.json +1 -0
- mt/multi/transformer.large.fast.mtpg/en/vocab.json +0 -0
- mt/multi/transformer.large.mtpg/en/merges.txt +1 -0
- mt/multi/transformer.large.mtpg/en/special_tokens_map.json +1 -0
- mt/multi/transformer.large.mtpg/en/tokenizer.json +0 -0
- mt/multi/transformer.large.mtpg/en/tokenizer_config.json +1 -0
- mt/multi/transformer.large.mtpg/en/vocab.json +0 -0
mt/multi/transformer.large.fast.mtpg/en/merges.txt
CHANGED
@@ -1,3 +1,4 @@
|
|
|
|
1 |
β t
|
2 |
h e
|
3 |
β a
|
|
|
1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
2 |
β t
|
3 |
h e
|
4 |
β a
|
mt/multi/transformer.large.fast.mtpg/en/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
mt/multi/transformer.large.fast.mtpg/en/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mt/multi/transformer.large.fast.mtpg/en/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": true, "trim_offsets": true, "name_or_path": "jinmang2/dooly-hub/mt/multi/transformer.large.fast.mtpg", "tokenizer_class": "RobertaTokenizer"}
|
mt/multi/transformer.large.fast.mtpg/en/vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
mt/multi/transformer.large.mtpg/en/merges.txt
CHANGED
@@ -1,3 +1,4 @@
|
|
|
|
1 |
β t
|
2 |
h e
|
3 |
β a
|
|
|
1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
2 |
β t
|
3 |
h e
|
4 |
β a
|
mt/multi/transformer.large.mtpg/en/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
mt/multi/transformer.large.mtpg/en/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mt/multi/transformer.large.mtpg/en/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": true, "trim_offsets": true, "name_or_path": "jinmang2/dooly-hub/mt/multi/transformer.large.mtpg", "tokenizer_class": "RobertaTokenizer"}
|
mt/multi/transformer.large.mtpg/en/vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|