Upload tokenizer
Browse files- README.md +0 -2
- added_tokens.json +1 -0
- special_tokens_map.json +7 -0
- tokenizer.json +10 -0
- tokenizer_config.json +10 -3
README.md
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
|
| 3 |
-
# Doc / guide: https://huggingface.co/docs/hub/model-cards
|
| 4 |
{}
|
| 5 |
---
|
| 6 |
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
{}
|
| 3 |
---
|
| 4 |
|
added_tokens.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"<|endoftext|>": 151643,
|
| 3 |
"<|im_end|>": 151645,
|
| 4 |
"<|im_start|>": 151644
|
|
|
|
| 1 |
{
|
| 2 |
+
"<image>": 151646,
|
| 3 |
"<|endoftext|>": 151643,
|
| 4 |
"<|im_end|>": 151645,
|
| 5 |
"<|im_start|>": 151644
|
special_tokens_map.json
CHANGED
|
@@ -3,6 +3,13 @@
|
|
| 3 |
"<|im_start|>",
|
| 4 |
"<|im_end|>"
|
| 5 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"eos_token": {
|
| 7 |
"content": "<|im_end|>",
|
| 8 |
"lstrip": false,
|
|
|
|
| 3 |
"<|im_start|>",
|
| 4 |
"<|im_end|>"
|
| 5 |
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<|im_start|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
"eos_token": {
|
| 14 |
"content": "<|im_end|>",
|
| 15 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -29,6 +29,15 @@
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": {
|
|
@@ -73,6 +82,7 @@
|
|
| 73 |
"end_of_word_suffix": "",
|
| 74 |
"fuse_unk": false,
|
| 75 |
"byte_fallback": false,
|
|
|
|
| 76 |
"vocab": {
|
| 77 |
"!": 0,
|
| 78 |
"\"": 1,
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 151646,
|
| 35 |
+
"content": "<image>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": {
|
|
|
|
| 82 |
"end_of_word_suffix": "",
|
| 83 |
"fuse_unk": false,
|
| 84 |
"byte_fallback": false,
|
| 85 |
+
"ignore_merges": false,
|
| 86 |
"vocab": {
|
| 87 |
"!": 0,
|
| 88 |
"\"": 1,
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"151643": {
|
| 5 |
"content": "<|endoftext|>",
|
|
@@ -24,14 +23,22 @@
|
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
}
|
| 28 |
},
|
| 29 |
"additional_special_tokens": [
|
| 30 |
"<|im_start|>",
|
| 31 |
"<|im_end|>"
|
| 32 |
],
|
| 33 |
-
"bos_token":
|
| 34 |
-
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content']
|
| 35 |
"clean_up_tokenization_spaces": false,
|
| 36 |
"eos_token": "<|im_end|>",
|
| 37 |
"errors": "replace",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"151643": {
|
| 4 |
"content": "<|endoftext|>",
|
|
|
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
+
},
|
| 27 |
+
"151646": {
|
| 28 |
+
"content": "<image>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
}
|
| 35 |
},
|
| 36 |
"additional_special_tokens": [
|
| 37 |
"<|im_start|>",
|
| 38 |
"<|im_end|>"
|
| 39 |
],
|
| 40 |
+
"bos_token": "<|im_start|>",
|
| 41 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 42 |
"clean_up_tokenization_spaces": false,
|
| 43 |
"eos_token": "<|im_end|>",
|
| 44 |
"errors": "replace",
|