chat template (#1)
Browse files- chat template (aecf8c06118794403ea3fa7e968fc669c2a3ad98)
- special_tokens_map.json +22 -17
- tokenizer.json +0 -1
- tokenizer_config.json +2 -4
special_tokens_map.json
CHANGED
@@ -1,23 +1,28 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
|
4 |
-
"content": "<|im_start|>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
-
{
|
11 |
-
"content": "<|im_end|>",
|
12 |
-
"lstrip": false,
|
13 |
-
"normalized": false,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
}
|
17 |
],
|
18 |
-
"bos_token":
|
19 |
-
|
20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"unk_token": {
|
22 |
"content": "<unk>",
|
23 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
"<|/inst|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
],
|
5 |
+
"bos_token": {
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"pad_token": {
|
20 |
+
"content": "<|endoftext|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
"unk_token": {
|
27 |
"content": "<unk>",
|
28 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -494,7 +494,6 @@
|
|
494 |
"end_of_word_suffix": null,
|
495 |
"fuse_unk": true,
|
496 |
"byte_fallback": true,
|
497 |
-
"ignore_merges": false,
|
498 |
"vocab": {
|
499 |
"<unk>": 0,
|
500 |
"<s>": 1,
|
|
|
494 |
"end_of_word_suffix": null,
|
495 |
"fuse_unk": true,
|
496 |
"byte_fallback": true,
|
|
|
497 |
"vocab": {
|
498 |
"<unk>": 0,
|
499 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -351,7 +349,7 @@
|
|
351 |
"<|/inst|>"
|
352 |
],
|
353 |
"bos_token": "<s>",
|
354 |
-
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '
|
355 |
"clean_up_tokenization_spaces": false,
|
356 |
"eos_token": "<|endoftext|>",
|
357 |
"legacy": false,
|
@@ -362,4 +360,4 @@
|
|
362 |
"tokenizer_class": "LlamaTokenizer",
|
363 |
"unk_token": "<unk>",
|
364 |
"use_default_system_prompt": false
|
365 |
-
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
|
|
349 |
"<|/inst|>"
|
350 |
],
|
351 |
"bos_token": "<s>",
|
352 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '' + message['content'] + '<|end|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
|
353 |
"clean_up_tokenization_spaces": false,
|
354 |
"eos_token": "<|endoftext|>",
|
355 |
"legacy": false,
|
|
|
360 |
"tokenizer_class": "LlamaTokenizer",
|
361 |
"unk_token": "<unk>",
|
362 |
"use_default_system_prompt": false
|
363 |
+
}
|