Upload 3 files
Browse files- special_tokens_map.json +2 -2
- tokenizer.json +2 -2
- tokenizer_config.json +2 -10
special_tokens_map.json
CHANGED
|
@@ -7,14 +7,14 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "<|
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "<|end_of_text|>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2539802b4016767e5475c0fa774895f4c33683f7c2ed9df643a61279e9ef1bd2
|
| 3 |
+
size 17209962
|
tokenizer_config.json
CHANGED
|
@@ -1,13 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "!",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
"128000": {
|
| 12 |
"content": "<|begin_of_text|>",
|
| 13 |
"lstrip": false,
|
|
@@ -2060,12 +2052,12 @@
|
|
| 2060 |
"bos_token": "<|begin_of_text|>",
|
| 2061 |
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2062 |
"clean_up_tokenization_spaces": true,
|
| 2063 |
-
"eos_token": "<|
|
| 2064 |
"model_input_names": [
|
| 2065 |
"input_ids",
|
| 2066 |
"attention_mask"
|
| 2067 |
],
|
| 2068 |
"model_max_length": 1000000000000000019884624838656,
|
| 2069 |
-
"pad_token": "
|
| 2070 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2071 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"128000": {
|
| 4 |
"content": "<|begin_of_text|>",
|
| 5 |
"lstrip": false,
|
|
|
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|end_of_text|>",
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 1000000000000000019884624838656,
|
| 2061 |
+
"pad_token": "<|end_of_text|>",
|
| 2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
}
|