Upload tokenizer
Browse files- tokenizer.json +2 -7
- tokenizer_config.json +1 -5
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 2048,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
@@ -2412,7 +2407,7 @@
|
|
| 2412 |
"end_of_word_suffix": null,
|
| 2413 |
"fuse_unk": false,
|
| 2414 |
"byte_fallback": false,
|
| 2415 |
-
"ignore_merges":
|
| 2416 |
"vocab": {
|
| 2417 |
"!": 0,
|
| 2418 |
"\"": 1,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 2407 |
"end_of_word_suffix": null,
|
| 2408 |
"fuse_unk": false,
|
| 2409 |
"byte_fallback": false,
|
| 2410 |
+
"ignore_merges": false,
|
| 2411 |
"vocab": {
|
| 2412 |
"!": 0,
|
| 2413 |
"\"": 1,
|
tokenizer_config.json
CHANGED
|
@@ -2053,15 +2053,11 @@
|
|
| 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 |
-
"max_length": 2048,
|
| 2057 |
"model_input_names": [
|
| 2058 |
"input_ids",
|
| 2059 |
"attention_mask"
|
| 2060 |
],
|
| 2061 |
"model_max_length": 1000000000000000019884624838656,
|
| 2062 |
"pad_token": "<|end_of_text|>",
|
| 2063 |
-
"
|
| 2064 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2065 |
-
"truncation_side": "right",
|
| 2066 |
-
"truncation_strategy": "longest_first"
|
| 2067 |
}
|
|
|
|
| 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 |
}
|