Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +0 -1
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "<|
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -2348,7 +2348,6 @@
|
|
| 2348 |
"end_of_word_suffix": null,
|
| 2349 |
"fuse_unk": false,
|
| 2350 |
"byte_fallback": false,
|
| 2351 |
-
"ignore_merges": true,
|
| 2352 |
"vocab": {
|
| 2353 |
"!": 0,
|
| 2354 |
"\"": 1,
|
|
|
|
| 2348 |
"end_of_word_suffix": null,
|
| 2349 |
"fuse_unk": false,
|
| 2350 |
"byte_fallback": false,
|
|
|
|
| 2351 |
"vocab": {
|
| 2352 |
"!": 0,
|
| 2353 |
"\"": 1,
|
tokenizer_config.json
CHANGED
|
@@ -2052,7 +2052,7 @@
|
|
| 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 %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
-
"eos_token": "<|
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
|
|
|
| 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 %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|