Update tokenizer_config.json
Browse files- tokenizer_config.json +2 -2
tokenizer_config.json
CHANGED
@@ -18,7 +18,7 @@
|
|
18 |
"special": true
|
19 |
},
|
20 |
"2": {
|
21 |
-
"content": "<|
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
@@ -37,7 +37,7 @@
|
|
37 |
"bos_token": "<s>",
|
38 |
"chat_template": "{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{%- for message in messages -%}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'].rstrip() + '<|eot_id|>' -}}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{-'<|start_header_id|>assistant<|end_header_id|>\n\n'-}}\n{%- endif -%}",
|
39 |
"clean_up_tokenization_spaces": true,
|
40 |
-
"eos_token": "<|
|
41 |
"model_max_length": 1000000000000000019884624838656,
|
42 |
"pad_token": "<pad>",
|
43 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
18 |
"special": true
|
19 |
},
|
20 |
"2": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
|
|
37 |
"bos_token": "<s>",
|
38 |
"chat_template": "{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{%- for message in messages -%}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'].rstrip() + '<|eot_id|>' -}}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{-'<|start_header_id|>assistant<|end_header_id|>\n\n'-}}\n{%- endif -%}",
|
39 |
"clean_up_tokenization_spaces": true,
|
40 |
+
"eos_token": "<|im_end|>",
|
41 |
"model_max_length": 1000000000000000019884624838656,
|
42 |
"pad_token": "<pad>",
|
43 |
"tokenizer_class": "GPT2Tokenizer",
|