danielhanchen
commited on
Commit
•
f57290b
1
Parent(s):
df02c6e
Upload tokenizer
Browse files- tokenizer.json +1 -0
- tokenizer_config.json +1 -0
tokenizer.json
CHANGED
@@ -2407,6 +2407,7 @@
|
|
2407 |
"end_of_word_suffix": null,
|
2408 |
"fuse_unk": false,
|
2409 |
"byte_fallback": false,
|
|
|
2410 |
"vocab": {
|
2411 |
"!": 0,
|
2412 |
"\"": 1,
|
|
|
2407 |
"end_of_word_suffix": null,
|
2408 |
"fuse_unk": false,
|
2409 |
"byte_fallback": false,
|
2410 |
+
"ignore_merges": true,
|
2411 |
"vocab": {
|
2412 |
"!": 0,
|
2413 |
"\"": 1,
|
tokenizer_config.json
CHANGED
@@ -2050,6 +2050,7 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|end_of_text|>",
|
2055 |
"model_input_names": [
|
|
|
2050 |
}
|
2051 |
},
|
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": [
|