Add Aya tokenizer files (avoid gated repo dependency)
Browse files- .gitattributes +1 -0
- tokenizer/chat_template.jinja +1 -0
- tokenizer/tokenizer.json +3 -0
- tokenizer/tokenizer_config.json +20 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
tokenizer/chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Aya, a brilliant, sophisticated, multilingual AI-assistant trained to assist human users by providing thorough responses. You are able to interact and respond to questions in 23 languages and you are powered by a multilingual model built by Cohere For AI.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}
|
tokenizer/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d72cb57ce120d4797ec0a544cee3792f228c9dca4cb1863e11cb341f0ec3e576
|
| 3 |
+
size 20124086
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<BOS_TOKEN>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"cls_token": "<CLS>",
|
| 7 |
+
"eos_token": "<|END_OF_TURN_TOKEN|>",
|
| 8 |
+
"errors": "replace",
|
| 9 |
+
"is_local": false,
|
| 10 |
+
"legacy": true,
|
| 11 |
+
"mask_token": "<MASK_TOKEN>",
|
| 12 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 13 |
+
"pad_token": "<PAD>",
|
| 14 |
+
"sep_token": "<SEP>",
|
| 15 |
+
"sp_model_kwargs": {},
|
| 16 |
+
"spaces_between_special_tokens": false,
|
| 17 |
+
"tokenizer_class": "CohereTokenizer",
|
| 18 |
+
"unk_token": null,
|
| 19 |
+
"use_default_system_prompt": false
|
| 20 |
+
}
|