Upload tokenizer
Browse files- README.md +2 -3
- tokenizer.json +1 -0
- tokenizer_config.json +3 -0
README.md
CHANGED
|
@@ -1,12 +1,11 @@
|
|
| 1 |
-
|
| 2 |
---
|
|
|
|
| 3 |
pipeline_tag: text-generation
|
| 4 |
inference: true
|
| 5 |
widget:
|
| 6 |
-
- text:
|
| 7 |
example_title: Hello world
|
| 8 |
group: Python
|
| 9 |
-
library_name: transformers
|
| 10 |
---
|
| 11 |
|
| 12 |
This model is randomly initialized, using the config from [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) but with smaller size.
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: transformers
|
| 3 |
pipeline_tag: text-generation
|
| 4 |
inference: true
|
| 5 |
widget:
|
| 6 |
+
- text: Hello!
|
| 7 |
example_title: Hello world
|
| 8 |
group: Python
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
This model is randomly initialized, using the config from [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) but with smaller size.
|
tokenizer.json
CHANGED
|
@@ -134,6 +134,7 @@
|
|
| 134 |
"end_of_word_suffix": null,
|
| 135 |
"fuse_unk": true,
|
| 136 |
"byte_fallback": true,
|
|
|
|
| 137 |
"vocab": {
|
| 138 |
"<unk>": 0,
|
| 139 |
"<s>": 1,
|
|
|
|
| 134 |
"end_of_word_suffix": null,
|
| 135 |
"fuse_unk": true,
|
| 136 |
"byte_fallback": true,
|
| 137 |
+
"ignore_merges": false,
|
| 138 |
"vocab": {
|
| 139 |
"<unk>": 0,
|
| 140 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
@@ -27,6 +29,7 @@
|
|
| 27 |
},
|
| 28 |
"additional_special_tokens": [],
|
| 29 |
"bos_token": "<s>",
|
|
|
|
| 30 |
"clean_up_tokenization_spaces": false,
|
| 31 |
"eos_token": "</s>",
|
| 32 |
"legacy": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 29 |
},
|
| 30 |
"additional_special_tokens": [],
|
| 31 |
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"legacy": true,
|