update tokenizer
Browse files- README.md +1 -1
- added_tokens.json +0 -4
- special_tokens_map.json +0 -14
- tokenizer_config.json +2 -18
README.md
CHANGED
|
@@ -59,7 +59,7 @@ tags:
|
|
| 59 |
pip install transformers==4.45.0 accelerate==0.34.1 sentencepiece==0.2.0 torchvision requests torch Pillow
|
| 60 |
pip install flash-attn --no-build-isolation
|
| 61 |
|
| 62 |
-
# For better performance, you can install grouped-gemm, which may take 3-5 minutes to install
|
| 63 |
pip install grouped_gemm==0.1.6
|
| 64 |
```
|
| 65 |
|
|
|
|
| 59 |
pip install transformers==4.45.0 accelerate==0.34.1 sentencepiece==0.2.0 torchvision requests torch Pillow
|
| 60 |
pip install flash-attn --no-build-isolation
|
| 61 |
|
| 62 |
+
# For better inference performance, you can install grouped-gemm, which may take 3-5 minutes to install
|
| 63 |
pip install grouped_gemm==0.1.6
|
| 64 |
```
|
| 65 |
|
added_tokens.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"</s>": 100353,
|
| 3 |
-
"<s>": 100352
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,18 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": {
|
| 3 |
-
"content": "<s>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "</s>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"unk_token": {
|
| 3 |
"content": "<unk>",
|
| 4 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -10,28 +10,12 @@
|
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false,
|
| 12 |
"special": true
|
| 13 |
-
},
|
| 14 |
-
"100352": {
|
| 15 |
-
"content": "<s>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false,
|
| 20 |
-
"special": true
|
| 21 |
-
},
|
| 22 |
-
"100353": {
|
| 23 |
-
"content": "</s>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": false,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"special": true
|
| 29 |
}
|
| 30 |
},
|
| 31 |
-
"bos_token":
|
| 32 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
-
"eos_token":
|
| 35 |
"legacy": true,
|
| 36 |
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
"pad_token": null,
|
|
|
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false,
|
| 12 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
}
|
| 14 |
},
|
| 15 |
+
"bos_token": null,
|
| 16 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 17 |
"clean_up_tokenization_spaces": false,
|
| 18 |
+
"eos_token": null,
|
| 19 |
"legacy": true,
|
| 20 |
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
"pad_token": null,
|