Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- .ipynb_checkpoints/README-checkpoint.md +100 -0
- .ipynb_checkpoints/config-checkpoint.json +29 -0
- README.md +100 -0
- added_tokens.json +24 -0
- assets/web.gif +3 -0
- config.json +29 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +211 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ 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 |
+
assets/web.gif filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.ipynb_checkpoints/README-checkpoint.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
model_name: LDAI-1.5-ANIU
|
4 |
+
base_model:
|
5 |
+
- Qwen/Qwen2.5-1.5B-Instruct
|
6 |
+
language:
|
7 |
+
- ru
|
8 |
+
license: cc-by-nc-4.0
|
9 |
+
---
|
10 |
+
|
11 |
+
# LDAI-1.5-ANIU
|
12 |
+
|
13 |
+
![https://aniu.lakomoor.com](assets/web.gif)
|
14 |
+
|
15 |
+
|
16 |
+
Модель предназначена для подбора аниме под предпочтения пользователей. LDAI-1.5-ANIU используется на сайте https://aniu.lakomoor.com
|
17 |
+
|
18 |
+
## Обучение:
|
19 |
+
|
20 |
+
Для обучения модели мы собрали датасет, основанный на данных с Aniu.
|
21 |
+
В качестве генерации синтетического датасета использовались модели [Vikhr-Nemo-12B-Instruct-R-21-09-24](https://huggingface.co/Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24) и [Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B), а за основу была взята модель [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
|
22 |
+
|
23 |
+
Использовался метод SFT для обучения модели.
|
24 |
+
|
25 |
+
Создание синтетического датасета и обучение модели потребовали около 120 часов работы на двух Nvidia Tesla P40 24GB.
|
26 |
+
|
27 |
+
## Пример кода для запуска:
|
28 |
+
|
29 |
+
**Рекомендуемая пареметры для генерации:**.
|
30 |
+
|
31 |
+
- temperature 0.3
|
32 |
+
- top_k 0
|
33 |
+
- top_p 1.0
|
34 |
+
|
35 |
+
***
|
36 |
+
|
37 |
+
```python
|
38 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
39 |
+
|
40 |
+
# Загрузка модели и токенизатора
|
41 |
+
model_name = "LakoMoor/LDAI-1.5-ANIU"
|
42 |
+
model = AutoModelForCausalLM.from_pretrained(model_name)
|
43 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
44 |
+
|
45 |
+
# Подготовка входного текста
|
46 |
+
input_text = "Семейное аниме для детей 8-12 лет"
|
47 |
+
|
48 |
+
messages = [
|
49 |
+
{"role": "system", "content": 'Вы модель "ldai-1.5-aniu", эксперт по подбору аниме на сайте Aniu. Пользователи описывают свои предпочтения, и ты рекомендуешь аниме, соответствующее их запросу. Учитывай жанры, возраст, предпочитаемый стиль и студию, а также добавляй краткое описание сюжета и полезные советы.'},
|
50 |
+
{"role": "user", "content": input_text},
|
51 |
+
]
|
52 |
+
|
53 |
+
# Токенизация и генерация текста
|
54 |
+
input_ids = tokenizer.apply_chat_template(messages, truncation=True, add_generation_prompt=True, return_tensors="pt")
|
55 |
+
output = model.generate(
|
56 |
+
input_ids,
|
57 |
+
max_length=512,
|
58 |
+
temperature=0.3,
|
59 |
+
num_return_sequences=1,
|
60 |
+
no_repeat_ngram_size=2,
|
61 |
+
top_k=0,
|
62 |
+
top_p=1.0,
|
63 |
+
)
|
64 |
+
|
65 |
+
# Декодирование и вывод результата
|
66 |
+
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
|
67 |
+
print(generated_text)
|
68 |
+
```
|
69 |
+
***
|
70 |
+
|
71 |
+
#### Ответ модели:
|
72 |
+
|
73 |
+
>{
|
74 |
+
> "title_ru": "Покемон: Современное поколение - Лукарио и загадка Мью",
|
75 |
+
> "title_alt": [
|
76 |
+
> "Pokemon: Lucario and the Mystery of Mew",
|
77 |
+
> "Gekijouban Pocket Monsters Advanced Generation: Myuu to Hadou no Yuusha Lucario",
|
78 |
+
> "Pokemon Movie 8"
|
79 |
+
> ],
|
80 |
+
> "year": 2010,
|
81 |
+
> "genres": [
|
82 |
+
> "детское",
|
83 |
+
> "экшен",
|
84 |
+
> "приключения",
|
85 |
+
> "драма",
|
86 |
+
> "фэнтези"
|
87 |
+
> ],
|
88 |
+
> "studio": "OLM",
|
89 |
+
> "author": "Кэти Пилон",
|
90 |
+
> "message": "Рекомендуем посмотреть аниме 'Покемон: Современное поколение - Лукарио и загадка Мью'. Это увлекательная история о приключениях в мире покемонов. Найдите его на сайте Aniu."
|
91 |
+
>}
|
92 |
+
|
93 |
+
|
94 |
+
|
95 |
+
|
96 |
+
### Ссылки
|
97 |
+
|
98 |
+
- [LakoMoor](https://t.me/lakomoordev)
|
99 |
+
- [Aniu](https://aniu.su/)
|
100 |
+
|
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 1536,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8960,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 21,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 2,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": true,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.46.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_sliding_window": false,
|
28 |
+
"vocab_size": 151665
|
29 |
+
}
|
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
model_name: LDAI-1.5-ANIU
|
4 |
+
base_model:
|
5 |
+
- Qwen/Qwen2.5-1.5B-Instruct
|
6 |
+
language:
|
7 |
+
- ru
|
8 |
+
license: cc-by-nc-4.0
|
9 |
+
---
|
10 |
+
|
11 |
+
# LDAI-1.5-ANIU
|
12 |
+
|
13 |
+
![https://aniu.lakomoor.com](assets/web.gif)
|
14 |
+
|
15 |
+
|
16 |
+
Модель предназначена для подбора аниме под предпочтения пользователей. LDAI-1.5-ANIU используется на сайте https://aniu.lakomoor.com
|
17 |
+
|
18 |
+
## Обучение:
|
19 |
+
|
20 |
+
Для обучения модели мы собрали датасет, основанный на данных с Aniu.
|
21 |
+
В качестве генерации синтетического датасета использовались модели [Vikhr-Nemo-12B-Instruct-R-21-09-24](https://huggingface.co/Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24) и [Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B), а за основу была взята модель [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
|
22 |
+
|
23 |
+
Использовался метод SFT для обучения модели.
|
24 |
+
|
25 |
+
Создание синтетического датасета и обучение модели потребовали около 120 часов работы на двух Nvidia Tesla P40 24GB.
|
26 |
+
|
27 |
+
## Пример кода для запуска:
|
28 |
+
|
29 |
+
**Рекомендуемая пареметры для генерации:**.
|
30 |
+
|
31 |
+
- temperature 0.3
|
32 |
+
- top_k 0
|
33 |
+
- top_p 1.0
|
34 |
+
|
35 |
+
***
|
36 |
+
|
37 |
+
```python
|
38 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
39 |
+
|
40 |
+
# Загрузка модели и токенизатора
|
41 |
+
model_name = "LakoMoor/LDAI-1.5-ANIU"
|
42 |
+
model = AutoModelForCausalLM.from_pretrained(model_name)
|
43 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
44 |
+
|
45 |
+
# Подготовка входного текста
|
46 |
+
input_text = "Семейное аниме для детей 8-12 лет"
|
47 |
+
|
48 |
+
messages = [
|
49 |
+
{"role": "system", "content": 'Вы модель "ldai-1.5-aniu", эксперт по подбору аниме на сайте Aniu. Пользователи описывают свои предпочтения, и ты рекомендуешь аниме, соответствующее их запросу. Учитывай жанры, возраст, предпочитаемый стиль и студию, а также добавляй краткое описание сюжета и полезные советы.'},
|
50 |
+
{"role": "user", "content": input_text},
|
51 |
+
]
|
52 |
+
|
53 |
+
# Токенизация и генерация текста
|
54 |
+
input_ids = tokenizer.apply_chat_template(messages, truncation=True, add_generation_prompt=True, return_tensors="pt")
|
55 |
+
output = model.generate(
|
56 |
+
input_ids,
|
57 |
+
max_length=512,
|
58 |
+
temperature=0.3,
|
59 |
+
num_return_sequences=1,
|
60 |
+
no_repeat_ngram_size=2,
|
61 |
+
top_k=0,
|
62 |
+
top_p=1.0,
|
63 |
+
)
|
64 |
+
|
65 |
+
# Декодирование и вывод результата
|
66 |
+
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
|
67 |
+
print(generated_text)
|
68 |
+
```
|
69 |
+
***
|
70 |
+
|
71 |
+
#### Ответ модели:
|
72 |
+
|
73 |
+
>{
|
74 |
+
> "title_ru": "Покемон: Современное поколение - Лукарио и загадка Мью",
|
75 |
+
> "title_alt": [
|
76 |
+
> "Pokemon: Lucario and the Mystery of Mew",
|
77 |
+
> "Gekijouban Pocket Monsters Advanced Generation: Myuu to Hadou no Yuusha Lucario",
|
78 |
+
> "Pokemon Movie 8"
|
79 |
+
> ],
|
80 |
+
> "year": 2010,
|
81 |
+
> "genres": [
|
82 |
+
> "детское",
|
83 |
+
> "экшен",
|
84 |
+
> "приключения",
|
85 |
+
> "драма",
|
86 |
+
> "фэнтези"
|
87 |
+
> ],
|
88 |
+
> "studio": "OLM",
|
89 |
+
> "author": "Кэти Пилон",
|
90 |
+
> "message": "Рекомендуем посмотреть аниме 'Покемон: Современное поколение - Лукарио и загадка Мью'. Это увлекательная история о приключениях в мире покемонов. Найдите его на сайте Aniu."
|
91 |
+
>}
|
92 |
+
|
93 |
+
|
94 |
+
|
95 |
+
|
96 |
+
### Ссылки
|
97 |
+
|
98 |
+
- [LakoMoor](https://t.me/lakomoordev)
|
99 |
+
- [Aniu](https://aniu.su/)
|
100 |
+
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
assets/web.gif
ADDED
Git LFS Details
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 1536,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8960,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 21,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 2,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": true,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.46.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_sliding_window": false,
|
28 |
+
"vocab_size": 151665
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.1,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.46.2"
|
14 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66ec0ea0cde95cce2436cba1b86932713965bbc92e710e386b1878020601274f
|
3 |
+
size 3086634632
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bd8c258c419667ebe0fb2fdb04f0f374292349d5deba1cba179d29177e80fc0
|
3 |
+
size 11421997
|
tokenizer_config.json
ADDED
@@ -0,0 +1,211 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"max_length": 131072,
|
203 |
+
"model_max_length": 131072,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"stride": 0,
|
207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
+
"truncation_side": "right",
|
209 |
+
"truncation_strategy": "longest_first",
|
210 |
+
"unk_token": null
|
211 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|