Add new SentenceTransformer model
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +10 -0
- README.md +535 -0
- added_tokens.json +28 -0
- chat_template.jinja +85 -0
- config.json +30 -0
- config_sentence_transformers.json +14 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +246 -0
- vocab.json +0 -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.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 1024,
|
| 3 |
+
"pooling_mode_cls_token": false,
|
| 4 |
+
"pooling_mode_mean_tokens": false,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": true,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,535 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- sentence-transformers
|
| 4 |
+
- sentence-similarity
|
| 5 |
+
- feature-extraction
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- dataset_size:166507
|
| 8 |
+
- loss:MultipleNegativesRankingLoss
|
| 9 |
+
base_model: tomaarsen/Qwen3-Embedding-0.6B-18-layers
|
| 10 |
+
widget:
|
| 11 |
+
- source_sentence: التطبيق الثاني، النادر، هو عندما يتم التشكيك في تأكيد عام أو عالمي
|
| 12 |
+
للغاية، ونحن قادرون على اختباره من خلال فحص حالة واحدة.
|
| 13 |
+
sentences:
|
| 14 |
+
- هناك على الأقل تطبيقان يمكن استخدامهما.
|
| 15 |
+
- كلية الثالوث تأسست كمركز للتعلم البروتستانتي.
|
| 16 |
+
- التطبيق الثاني ليس نادرًا على الإطلاق ويتم استخدامه عادة.
|
| 17 |
+
- source_sentence: كيف أن ضوء نجم يسافر عبر الكون؟
|
| 18 |
+
sentences:
|
| 19 |
+
- هل يمكنك سحب حسابك المصرفي باستخدام بطاقة الخصم الخاصة بك في الصراف الآلي؟
|
| 20 |
+
- ما هي أفضل الأماكن للزيارة في كانغانغاد، كيرالا؟
|
| 21 |
+
- كيف يسافر الضوء عبر الفضاء؟
|
| 22 |
+
- source_sentence: أنا فخور بهم تقريباً
|
| 23 |
+
sentences:
|
| 24 |
+
- أنا فخور بهم تقريباً
|
| 25 |
+
- أنا أكرههم
|
| 26 |
+
- لقد استخدم هذا المكان لتخزين الأسلحة الكيميائية
|
| 27 |
+
- source_sentence: هل (كريستوفر لانجان) أذكى شخص في العالم؟
|
| 28 |
+
sentences:
|
| 29 |
+
- هل هناك أي موقع مثل Quora؟
|
| 30 |
+
- هل (كريس لانجان) أذكى رجل على وجه الأرض؟
|
| 31 |
+
- أنثى قوقازية تجمع بعض الأمثلة من الصخور
|
| 32 |
+
- source_sentence: إذا كنت تساوم على سجادة في البازار الكبير سوف تحصل على خلال اثنين
|
| 33 |
+
أو ثلاثة أكواب من كاي قبل أن يتم الاتفاق على سعر.
|
| 34 |
+
sentences:
|
| 35 |
+
- لا يمكنك المساومة على سجادة في البازار الكبير
|
| 36 |
+
- '|. على الصعيد الوطني ، يبلغ متوسط أجر علماء الفيزياء 6970 دولارًا في الشهر
|
| 37 |
+
(40.23 دولارًا للساعة). يكسب نصف الفيزيائيين ما بين 5430 دولارًا و 8690 دولارًا
|
| 38 |
+
شهريًا (31.35 دولارًا و 50.14 دولارًا في الساعة). يمكن لمعظم الفيزيائيين توقع
|
| 39 |
+
فوائد مثل الإجازة مدفوعة الأجر والإجازة المرضية والتأمين الصحي وخطة التقاعد. في
|
| 40 |
+
مينيسوتا ، متوسط أجر الفيزيائيين هو 36.88 دولارًا للساعة ، أو 6391 دولارًا شهريًا
|
| 41 |
+
لعامل بدوام كامل. يكسب نصف الفيزيائيين ما بين 31.78 دولارًا و 49.10 دولارًا في
|
| 42 |
+
الساعة ، أو ما بين 5507 دولارًا و 8509 دولارات شهريًا.'
|
| 43 |
+
- قبل الموافقة على السعر سوف تتناولين كوبين أو ثلاثة من الخمر
|
| 44 |
+
pipeline_tag: sentence-similarity
|
| 45 |
+
library_name: sentence-transformers
|
| 46 |
+
metrics:
|
| 47 |
+
- cosine_accuracy
|
| 48 |
+
model-index:
|
| 49 |
+
- name: SentenceTransformer based on tomaarsen/Qwen3-Embedding-0.6B-18-layers
|
| 50 |
+
results:
|
| 51 |
+
- task:
|
| 52 |
+
type: triplet
|
| 53 |
+
name: Triplet
|
| 54 |
+
dataset:
|
| 55 |
+
name: all nli dev
|
| 56 |
+
type: all-nli-dev
|
| 57 |
+
metrics:
|
| 58 |
+
- type: cosine_accuracy
|
| 59 |
+
value: 0.9200000166893005
|
| 60 |
+
name: Cosine Accuracy
|
| 61 |
+
- task:
|
| 62 |
+
type: triplet
|
| 63 |
+
name: Triplet
|
| 64 |
+
dataset:
|
| 65 |
+
name: 1million qwen 18
|
| 66 |
+
type: 1million-qwen-18
|
| 67 |
+
metrics:
|
| 68 |
+
- type: cosine_accuracy
|
| 69 |
+
value: 0.9178467392921448
|
| 70 |
+
name: Cosine Accuracy
|
| 71 |
+
---
|
| 72 |
+
|
| 73 |
+
# SentenceTransformer based on tomaarsen/Qwen3-Embedding-0.6B-18-layers
|
| 74 |
+
|
| 75 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [tomaarsen/Qwen3-Embedding-0.6B-18-layers](https://huggingface.co/tomaarsen/Qwen3-Embedding-0.6B-18-layers). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
| 76 |
+
|
| 77 |
+
## Model Details
|
| 78 |
+
|
| 79 |
+
### Model Description
|
| 80 |
+
- **Model Type:** Sentence Transformer
|
| 81 |
+
- **Base model:** [tomaarsen/Qwen3-Embedding-0.6B-18-layers](https://huggingface.co/tomaarsen/Qwen3-Embedding-0.6B-18-layers) <!-- at revision 0bf483f51888212cc2906e88687552bc9b169a9e -->
|
| 82 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 83 |
+
- **Output Dimensionality:** 1024 dimensions
|
| 84 |
+
- **Similarity Function:** Cosine Similarity
|
| 85 |
+
<!-- - **Training Dataset:** Unknown -->
|
| 86 |
+
<!-- - **Language:** Unknown -->
|
| 87 |
+
<!-- - **License:** Unknown -->
|
| 88 |
+
|
| 89 |
+
### Model Sources
|
| 90 |
+
|
| 91 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 92 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 93 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 94 |
+
|
| 95 |
+
### Full Model Architecture
|
| 96 |
+
|
| 97 |
+
```
|
| 98 |
+
SentenceTransformer(
|
| 99 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: Qwen3Model
|
| 100 |
+
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
|
| 101 |
+
(2): Normalize()
|
| 102 |
+
)
|
| 103 |
+
```
|
| 104 |
+
|
| 105 |
+
## Usage
|
| 106 |
+
|
| 107 |
+
### Direct Usage (Sentence Transformers)
|
| 108 |
+
|
| 109 |
+
First install the Sentence Transformers library:
|
| 110 |
+
|
| 111 |
+
```bash
|
| 112 |
+
pip install -U sentence-transformers
|
| 113 |
+
```
|
| 114 |
+
|
| 115 |
+
Then you can load this model and run inference.
|
| 116 |
+
```python
|
| 117 |
+
from sentence_transformers import SentenceTransformer
|
| 118 |
+
|
| 119 |
+
# Download from the 🤗 Hub
|
| 120 |
+
model = SentenceTransformer("Abdelkareem/ara-qwen3-18")
|
| 121 |
+
# Run inference
|
| 122 |
+
sentences = [
|
| 123 |
+
'إذا كنت تساوم على سجادة في البازار الكبير سوف تحصل على خلال اثنين أو ثلاثة أكواب من كاي قبل أن يتم الاتفاق على سعر.',
|
| 124 |
+
'قبل الموافقة على السعر سوف تتناولين كوبين أو ثلاثة من الخمر',
|
| 125 |
+
'لا يمكنك المساومة على سجادة في البازار الكبير',
|
| 126 |
+
]
|
| 127 |
+
embeddings = model.encode(sentences)
|
| 128 |
+
print(embeddings.shape)
|
| 129 |
+
# [3, 1024]
|
| 130 |
+
|
| 131 |
+
# Get the similarity scores for the embeddings
|
| 132 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 133 |
+
print(similarities.shape)
|
| 134 |
+
# [3, 3]
|
| 135 |
+
```
|
| 136 |
+
|
| 137 |
+
<!--
|
| 138 |
+
### Direct Usage (Transformers)
|
| 139 |
+
|
| 140 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 141 |
+
|
| 142 |
+
</details>
|
| 143 |
+
-->
|
| 144 |
+
|
| 145 |
+
<!--
|
| 146 |
+
### Downstream Usage (Sentence Transformers)
|
| 147 |
+
|
| 148 |
+
You can finetune this model on your own dataset.
|
| 149 |
+
|
| 150 |
+
<details><summary>Click to expand</summary>
|
| 151 |
+
|
| 152 |
+
</details>
|
| 153 |
+
-->
|
| 154 |
+
|
| 155 |
+
<!--
|
| 156 |
+
### Out-of-Scope Use
|
| 157 |
+
|
| 158 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 159 |
+
-->
|
| 160 |
+
|
| 161 |
+
## Evaluation
|
| 162 |
+
|
| 163 |
+
### Metrics
|
| 164 |
+
|
| 165 |
+
#### Triplet
|
| 166 |
+
|
| 167 |
+
* Datasets: `all-nli-dev` and `1million-qwen-18`
|
| 168 |
+
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
|
| 169 |
+
|
| 170 |
+
| Metric | all-nli-dev | 1million-qwen-18 |
|
| 171 |
+
|:--------------------|:------------|:-----------------|
|
| 172 |
+
| **cosine_accuracy** | **0.92** | **0.9178** |
|
| 173 |
+
|
| 174 |
+
<!--
|
| 175 |
+
## Bias, Risks and Limitations
|
| 176 |
+
|
| 177 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 178 |
+
-->
|
| 179 |
+
|
| 180 |
+
<!--
|
| 181 |
+
### Recommendations
|
| 182 |
+
|
| 183 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 184 |
+
-->
|
| 185 |
+
|
| 186 |
+
## Training Details
|
| 187 |
+
|
| 188 |
+
### Training Dataset
|
| 189 |
+
|
| 190 |
+
#### Unnamed Dataset
|
| 191 |
+
|
| 192 |
+
* Size: 166,507 training samples
|
| 193 |
+
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
| 194 |
+
* Approximate statistics based on the first 1000 samples:
|
| 195 |
+
| | anchor | positive | negative |
|
| 196 |
+
|:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
| 197 |
+
| type | string | string | string |
|
| 198 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 24.05 tokens</li><li>max: 113 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 52.3 tokens</li><li>max: 310 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 49.75 tokens</li><li>max: 441 tokens</li></ul> |
|
| 199 |
+
* Samples:
|
| 200 |
+
| anchor | positive | negative |
|
| 201 |
+
|:------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------|
|
| 202 |
+
| <code>الناس يقاتلون</code> | <code>رجلين يضربان بعضهما في الوجه في مباراة ملاكمة</code> | <code>رجلين يمشون على السقالة</code> |
|
| 203 |
+
| <code>ما هو الحد الذي يصف المسافة من مركز الدائرة إلى أي نقطة على الدائرة؟</code> | <code>مثال على مركز الدائرة. 1 المسافة الثابتة من مركز الدائرة إلى أي نقطة على الدائرة تسمى نصف قطر الدائرة. 2 قطر الدائرة هو قطعة مستقيمة تربط نقطتين على دائرة ويمر بمركز الدائرة.</code> | <code>قطر الدائرة هو المسافة من نقطة على الدائرة إلى نقطة راديان بعيدة ، وهو أقصى مسافة من نقطة على دائرة إلى أخرى.</code> |
|
| 204 |
+
| <code>تم تحويل مخزن الحبوب في القرن الثالث عشر ، بجانب طاحونة دقيق أقدم ، إلى متحف رائع لرؤوس الأبراج المنحوتة المعروضة على أعمدة أعيد بناؤها.</code> | <code>يمكن للزوار أن يروا العواصم المنحوتة في الدير في المتحف الذي كان يوما مخزن الحبوب.</code> | <code>مخزن الحبوب من القرن الثالث عشر تم التخلي عنه ولم يعد أحد يستخدمه لأي شيء</code> |
|
| 205 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
| 206 |
+
```json
|
| 207 |
+
{
|
| 208 |
+
"scale": 20.0,
|
| 209 |
+
"similarity_fct": "cos_sim"
|
| 210 |
+
}
|
| 211 |
+
```
|
| 212 |
+
|
| 213 |
+
### Evaluation Dataset
|
| 214 |
+
|
| 215 |
+
#### Unnamed Dataset
|
| 216 |
+
|
| 217 |
+
* Size: 9,250 evaluation samples
|
| 218 |
+
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
| 219 |
+
* Approximate statistics based on the first 1000 samples:
|
| 220 |
+
| | anchor | positive | negative |
|
| 221 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
| 222 |
+
| type | string | string | string |
|
| 223 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 23.95 tokens</li><li>max: 113 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 50.21 tokens</li><li>max: 321 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 47.97 tokens</li><li>max: 353 tokens</li></ul> |
|
| 224 |
+
* Samples:
|
| 225 |
+
| anchor | positive | negative |
|
| 226 |
+
|:----------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 227 |
+
| <code>في تعريف السكان المعرضين للخطر</code> | <code>في الطبيعة المحددة للسكان المعرضين للخطر ، يشير المصطلح إلى عملية أو سلسلة من الأحداث التي يمكن التنبؤ بها والتي تضع المجموعة المعلنة في مسار بعض الضرر المستقبلي. نظرًا لأن المصطلح قد تم استبعاده من السياق ، فليس لدينا أي طريقة للتعامل مع تفاصيل عملية أو حدث المخاطرة. المجموعات السكانية الخاصة) ، والتي لها عوامل فردية أو مركبة تجعلها عرضة لنتائج سيئة. من الواضح أن العوامل تختلف باختلاف فئة الخطر.</code> | <code>تعتمد الممارسة الإحصائية الناجحة على تعريف المشكلة المركّز. في أخذ العينات ، يتضمن ذلك تحديد المجتمع الذي يتم أخذ العينة منه. يمكن تعريف المجتمع على أنه يشمل جميع الأشخاص أو العناصر التي لها الصفة المميزة التي يرغب المرء في فهمها.</code> |
|
| 228 |
+
| <code>ومع ذلك، فإن العديد من الأنشطة باللغة العبرية فقط.</code> | <code>الكثير من الأنشطة متاحة فقط باللغة العبرية.</code> | <code>كل شيء كان باللغة الإنجليزية</code> |
|
| 229 |
+
| <code>هل جاذبية المشتري أقوى من الأرض</code> | <code>نتيجة لذلك ، تبلغ جاذبية سطح المشتري (التي تُعرَّف على أنها قوة الجاذبية عند قمم السحابة) 24.79 م / ث ، أو 2.528 جم. الجاذبية على زحل: مثل كوكب المشتري ، زحل هو عملاق غازي ضخم أكبر بكثير وأكثر كتلة من الأرض ، ولكنه أقل كثافة بكثير. باختصار ، متوسط نصف قطرها هو 58232 ± 6 كم (9.13 من الأرض) ، وكتلتها 5.6846 × 1026 كجم (95.15 مرة من الكتلة) ، وبكثافة 0.687 جم / سم 3.</code> | <code>على الأرض: تسارع الجاذبية. . . . . . . . . . . . 9.807 م / ث 2 تسارع مقارنة بكوكب الزهرة. . 111٪ تسارع مقارنة بالمريخ. . . 263.5٪ كتلة الرجل الذي يزن 100 رطل على وجه الأرض. . . . . 45.359 كجم وزن الرجل الذي يزن 100 رطل على كوكب الزهرة. . 110.7 رطل وزن الرجل الذي يزن 100 رطل على المريخ. . . 263.5 رطل على الزهرة: تسارع الجاذبية. . . . . . . . . . 8.858 م / ث 2 تسارع مقارنة بالأرض. . 90.3٪ تسارع مقارنة بـ ...</code> |
|
| 230 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
| 231 |
+
```json
|
| 232 |
+
{
|
| 233 |
+
"scale": 20.0,
|
| 234 |
+
"similarity_fct": "cos_sim"
|
| 235 |
+
}
|
| 236 |
+
```
|
| 237 |
+
|
| 238 |
+
### Training Hyperparameters
|
| 239 |
+
#### Non-Default Hyperparameters
|
| 240 |
+
|
| 241 |
+
- `eval_strategy`: steps
|
| 242 |
+
- `learning_rate`: 2e-05
|
| 243 |
+
- `num_train_epochs`: 1
|
| 244 |
+
- `warmup_ratio`: 0.1
|
| 245 |
+
- `fp16`: True
|
| 246 |
+
- `batch_sampler`: no_duplicates
|
| 247 |
+
|
| 248 |
+
#### All Hyperparameters
|
| 249 |
+
<details><summary>Click to expand</summary>
|
| 250 |
+
|
| 251 |
+
- `overwrite_output_dir`: False
|
| 252 |
+
- `do_predict`: False
|
| 253 |
+
- `eval_strategy`: steps
|
| 254 |
+
- `prediction_loss_only`: True
|
| 255 |
+
- `per_device_train_batch_size`: 8
|
| 256 |
+
- `per_device_eval_batch_size`: 8
|
| 257 |
+
- `per_gpu_train_batch_size`: None
|
| 258 |
+
- `per_gpu_eval_batch_size`: None
|
| 259 |
+
- `gradient_accumulation_steps`: 1
|
| 260 |
+
- `eval_accumulation_steps`: None
|
| 261 |
+
- `torch_empty_cache_steps`: None
|
| 262 |
+
- `learning_rate`: 2e-05
|
| 263 |
+
- `weight_decay`: 0.0
|
| 264 |
+
- `adam_beta1`: 0.9
|
| 265 |
+
- `adam_beta2`: 0.999
|
| 266 |
+
- `adam_epsilon`: 1e-08
|
| 267 |
+
- `max_grad_norm`: 1.0
|
| 268 |
+
- `num_train_epochs`: 1
|
| 269 |
+
- `max_steps`: -1
|
| 270 |
+
- `lr_scheduler_type`: linear
|
| 271 |
+
- `lr_scheduler_kwargs`: {}
|
| 272 |
+
- `warmup_ratio`: 0.1
|
| 273 |
+
- `warmup_steps`: 0
|
| 274 |
+
- `log_level`: passive
|
| 275 |
+
- `log_level_replica`: warning
|
| 276 |
+
- `log_on_each_node`: True
|
| 277 |
+
- `logging_nan_inf_filter`: True
|
| 278 |
+
- `save_safetensors`: True
|
| 279 |
+
- `save_on_each_node`: False
|
| 280 |
+
- `save_only_model`: False
|
| 281 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 282 |
+
- `no_cuda`: False
|
| 283 |
+
- `use_cpu`: False
|
| 284 |
+
- `use_mps_device`: False
|
| 285 |
+
- `seed`: 42
|
| 286 |
+
- `data_seed`: None
|
| 287 |
+
- `jit_mode_eval`: False
|
| 288 |
+
- `use_ipex`: False
|
| 289 |
+
- `bf16`: False
|
| 290 |
+
- `fp16`: True
|
| 291 |
+
- `fp16_opt_level`: O1
|
| 292 |
+
- `half_precision_backend`: auto
|
| 293 |
+
- `bf16_full_eval`: False
|
| 294 |
+
- `fp16_full_eval`: False
|
| 295 |
+
- `tf32`: None
|
| 296 |
+
- `local_rank`: 0
|
| 297 |
+
- `ddp_backend`: None
|
| 298 |
+
- `tpu_num_cores`: None
|
| 299 |
+
- `tpu_metrics_debug`: False
|
| 300 |
+
- `debug`: []
|
| 301 |
+
- `dataloader_drop_last`: False
|
| 302 |
+
- `dataloader_num_workers`: 0
|
| 303 |
+
- `dataloader_prefetch_factor`: None
|
| 304 |
+
- `past_index`: -1
|
| 305 |
+
- `disable_tqdm`: False
|
| 306 |
+
- `remove_unused_columns`: True
|
| 307 |
+
- `label_names`: None
|
| 308 |
+
- `load_best_model_at_end`: False
|
| 309 |
+
- `ignore_data_skip`: False
|
| 310 |
+
- `fsdp`: []
|
| 311 |
+
- `fsdp_min_num_params`: 0
|
| 312 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 313 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 314 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 315 |
+
- `deepspeed`: None
|
| 316 |
+
- `label_smoothing_factor`: 0.0
|
| 317 |
+
- `optim`: adamw_torch
|
| 318 |
+
- `optim_args`: None
|
| 319 |
+
- `adafactor`: False
|
| 320 |
+
- `group_by_length`: False
|
| 321 |
+
- `length_column_name`: length
|
| 322 |
+
- `ddp_find_unused_parameters`: None
|
| 323 |
+
- `ddp_bucket_cap_mb`: None
|
| 324 |
+
- `ddp_broadcast_buffers`: False
|
| 325 |
+
- `dataloader_pin_memory`: True
|
| 326 |
+
- `dataloader_persistent_workers`: False
|
| 327 |
+
- `skip_memory_metrics`: True
|
| 328 |
+
- `use_legacy_prediction_loop`: False
|
| 329 |
+
- `push_to_hub`: False
|
| 330 |
+
- `resume_from_checkpoint`: None
|
| 331 |
+
- `hub_model_id`: None
|
| 332 |
+
- `hub_strategy`: every_save
|
| 333 |
+
- `hub_private_repo`: None
|
| 334 |
+
- `hub_always_push`: False
|
| 335 |
+
- `gradient_checkpointing`: False
|
| 336 |
+
- `gradient_checkpointing_kwargs`: None
|
| 337 |
+
- `include_inputs_for_metrics`: False
|
| 338 |
+
- `include_for_metrics`: []
|
| 339 |
+
- `eval_do_concat_batches`: True
|
| 340 |
+
- `fp16_backend`: auto
|
| 341 |
+
- `push_to_hub_model_id`: None
|
| 342 |
+
- `push_to_hub_organization`: None
|
| 343 |
+
- `mp_parameters`:
|
| 344 |
+
- `auto_find_batch_size`: False
|
| 345 |
+
- `full_determinism`: False
|
| 346 |
+
- `torchdynamo`: None
|
| 347 |
+
- `ray_scope`: last
|
| 348 |
+
- `ddp_timeout`: 1800
|
| 349 |
+
- `torch_compile`: False
|
| 350 |
+
- `torch_compile_backend`: None
|
| 351 |
+
- `torch_compile_mode`: None
|
| 352 |
+
- `include_tokens_per_second`: False
|
| 353 |
+
- `include_num_input_tokens_seen`: False
|
| 354 |
+
- `neftune_noise_alpha`: None
|
| 355 |
+
- `optim_target_modules`: None
|
| 356 |
+
- `batch_eval_metrics`: False
|
| 357 |
+
- `eval_on_start`: False
|
| 358 |
+
- `use_liger_kernel`: False
|
| 359 |
+
- `eval_use_gather_object`: False
|
| 360 |
+
- `average_tokens_across_devices`: False
|
| 361 |
+
- `prompts`: None
|
| 362 |
+
- `batch_sampler`: no_duplicates
|
| 363 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 364 |
+
|
| 365 |
+
</details>
|
| 366 |
+
|
| 367 |
+
### Training Logs
|
| 368 |
+
<details><summary>Click to expand</summary>
|
| 369 |
+
|
| 370 |
+
| Epoch | Step | Training Loss | Validation Loss | all-nli-dev_cosine_accuracy | 1million-qwen-18_cosine_accuracy |
|
| 371 |
+
|:------:|:-----:|:-------------:|:---------------:|:---------------------------:|:--------------------------------:|
|
| 372 |
+
| -1 | -1 | - | - | 0.8039 | - |
|
| 373 |
+
| 0.0096 | 100 | 0.7579 | - | - | - |
|
| 374 |
+
| 0.0192 | 200 | 0.6067 | - | - | - |
|
| 375 |
+
| 0.0288 | 300 | 0.5796 | - | - | - |
|
| 376 |
+
| 0.0384 | 400 | 0.53 | - | - | - |
|
| 377 |
+
| 0.0480 | 500 | 0.5191 | - | - | - |
|
| 378 |
+
| 0.0577 | 600 | 0.5275 | - | - | - |
|
| 379 |
+
| 0.0673 | 700 | 0.5512 | - | - | - |
|
| 380 |
+
| 0.0769 | 800 | 0.5102 | - | - | - |
|
| 381 |
+
| 0.0865 | 900 | 0.5531 | - | - | - |
|
| 382 |
+
| 0.0961 | 1000 | 0.5475 | - | - | - |
|
| 383 |
+
| 0.1057 | 1100 | 0.5257 | - | - | - |
|
| 384 |
+
| 0.1153 | 1200 | 0.5233 | - | - | - |
|
| 385 |
+
| 0.1249 | 1300 | 0.5011 | - | - | - |
|
| 386 |
+
| 0.1345 | 1400 | 0.5626 | - | - | - |
|
| 387 |
+
| 0.1441 | 1500 | 0.527 | - | - | - |
|
| 388 |
+
| 0.1537 | 1600 | 0.4856 | - | - | - |
|
| 389 |
+
| 0.1634 | 1700 | 0.5102 | - | - | - |
|
| 390 |
+
| 0.1730 | 1800 | 0.4915 | - | - | - |
|
| 391 |
+
| 0.1826 | 1900 | 0.4725 | - | - | - |
|
| 392 |
+
| 0.1922 | 2000 | 0.4936 | - | - | - |
|
| 393 |
+
| 0.2018 | 2100 | 0.4771 | - | - | - |
|
| 394 |
+
| 0.2114 | 2200 | 0.5027 | - | - | - |
|
| 395 |
+
| 0.2210 | 2300 | 0.4802 | - | - | - |
|
| 396 |
+
| 0.2306 | 2400 | 0.5123 | - | - | - |
|
| 397 |
+
| 0.2402 | 2500 | 0.4633 | - | - | - |
|
| 398 |
+
| 0.2498 | 2600 | 0.4413 | - | - | - |
|
| 399 |
+
| 0.2594 | 2700 | 0.4486 | - | - | - |
|
| 400 |
+
| 0.2690 | 2800 | 0.4743 | - | - | - |
|
| 401 |
+
| 0.2787 | 2900 | 0.4082 | - | - | - |
|
| 402 |
+
| 0.2883 | 3000 | 0.4879 | - | - | - |
|
| 403 |
+
| 0.2979 | 3100 | 0.4499 | - | - | - |
|
| 404 |
+
| 0.3075 | 3200 | 0.4273 | - | - | - |
|
| 405 |
+
| 0.3171 | 3300 | 0.4311 | - | - | - |
|
| 406 |
+
| 0.3267 | 3400 | 0.431 | - | - | - |
|
| 407 |
+
| 0.3363 | 3500 | 0.4339 | - | - | - |
|
| 408 |
+
| 0.3459 | 3600 | 0.4189 | - | - | - |
|
| 409 |
+
| 0.3555 | 3700 | 0.433 | - | - | - |
|
| 410 |
+
| 0.3651 | 3800 | 0.434 | - | - | - |
|
| 411 |
+
| 0.3747 | 3900 | 0.4416 | - | - | - |
|
| 412 |
+
| 0.3844 | 4000 | 0.4024 | - | - | - |
|
| 413 |
+
| 0.3940 | 4100 | 0.4052 | - | - | - |
|
| 414 |
+
| 0.4036 | 4200 | 0.4153 | - | - | - |
|
| 415 |
+
| 0.4132 | 4300 | 0.4024 | - | - | - |
|
| 416 |
+
| 0.4228 | 4400 | 0.4244 | - | - | - |
|
| 417 |
+
| 0.4324 | 4500 | 0.4543 | - | - | - |
|
| 418 |
+
| 0.4420 | 4600 | 0.4018 | - | - | - |
|
| 419 |
+
| 0.4516 | 4700 | 0.3622 | - | - | - |
|
| 420 |
+
| 0.4612 | 4800 | 0.3914 | - | - | - |
|
| 421 |
+
| 0.4708 | 4900 | 0.3855 | - | - | - |
|
| 422 |
+
| 0.4804 | 5000 | 0.3716 | - | - | - |
|
| 423 |
+
| 0.4901 | 5100 | 0.3798 | - | - | - |
|
| 424 |
+
| 0.4997 | 5200 | 0.3822 | - | - | - |
|
| 425 |
+
| 0.5093 | 5300 | 0.3467 | - | - | - |
|
| 426 |
+
| 0.5189 | 5400 | 0.3647 | - | - | - |
|
| 427 |
+
| 0.5285 | 5500 | 0.3563 | - | - | - |
|
| 428 |
+
| 0.5381 | 5600 | 0.3583 | - | - | - |
|
| 429 |
+
| 0.5477 | 5700 | 0.3159 | - | - | - |
|
| 430 |
+
| 0.5573 | 5800 | 0.3817 | - | - | - |
|
| 431 |
+
| 0.5669 | 5900 | 0.3892 | - | - | - |
|
| 432 |
+
| 0.5765 | 6000 | 0.351 | - | - | - |
|
| 433 |
+
| 0.5861 | 6100 | 0.3505 | - | - | - |
|
| 434 |
+
| 0.5958 | 6200 | 0.3735 | - | - | - |
|
| 435 |
+
| 0.6054 | 6300 | 0.3479 | - | - | - |
|
| 436 |
+
| 0.6150 | 6400 | 0.3608 | - | - | - |
|
| 437 |
+
| 0.6246 | 6500 | 0.3634 | - | - | - |
|
| 438 |
+
| 0.6342 | 6600 | 0.3787 | - | - | - |
|
| 439 |
+
| 0.6438 | 6700 | 0.3263 | - | - | - |
|
| 440 |
+
| 0.6534 | 6800 | 0.3181 | - | - | - |
|
| 441 |
+
| 0.6630 | 6900 | 0.3163 | - | - | - |
|
| 442 |
+
| 0.6726 | 7000 | 0.3141 | - | - | - |
|
| 443 |
+
| 0.6822 | 7100 | 0.3369 | - | - | - |
|
| 444 |
+
| 0.6918 | 7200 | 0.3503 | - | - | - |
|
| 445 |
+
| 0.7015 | 7300 | 0.3438 | - | - | - |
|
| 446 |
+
| 0.7111 | 7400 | 0.3219 | - | - | - |
|
| 447 |
+
| 0.7207 | 7500 | 0.3324 | - | - | - |
|
| 448 |
+
| 0.7303 | 7600 | 0.3313 | - | - | - |
|
| 449 |
+
| 0.7399 | 7700 | 0.3364 | - | - | - |
|
| 450 |
+
| 0.7495 | 7800 | 0.3103 | - | - | - |
|
| 451 |
+
| 0.7591 | 7900 | 0.278 | - | - | - |
|
| 452 |
+
| 0.7687 | 8000 | 0.2997 | - | - | - |
|
| 453 |
+
| 0.7783 | 8100 | 0.3233 | - | - | - |
|
| 454 |
+
| 0.7879 | 8200 | 0.3364 | - | - | - |
|
| 455 |
+
| 0.7975 | 8300 | 0.3326 | - | - | - |
|
| 456 |
+
| 0.8071 | 8400 | 0.3192 | - | - | - |
|
| 457 |
+
| 0.8168 | 8500 | 0.3483 | - | - | - |
|
| 458 |
+
| 0.8264 | 8600 | 0.2998 | - | - | - |
|
| 459 |
+
| 0.8360 | 8700 | 0.3139 | - | - | - |
|
| 460 |
+
| 0.8456 | 8800 | 0.2926 | - | - | - |
|
| 461 |
+
| 0.8552 | 8900 | 0.3425 | - | - | - |
|
| 462 |
+
| 0.8648 | 9000 | 0.2992 | - | - | - |
|
| 463 |
+
| 0.8744 | 9100 | 0.3056 | - | - | - |
|
| 464 |
+
| 0.8840 | 9200 | 0.3004 | - | - | - |
|
| 465 |
+
| 0.8936 | 9300 | 0.3005 | - | - | - |
|
| 466 |
+
| 0.9032 | 9400 | 0.3352 | - | - | - |
|
| 467 |
+
| 0.9128 | 9500 | 0.2853 | - | - | - |
|
| 468 |
+
| 0.9225 | 9600 | 0.3024 | - | - | - |
|
| 469 |
+
| 0.9321 | 9700 | 0.3329 | - | - | - |
|
| 470 |
+
| 0.9417 | 9800 | 0.2883 | - | - | - |
|
| 471 |
+
| 0.9513 | 9900 | 0.2739 | - | - | - |
|
| 472 |
+
| 0.9609 | 10000 | 0.3024 | 0.2919 | 0.9200 | - |
|
| 473 |
+
| 0.9705 | 10100 | 0.3177 | - | - | - |
|
| 474 |
+
| 0.9801 | 10200 | 0.3232 | - | - | - |
|
| 475 |
+
| 0.9897 | 10300 | 0.2829 | - | - | - |
|
| 476 |
+
| 0.9993 | 10400 | 0.3013 | - | - | - |
|
| 477 |
+
| -1 | -1 | - | - | - | 0.9178 |
|
| 478 |
+
|
| 479 |
+
</details>
|
| 480 |
+
|
| 481 |
+
### Framework Versions
|
| 482 |
+
- Python: 3.12.11
|
| 483 |
+
- Sentence Transformers: 4.0.2
|
| 484 |
+
- Transformers: 4.52.4
|
| 485 |
+
- PyTorch: 2.7.1+cu126
|
| 486 |
+
- Accelerate: 1.7.0
|
| 487 |
+
- Datasets: 3.6.0
|
| 488 |
+
- Tokenizers: 0.21.1
|
| 489 |
+
|
| 490 |
+
## Citation
|
| 491 |
+
|
| 492 |
+
### BibTeX
|
| 493 |
+
|
| 494 |
+
#### Sentence Transformers
|
| 495 |
+
```bibtex
|
| 496 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 497 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 498 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 499 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 500 |
+
month = "11",
|
| 501 |
+
year = "2019",
|
| 502 |
+
publisher = "Association for Computational Linguistics",
|
| 503 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 504 |
+
}
|
| 505 |
+
```
|
| 506 |
+
|
| 507 |
+
#### MultipleNegativesRankingLoss
|
| 508 |
+
```bibtex
|
| 509 |
+
@misc{henderson2017efficient,
|
| 510 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
| 511 |
+
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
|
| 512 |
+
year={2017},
|
| 513 |
+
eprint={1705.00652},
|
| 514 |
+
archivePrefix={arXiv},
|
| 515 |
+
primaryClass={cs.CL}
|
| 516 |
+
}
|
| 517 |
+
```
|
| 518 |
+
|
| 519 |
+
<!--
|
| 520 |
+
## Glossary
|
| 521 |
+
|
| 522 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 523 |
+
-->
|
| 524 |
+
|
| 525 |
+
<!--
|
| 526 |
+
## Model Card Authors
|
| 527 |
+
|
| 528 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 529 |
+
-->
|
| 530 |
+
|
| 531 |
+
<!--
|
| 532 |
+
## Model Card Contact
|
| 533 |
+
|
| 534 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 535 |
+
-->
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# 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>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\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" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3Model"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 18,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.52.4",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151669
|
| 30 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"prompts": {
|
| 3 |
+
"query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:",
|
| 4 |
+
"document": ""
|
| 5 |
+
},
|
| 6 |
+
"default_prompt_name": null,
|
| 7 |
+
"similarity_fn_name": "cosine",
|
| 8 |
+
"model_type": "SentenceTransformer",
|
| 9 |
+
"__version__": {
|
| 10 |
+
"sentence_transformers": "4.0.2",
|
| 11 |
+
"transformers": "4.52.4",
|
| 12 |
+
"pytorch": "2.7.1+cu126"
|
| 13 |
+
}
|
| 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:c86d725ae3e8abe58ba6c8e21e98becff9f5a4f73c6f8b55619cdf9b7681f354
|
| 3 |
+
size 1753889768
|
modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.models.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
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 sha256:7a5b90ffcbd8fe896c9ee9fe56c5dd84116f876ad5cdbe0d1424fbe150f41ca6
|
| 3 |
+
size 11423970
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"max_length": 512,
|
| 235 |
+
"model_max_length": 512,
|
| 236 |
+
"pad_to_multiple_of": null,
|
| 237 |
+
"pad_token": "<|endoftext|>",
|
| 238 |
+
"pad_token_type_id": 0,
|
| 239 |
+
"padding_side": "left",
|
| 240 |
+
"split_special_tokens": false,
|
| 241 |
+
"stride": 0,
|
| 242 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 243 |
+
"truncation_side": "right",
|
| 244 |
+
"truncation_strategy": "longest_first",
|
| 245 |
+
"unk_token": null
|
| 246 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|