Text Ranking
sentence-transformers
Safetensors
qwen3
sentence-similarity
cross-encoder
reranker
feature-extraction
telepix
Instructions to use telepix/PIXIE-Spell-Reranker-Preview-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use telepix/PIXIE-Spell-Reranker-Preview-0.6B with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("telepix/PIXIE-Spell-Reranker-Preview-0.6B") query = "Which planet is known as the Red Planet?" passages = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", "Saturn, famous for its rings, is sometimes mistaken for the Red Planet." ] scores = model.predict([(query, passage) for passage in passages]) print(scores) - Notebooks
- Google Colab
- Kaggle
Initial commit
Browse files- .gitattributes +1 -0
- README.md +611 -3
- added_tokens.json +28 -0
- config.json +71 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -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
|
README.md
CHANGED
|
@@ -1,3 +1,611 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
--
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- sentence-transformers
|
| 4 |
+
- cross-encoder
|
| 5 |
+
- reranker
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- dataset_size:1792739
|
| 8 |
+
- loss:CachedMultipleNegativesRankingLoss
|
| 9 |
+
base_model: tomaarsen/Qwen3-Reranker-0.6B-seq-cls
|
| 10 |
+
pipeline_tag: text-ranking
|
| 11 |
+
library_name: sentence-transformers
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# CrossEncoder based on tomaarsen/Qwen3-Reranker-0.6B-seq-cls
|
| 15 |
+
|
| 16 |
+
This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [tomaarsen/Qwen3-Reranker-0.6B-seq-cls](https://huggingface.co/tomaarsen/Qwen3-Reranker-0.6B-seq-cls) on the json dataset using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
- **Model Type:** Cross Encoder
|
| 22 |
+
- **Base model:** [tomaarsen/Qwen3-Reranker-0.6B-seq-cls](https://huggingface.co/tomaarsen/Qwen3-Reranker-0.6B-seq-cls) <!-- at revision 6a5829f5079c66e78d911e06fe21931cc00232f7 -->
|
| 23 |
+
- **Maximum Sequence Length:** 40960 tokens
|
| 24 |
+
- **Number of Output Labels:** 1 label
|
| 25 |
+
- **Training Dataset:**
|
| 26 |
+
- json
|
| 27 |
+
<!-- - **Language:** Unknown -->
|
| 28 |
+
<!-- - **License:** Unknown -->
|
| 29 |
+
|
| 30 |
+
### Model Sources
|
| 31 |
+
|
| 32 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 33 |
+
- **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html)
|
| 34 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 35 |
+
- **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder)
|
| 36 |
+
|
| 37 |
+
## Usage
|
| 38 |
+
|
| 39 |
+
### Direct Usage (Sentence Transformers)
|
| 40 |
+
|
| 41 |
+
First install the Sentence Transformers library:
|
| 42 |
+
|
| 43 |
+
```bash
|
| 44 |
+
pip install -U sentence-transformers
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
Then you can load this model and run inference.
|
| 48 |
+
```python
|
| 49 |
+
from sentence_transformers import CrossEncoder
|
| 50 |
+
|
| 51 |
+
# Download from the 🤗 Hub
|
| 52 |
+
model = CrossEncoder("cross_encoder_model_id")
|
| 53 |
+
# Get scores for pairs of texts
|
| 54 |
+
pairs = [
|
| 55 |
+
['<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>\n<|im_start|>user\n<Instruct>: Given a web search query, retrieve relevant passages that answer the query\n<Query>: ATP란?\n', '<Document>: 아데노신 삼인산 아데노신 삼인산(, ATP)은 생명체의 주된 에너지원이다.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n'],
|
| 56 |
+
['<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>\n<|im_start|>user\n<Instruct>: Given a web search query, retrieve relevant passages that answer the query\n<Query>: 난촨구와 둥촨구는 어느 나라에 위치해 있습니까?\n', '<Document>: 난촨구(南川区)는 중국 충칭의 구이자 이전의 현이다.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n'],
|
| 57 |
+
['<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>\n<|im_start|>user\n<Instruct>: Given a web search query, retrieve relevant passages that answer the query\n<Query>: 그저우와 헤이룽장성 동닝은 어떤 나라와 접경하고 있습니까?\n', '<Document>: 허주(贺州)는 중화인민공화국 광시 좡족 자치구 북동부에 위치한 지급시이다.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n'],
|
| 58 |
+
['<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>\n<|im_start|>user\n<Instruct>: Given a web search query, retrieve relevant passages that answer the query\n<Query>: 가짜대나무(Pseudosasa)와 별꽃(Cerastium)은 모두 자생 식물과 관련이 있습니까?\n', '<Document>: 가짜사사(Pseudosasa)는 풀과에 속하는 동아시아 대나무의 속입니다.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n'],
|
| 59 |
+
['<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>\n<|im_start|>user\n<Instruct>: Given a web search query, retrieve relevant passages that answer the query\n<Query>: 샤허(Shahhe), 허베이(河北)와 조청(邹城)은 모두 현급 도시인가요?\n', '<Document>: 샤허(Shahe)는 중국 허베이성의 남부에 위치한 싱타이(Xingtai) 지구의 군급 도시입니다.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n'],
|
| 60 |
+
]
|
| 61 |
+
scores = model.predict(pairs)
|
| 62 |
+
print(scores.shape)
|
| 63 |
+
# (5,)
|
| 64 |
+
|
| 65 |
+
# Or rank different texts based on similarity to a single text
|
| 66 |
+
ranks = model.rank(
|
| 67 |
+
'<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>\n<|im_start|>user\n<Instruct>: Given a web search query, retrieve relevant passages that answer the query\n<Query>: ATP란?\n',
|
| 68 |
+
[
|
| 69 |
+
'<Document>: 아데노신 삼인산 아데노신 삼인산(, ATP)은 생명체의 주된 에너지원이다.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n',
|
| 70 |
+
'<Document>: 난촨구(南川区)는 중국 충칭의 구이자 이전의 현이다.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n',
|
| 71 |
+
'<Document>: 허주(贺州)는 중화인민공화국 광시 좡족 자치구 북동부에 위치한 지급시이다.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n',
|
| 72 |
+
'<Document>: 가짜사사(Pseudosasa)는 풀과에 속하는 동아시아 대나무의 속입니다.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n',
|
| 73 |
+
'<Document>: 샤허(Shahe)는 중국 허베이성의 남부에 위치한 싱타이(Xingtai) 지구의 군급 도시입니다.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n',
|
| 74 |
+
]
|
| 75 |
+
)
|
| 76 |
+
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
|
| 77 |
+
```
|
| 78 |
+
|
| 79 |
+
<!--
|
| 80 |
+
### Direct Usage (Transformers)
|
| 81 |
+
|
| 82 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 83 |
+
|
| 84 |
+
</details>
|
| 85 |
+
-->
|
| 86 |
+
|
| 87 |
+
<!--
|
| 88 |
+
### Downstream Usage (Sentence Transformers)
|
| 89 |
+
|
| 90 |
+
You can finetune this model on your own dataset.
|
| 91 |
+
|
| 92 |
+
<details><summary>Click to expand</summary>
|
| 93 |
+
|
| 94 |
+
</details>
|
| 95 |
+
-->
|
| 96 |
+
|
| 97 |
+
<!--
|
| 98 |
+
### Out-of-Scope Use
|
| 99 |
+
|
| 100 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 101 |
+
-->
|
| 102 |
+
|
| 103 |
+
<!--
|
| 104 |
+
## Bias, Risks and Limitations
|
| 105 |
+
|
| 106 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 107 |
+
-->
|
| 108 |
+
|
| 109 |
+
<!--
|
| 110 |
+
### Recommendations
|
| 111 |
+
|
| 112 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 113 |
+
-->
|
| 114 |
+
|
| 115 |
+
## Training Details
|
| 116 |
+
|
| 117 |
+
### Training Dataset
|
| 118 |
+
|
| 119 |
+
#### json
|
| 120 |
+
|
| 121 |
+
* Dataset: json
|
| 122 |
+
* Size: 1,792,739 training samples
|
| 123 |
+
* Columns: <code>query</code>, <code>positive</code>, <code>negative_1</code>, <code>negative_2</code>, and <code>negative_3</code>
|
| 124 |
+
* Approximate statistics based on the first 1000 samples:
|
| 125 |
+
| | query | positive | negative_1 | negative_2 | negative_3 |
|
| 126 |
+
|:--------|:--------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|
|
| 127 |
+
| type | string | string | string | string | string |
|
| 128 |
+
| details | <ul><li>min: 289 characters</li><li>mean: 317.46 characters</li><li>max: 406 characters</li></ul> | <ul><li>min: 90 characters</li><li>mean: 154.19 characters</li><li>max: 184 characters</li></ul> | <ul><li>min: 72 characters</li><li>mean: 149.13 characters</li><li>max: 184 characters</li></ul> | <ul><li>min: 79 characters</li><li>mean: 148.5 characters</li><li>max: 184 characters</li></ul> | <ul><li>min: 70 characters</li><li>mean: 149.09 characters</li><li>max: 184 characters</li></ul> |
|
| 129 |
+
* Samples:
|
| 130 |
+
| query | positive | negative_1 | negative_2 | negative_3 |
|
| 131 |
+
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 132 |
+
| <code><|im_start|>system<br>Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|><br><|im_start|>user<br><Instruct>: Given a web search query, retrieve relevant passages that answer the query<br><Query>: ATP란?<br></code> | <code><Document>: 아데노신 삼인산 아데노신 삼인산(, ATP)은 생명체의 주된 에너지원이다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> | <code><Document>: ATP ATP는 다음 뜻의 약자이다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> | <code><Document>: 해당 실제로 ADP는 ADPMg로, ATP는 ATPMg로 존재한다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> | <code><Document>: ATE ATE는 다음을 가리킨다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> |
|
| 133 |
+
| <code><|im_start|>system<br>Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|><br><|im_start|>user<br><Instruct>: Given a web search query, retrieve relevant passages that answer the query<br><Query>: 난촨구와 둥촨구는 어느 나라에 위치해 있습니까?<br></code> | <code><Document>: 난촨구(南川区)는 중국 충칭의 구이자 이전의 현이다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> | <code><Document>: 남풍현(南丰县)은 중국 장시성(江西省) 푸저우(福州)에 위치한 군이다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> | <code><Document>: 도교, 광둥 도교(道滘)는 중국 남부 광둥성 동관 시의 관할 하에 있는 도시입니다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> | <code><Document>: 동포구 동포구는 중국 쓰촨성의 구역입니다. 이곳은 메이산시의 관할 하에 있습니다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> |
|
| 134 |
+
| <code><|im_start|>system<br>Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|><br><|im_start|>user<br><Instruct>: Given a web search query, retrieve relevant passages that answer the query<br><Query>: 그저우와 헤이룽장성 동닝은 어떤 나라와 접경하고 있습니까?<br></code> | <code><Document>: 허주(贺州)는 중화인민공화국 광시 좡족 자치구 북동부에 위치한 지급시이다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> | <code><Document>: 지관구(지관구)는 중국 인민공화국 헤이룽장성 지시시의 구이자 시청 소재지입니다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> | <code><Document>: 헤동 가도(河东街道)는 중국 광시(广西) 리우저우(柳州) 청중 구(城中区)의 가도입니다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> | <code><Document>: 화닝현 (华宁县; 병음: Huáníng Xiàn)은 중국 윈난성 유시시에 위치해 있습니다.<|im_end|><br><|im_start|>assistant<br><think><br><br></think><br><br></code> |
|
| 135 |
+
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
|
| 136 |
+
```json
|
| 137 |
+
{
|
| 138 |
+
"scale": 15,
|
| 139 |
+
"num_negatives": 61,
|
| 140 |
+
"activation_fn": "torch.nn.modules.activation.Sigmoid",
|
| 141 |
+
"mini_batch_size": 4
|
| 142 |
+
}
|
| 143 |
+
```
|
| 144 |
+
|
| 145 |
+
### Training Hyperparameters
|
| 146 |
+
#### Non-Default Hyperparameters
|
| 147 |
+
|
| 148 |
+
- `per_device_train_batch_size`: 1024
|
| 149 |
+
- `per_device_eval_batch_size`: 32
|
| 150 |
+
- `learning_rate`: 2e-05
|
| 151 |
+
- `num_train_epochs`: 1
|
| 152 |
+
- `warmup_ratio`: 0.05
|
| 153 |
+
- `bf16`: True
|
| 154 |
+
- `ddp_find_unused_parameters`: True
|
| 155 |
+
- `ddp_timeout`: 7200
|
| 156 |
+
- `batch_sampler`: no_duplicates
|
| 157 |
+
|
| 158 |
+
#### All Hyperparameters
|
| 159 |
+
<details><summary>Click to expand</summary>
|
| 160 |
+
|
| 161 |
+
- `overwrite_output_dir`: False
|
| 162 |
+
- `do_predict`: False
|
| 163 |
+
- `eval_strategy`: no
|
| 164 |
+
- `prediction_loss_only`: True
|
| 165 |
+
- `per_device_train_batch_size`: 1024
|
| 166 |
+
- `per_device_eval_batch_size`: 32
|
| 167 |
+
- `per_gpu_train_batch_size`: None
|
| 168 |
+
- `per_gpu_eval_batch_size`: None
|
| 169 |
+
- `gradient_accumulation_steps`: 1
|
| 170 |
+
- `eval_accumulation_steps`: None
|
| 171 |
+
- `torch_empty_cache_steps`: None
|
| 172 |
+
- `learning_rate`: 2e-05
|
| 173 |
+
- `weight_decay`: 0.0
|
| 174 |
+
- `adam_beta1`: 0.9
|
| 175 |
+
- `adam_beta2`: 0.999
|
| 176 |
+
- `adam_epsilon`: 1e-08
|
| 177 |
+
- `max_grad_norm`: 1.0
|
| 178 |
+
- `num_train_epochs`: 1
|
| 179 |
+
- `max_steps`: -1
|
| 180 |
+
- `lr_scheduler_type`: linear
|
| 181 |
+
- `lr_scheduler_kwargs`: {}
|
| 182 |
+
- `warmup_ratio`: 0.05
|
| 183 |
+
- `warmup_steps`: 0
|
| 184 |
+
- `log_level`: passive
|
| 185 |
+
- `log_level_replica`: warning
|
| 186 |
+
- `log_on_each_node`: True
|
| 187 |
+
- `logging_nan_inf_filter`: True
|
| 188 |
+
- `save_safetensors`: True
|
| 189 |
+
- `save_on_each_node`: False
|
| 190 |
+
- `save_only_model`: False
|
| 191 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 192 |
+
- `no_cuda`: False
|
| 193 |
+
- `use_cpu`: False
|
| 194 |
+
- `use_mps_device`: False
|
| 195 |
+
- `seed`: 42
|
| 196 |
+
- `data_seed`: None
|
| 197 |
+
- `jit_mode_eval`: False
|
| 198 |
+
- `use_ipex`: False
|
| 199 |
+
- `bf16`: True
|
| 200 |
+
- `fp16`: False
|
| 201 |
+
- `fp16_opt_level`: O1
|
| 202 |
+
- `half_precision_backend`: auto
|
| 203 |
+
- `bf16_full_eval`: False
|
| 204 |
+
- `fp16_full_eval`: False
|
| 205 |
+
- `tf32`: None
|
| 206 |
+
- `local_rank`: 0
|
| 207 |
+
- `ddp_backend`: None
|
| 208 |
+
- `tpu_num_cores`: None
|
| 209 |
+
- `tpu_metrics_debug`: False
|
| 210 |
+
- `debug`: []
|
| 211 |
+
- `dataloader_drop_last`: True
|
| 212 |
+
- `dataloader_num_workers`: 0
|
| 213 |
+
- `dataloader_prefetch_factor`: None
|
| 214 |
+
- `past_index`: -1
|
| 215 |
+
- `disable_tqdm`: False
|
| 216 |
+
- `remove_unused_columns`: True
|
| 217 |
+
- `label_names`: None
|
| 218 |
+
- `load_best_model_at_end`: False
|
| 219 |
+
- `ignore_data_skip`: False
|
| 220 |
+
- `fsdp`: []
|
| 221 |
+
- `fsdp_min_num_params`: 0
|
| 222 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 223 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 224 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 225 |
+
- `deepspeed`: None
|
| 226 |
+
- `label_smoothing_factor`: 0.0
|
| 227 |
+
- `optim`: adamw_torch
|
| 228 |
+
- `optim_args`: None
|
| 229 |
+
- `adafactor`: False
|
| 230 |
+
- `group_by_length`: False
|
| 231 |
+
- `length_column_name`: length
|
| 232 |
+
- `ddp_find_unused_parameters`: True
|
| 233 |
+
- `ddp_bucket_cap_mb`: None
|
| 234 |
+
- `ddp_broadcast_buffers`: False
|
| 235 |
+
- `dataloader_pin_memory`: True
|
| 236 |
+
- `dataloader_persistent_workers`: False
|
| 237 |
+
- `skip_memory_metrics`: True
|
| 238 |
+
- `use_legacy_prediction_loop`: False
|
| 239 |
+
- `push_to_hub`: False
|
| 240 |
+
- `resume_from_checkpoint`: None
|
| 241 |
+
- `hub_model_id`: None
|
| 242 |
+
- `hub_strategy`: every_save
|
| 243 |
+
- `hub_private_repo`: None
|
| 244 |
+
- `hub_always_push`: False
|
| 245 |
+
- `hub_revision`: None
|
| 246 |
+
- `gradient_checkpointing`: False
|
| 247 |
+
- `gradient_checkpointing_kwargs`: None
|
| 248 |
+
- `include_inputs_for_metrics`: False
|
| 249 |
+
- `include_for_metrics`: []
|
| 250 |
+
- `eval_do_concat_batches`: True
|
| 251 |
+
- `fp16_backend`: auto
|
| 252 |
+
- `push_to_hub_model_id`: None
|
| 253 |
+
- `push_to_hub_organization`: None
|
| 254 |
+
- `mp_parameters`:
|
| 255 |
+
- `auto_find_batch_size`: False
|
| 256 |
+
- `full_determinism`: False
|
| 257 |
+
- `torchdynamo`: None
|
| 258 |
+
- `ray_scope`: last
|
| 259 |
+
- `ddp_timeout`: 7200
|
| 260 |
+
- `torch_compile`: False
|
| 261 |
+
- `torch_compile_backend`: None
|
| 262 |
+
- `torch_compile_mode`: None
|
| 263 |
+
- `include_tokens_per_second`: False
|
| 264 |
+
- `include_num_input_tokens_seen`: False
|
| 265 |
+
- `neftune_noise_alpha`: None
|
| 266 |
+
- `optim_target_modules`: None
|
| 267 |
+
- `batch_eval_metrics`: False
|
| 268 |
+
- `eval_on_start`: False
|
| 269 |
+
- `use_liger_kernel`: False
|
| 270 |
+
- `liger_kernel_config`: None
|
| 271 |
+
- `eval_use_gather_object`: False
|
| 272 |
+
- `average_tokens_across_devices`: False
|
| 273 |
+
- `prompts`: None
|
| 274 |
+
- `batch_sampler`: no_duplicates
|
| 275 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 276 |
+
- `router_mapping`: {}
|
| 277 |
+
- `learning_rate_mapping`: {}
|
| 278 |
+
|
| 279 |
+
</details>
|
| 280 |
+
|
| 281 |
+
### Training Logs
|
| 282 |
+
<details><summary>Click to expand</summary>
|
| 283 |
+
|
| 284 |
+
| Epoch | Step | Training Loss |
|
| 285 |
+
|:------:|:----:|:-------------:|
|
| 286 |
+
| 0.0034 | 1 | 1.2714 |
|
| 287 |
+
| 0.0069 | 2 | 1.3902 |
|
| 288 |
+
| 0.0103 | 3 | 1.3308 |
|
| 289 |
+
| 0.0137 | 4 | 1.2726 |
|
| 290 |
+
| 0.0172 | 5 | 1.2519 |
|
| 291 |
+
| 0.0206 | 6 | 1.1254 |
|
| 292 |
+
| 0.0241 | 7 | 0.9001 |
|
| 293 |
+
| 0.0275 | 8 | 0.7529 |
|
| 294 |
+
| 0.0309 | 9 | 0.9942 |
|
| 295 |
+
| 0.0344 | 10 | 0.8769 |
|
| 296 |
+
| 0.0378 | 11 | 0.6895 |
|
| 297 |
+
| 0.0412 | 12 | 0.6813 |
|
| 298 |
+
| 0.0447 | 13 | 0.6841 |
|
| 299 |
+
| 0.0481 | 14 | 0.6025 |
|
| 300 |
+
| 0.0515 | 15 | 0.619 |
|
| 301 |
+
| 0.0550 | 16 | 0.6005 |
|
| 302 |
+
| 0.0584 | 17 | 0.5917 |
|
| 303 |
+
| 0.0619 | 18 | 0.5658 |
|
| 304 |
+
| 0.0653 | 19 | 0.5571 |
|
| 305 |
+
| 0.0687 | 20 | 0.5411 |
|
| 306 |
+
| 0.0722 | 21 | 0.5374 |
|
| 307 |
+
| 0.0756 | 22 | 0.5304 |
|
| 308 |
+
| 0.0790 | 23 | 0.5103 |
|
| 309 |
+
| 0.0825 | 24 | 0.5184 |
|
| 310 |
+
| 0.0859 | 25 | 0.5036 |
|
| 311 |
+
| 0.0893 | 26 | 0.5213 |
|
| 312 |
+
| 0.0928 | 27 | 0.5399 |
|
| 313 |
+
| 0.0962 | 28 | 0.5414 |
|
| 314 |
+
| 0.0997 | 29 | 0.5177 |
|
| 315 |
+
| 0.1031 | 30 | 0.5248 |
|
| 316 |
+
| 0.1065 | 31 | 0.5196 |
|
| 317 |
+
| 0.1100 | 32 | 0.499 |
|
| 318 |
+
| 0.1134 | 33 | 0.514 |
|
| 319 |
+
| 0.1168 | 34 | 0.5154 |
|
| 320 |
+
| 0.1203 | 35 | 0.5114 |
|
| 321 |
+
| 0.1237 | 36 | 0.508 |
|
| 322 |
+
| 0.1271 | 37 | 0.5117 |
|
| 323 |
+
| 0.1306 | 38 | 0.495 |
|
| 324 |
+
| 0.1340 | 39 | 0.5304 |
|
| 325 |
+
| 0.1375 | 40 | 0.4956 |
|
| 326 |
+
| 0.1409 | 41 | 0.5274 |
|
| 327 |
+
| 0.1443 | 42 | 0.5181 |
|
| 328 |
+
| 0.1478 | 43 | 0.5103 |
|
| 329 |
+
| 0.1512 | 44 | 0.5116 |
|
| 330 |
+
| 0.1546 | 45 | 0.499 |
|
| 331 |
+
| 0.1581 | 46 | 0.5072 |
|
| 332 |
+
| 0.1615 | 47 | 0.5044 |
|
| 333 |
+
| 0.1649 | 48 | 0.5071 |
|
| 334 |
+
| 0.1684 | 49 | 0.5129 |
|
| 335 |
+
| 0.1718 | 50 | 0.5095 |
|
| 336 |
+
| 0.1753 | 51 | 0.5174 |
|
| 337 |
+
| 0.1787 | 52 | 0.4748 |
|
| 338 |
+
| 0.1821 | 53 | 0.4507 |
|
| 339 |
+
| 0.1856 | 54 | 0.4927 |
|
| 340 |
+
| 0.1890 | 55 | 0.452 |
|
| 341 |
+
| 0.1924 | 56 | 0.4999 |
|
| 342 |
+
| 0.1959 | 57 | 0.4744 |
|
| 343 |
+
| 0.1993 | 58 | 0.4486 |
|
| 344 |
+
| 0.2027 | 59 | 0.4725 |
|
| 345 |
+
| 0.2062 | 60 | 0.4723 |
|
| 346 |
+
| 0.2096 | 61 | 0.4747 |
|
| 347 |
+
| 0.2131 | 62 | 0.4317 |
|
| 348 |
+
| 0.2165 | 63 | 0.4668 |
|
| 349 |
+
| 0.2199 | 64 | 0.453 |
|
| 350 |
+
| 0.2234 | 65 | 0.4457 |
|
| 351 |
+
| 0.2268 | 66 | 0.4179 |
|
| 352 |
+
| 0.2302 | 67 | 0.4124 |
|
| 353 |
+
| 0.2337 | 68 | 0.4454 |
|
| 354 |
+
| 0.2371 | 69 | 0.4222 |
|
| 355 |
+
| 0.2405 | 70 | 0.4151 |
|
| 356 |
+
| 0.2440 | 71 | 0.4172 |
|
| 357 |
+
| 0.2474 | 72 | 0.422 |
|
| 358 |
+
| 0.2509 | 73 | 0.4088 |
|
| 359 |
+
| 0.2543 | 74 | 0.4107 |
|
| 360 |
+
| 0.2577 | 75 | 0.3977 |
|
| 361 |
+
| 0.2612 | 76 | 0.4141 |
|
| 362 |
+
| 0.2646 | 77 | 0.3991 |
|
| 363 |
+
| 0.2680 | 78 | 0.3955 |
|
| 364 |
+
| 0.2715 | 79 | 0.3864 |
|
| 365 |
+
| 0.2749 | 80 | 0.4147 |
|
| 366 |
+
| 0.2784 | 81 | 0.4084 |
|
| 367 |
+
| 0.2818 | 82 | 0.4139 |
|
| 368 |
+
| 0.2852 | 83 | 0.3999 |
|
| 369 |
+
| 0.2887 | 84 | 0.4305 |
|
| 370 |
+
| 0.2921 | 85 | 0.4188 |
|
| 371 |
+
| 0.2955 | 86 | 0.4171 |
|
| 372 |
+
| 0.2990 | 87 | 0.407 |
|
| 373 |
+
| 0.3024 | 88 | 0.3871 |
|
| 374 |
+
| 0.3058 | 89 | 0.389 |
|
| 375 |
+
| 0.3093 | 90 | 0.3813 |
|
| 376 |
+
| 0.3127 | 91 | 0.3814 |
|
| 377 |
+
| 0.3162 | 92 | 0.3732 |
|
| 378 |
+
| 0.3196 | 93 | 0.3899 |
|
| 379 |
+
| 0.3230 | 94 | 0.3655 |
|
| 380 |
+
| 0.3265 | 95 | 0.3638 |
|
| 381 |
+
| 0.3299 | 96 | 0.3784 |
|
| 382 |
+
| 0.3333 | 97 | 0.3729 |
|
| 383 |
+
| 0.3368 | 98 | 0.3665 |
|
| 384 |
+
| 0.3402 | 99 | 0.3579 |
|
| 385 |
+
| 0.3436 | 100 | 0.3414 |
|
| 386 |
+
| 0.3471 | 101 | 0.3304 |
|
| 387 |
+
| 0.3505 | 102 | 0.347 |
|
| 388 |
+
| 0.3540 | 103 | 0.3076 |
|
| 389 |
+
| 0.3574 | 104 | 0.3111 |
|
| 390 |
+
| 0.3608 | 105 | 0.3121 |
|
| 391 |
+
| 0.3643 | 106 | 0.3272 |
|
| 392 |
+
| 0.3677 | 107 | 0.3108 |
|
| 393 |
+
| 0.3711 | 108 | 0.3092 |
|
| 394 |
+
| 0.3746 | 109 | 0.2951 |
|
| 395 |
+
| 0.3780 | 110 | 0.3195 |
|
| 396 |
+
| 0.3814 | 111 | 0.2915 |
|
| 397 |
+
| 0.3849 | 112 | 0.2855 |
|
| 398 |
+
| 0.3883 | 113 | 0.2904 |
|
| 399 |
+
| 0.3918 | 114 | 0.2873 |
|
| 400 |
+
| 0.3952 | 115 | 0.273 |
|
| 401 |
+
| 0.3986 | 116 | 0.2779 |
|
| 402 |
+
| 0.4021 | 117 | 0.2939 |
|
| 403 |
+
| 0.4055 | 118 | 0.276 |
|
| 404 |
+
| 0.4089 | 119 | 0.2535 |
|
| 405 |
+
| 0.4124 | 120 | 0.2774 |
|
| 406 |
+
| 0.4158 | 121 | 0.2597 |
|
| 407 |
+
| 0.4192 | 122 | 0.2541 |
|
| 408 |
+
| 0.4227 | 123 | 0.2587 |
|
| 409 |
+
| 0.4261 | 124 | 0.27 |
|
| 410 |
+
| 0.4296 | 125 | 0.2724 |
|
| 411 |
+
| 0.4330 | 126 | 0.2446 |
|
| 412 |
+
| 0.4364 | 127 | 0.2747 |
|
| 413 |
+
| 0.4399 | 128 | 0.268 |
|
| 414 |
+
| 0.4433 | 129 | 0.2585 |
|
| 415 |
+
| 0.4467 | 130 | 0.2652 |
|
| 416 |
+
| 0.4502 | 131 | 0.2685 |
|
| 417 |
+
| 0.4536 | 132 | 0.2565 |
|
| 418 |
+
| 0.4570 | 133 | 0.2503 |
|
| 419 |
+
| 0.4605 | 134 | 0.2634 |
|
| 420 |
+
| 0.4639 | 135 | 0.2501 |
|
| 421 |
+
| 0.4674 | 136 | 0.2479 |
|
| 422 |
+
| 0.4708 | 137 | 0.2628 |
|
| 423 |
+
| 0.4742 | 138 | 0.2505 |
|
| 424 |
+
| 0.4777 | 139 | 0.2468 |
|
| 425 |
+
| 0.4811 | 140 | 0.2365 |
|
| 426 |
+
| 0.4845 | 141 | 0.2496 |
|
| 427 |
+
| 0.4880 | 142 | 0.248 |
|
| 428 |
+
| 0.4914 | 143 | 0.2604 |
|
| 429 |
+
| 0.4948 | 144 | 0.2477 |
|
| 430 |
+
| 0.4983 | 145 | 0.259 |
|
| 431 |
+
| 0.5017 | 146 | 0.2556 |
|
| 432 |
+
| 0.5052 | 147 | 0.2618 |
|
| 433 |
+
| 0.5086 | 148 | 0.2583 |
|
| 434 |
+
| 0.5120 | 149 | 0.2588 |
|
| 435 |
+
| 0.5155 | 150 | 0.2468 |
|
| 436 |
+
| 0.5189 | 151 | 0.2437 |
|
| 437 |
+
| 0.5223 | 152 | 0.2595 |
|
| 438 |
+
| 0.5258 | 153 | 0.2647 |
|
| 439 |
+
| 0.5292 | 154 | 0.2699 |
|
| 440 |
+
| 0.5326 | 155 | 0.2529 |
|
| 441 |
+
| 0.5361 | 156 | 0.2339 |
|
| 442 |
+
| 0.5395 | 157 | 0.2557 |
|
| 443 |
+
| 0.5430 | 158 | 0.2402 |
|
| 444 |
+
| 0.5464 | 159 | 0.2583 |
|
| 445 |
+
| 0.5498 | 160 | 0.2688 |
|
| 446 |
+
| 0.5533 | 161 | 0.2567 |
|
| 447 |
+
| 0.5567 | 162 | 0.2702 |
|
| 448 |
+
| 0.5601 | 163 | 0.2669 |
|
| 449 |
+
| 0.5636 | 164 | 0.2699 |
|
| 450 |
+
| 0.5670 | 165 | 0.2561 |
|
| 451 |
+
| 0.5704 | 166 | 0.2406 |
|
| 452 |
+
| 0.5739 | 167 | 0.2438 |
|
| 453 |
+
| 0.5773 | 168 | 0.2523 |
|
| 454 |
+
| 0.5808 | 169 | 0.2535 |
|
| 455 |
+
| 0.5842 | 170 | 0.2533 |
|
| 456 |
+
| 0.5876 | 171 | 0.2643 |
|
| 457 |
+
| 0.5911 | 172 | 0.2684 |
|
| 458 |
+
| 0.5945 | 173 | 0.2503 |
|
| 459 |
+
| 0.5979 | 174 | 0.2735 |
|
| 460 |
+
| 0.6014 | 175 | 0.2612 |
|
| 461 |
+
| 0.6048 | 176 | 0.2721 |
|
| 462 |
+
| 0.6082 | 177 | 0.2533 |
|
| 463 |
+
| 0.6117 | 178 | 0.2704 |
|
| 464 |
+
| 0.6151 | 179 | 0.2609 |
|
| 465 |
+
| 0.6186 | 180 | 0.2605 |
|
| 466 |
+
| 0.6220 | 181 | 0.2664 |
|
| 467 |
+
| 0.6254 | 182 | 0.2516 |
|
| 468 |
+
| 0.6289 | 183 | 0.2513 |
|
| 469 |
+
| 0.6323 | 184 | 0.2439 |
|
| 470 |
+
| 0.6357 | 185 | 0.258 |
|
| 471 |
+
| 0.6392 | 186 | 0.2534 |
|
| 472 |
+
| 0.6426 | 187 | 0.2638 |
|
| 473 |
+
| 0.6460 | 188 | 0.2535 |
|
| 474 |
+
| 0.6495 | 189 | 0.2481 |
|
| 475 |
+
| 0.6529 | 190 | 0.264 |
|
| 476 |
+
| 0.6564 | 191 | 0.2418 |
|
| 477 |
+
| 0.6598 | 192 | 0.2326 |
|
| 478 |
+
| 0.6632 | 193 | 0.2476 |
|
| 479 |
+
| 0.6667 | 194 | 0.2271 |
|
| 480 |
+
| 0.6701 | 195 | 0.229 |
|
| 481 |
+
| 0.6735 | 196 | 0.2303 |
|
| 482 |
+
| 0.6770 | 197 | 0.2272 |
|
| 483 |
+
| 0.6804 | 198 | 0.2309 |
|
| 484 |
+
| 0.6838 | 199 | 0.2159 |
|
| 485 |
+
| 0.6873 | 200 | 0.2178 |
|
| 486 |
+
| 0.6907 | 201 | 0.208 |
|
| 487 |
+
| 0.6942 | 202 | 0.2257 |
|
| 488 |
+
| 0.6976 | 203 | 0.2032 |
|
| 489 |
+
| 0.7010 | 204 | 0.2047 |
|
| 490 |
+
| 0.7045 | 205 | 0.2223 |
|
| 491 |
+
| 0.7079 | 206 | 0.1964 |
|
| 492 |
+
| 0.7113 | 207 | 0.1846 |
|
| 493 |
+
| 0.7148 | 208 | 0.1899 |
|
| 494 |
+
| 0.7182 | 209 | 0.1986 |
|
| 495 |
+
| 0.7216 | 210 | 0.1898 |
|
| 496 |
+
| 0.7251 | 211 | 0.1999 |
|
| 497 |
+
| 0.7285 | 212 | 0.1754 |
|
| 498 |
+
| 0.7320 | 213 | 0.1912 |
|
| 499 |
+
| 0.7354 | 214 | 0.1702 |
|
| 500 |
+
| 0.7388 | 215 | 0.17 |
|
| 501 |
+
| 0.7423 | 216 | 0.1768 |
|
| 502 |
+
| 0.7457 | 217 | 0.1647 |
|
| 503 |
+
| 0.7491 | 218 | 0.1711 |
|
| 504 |
+
| 0.7526 | 219 | 0.1507 |
|
| 505 |
+
| 0.7560 | 220 | 0.1657 |
|
| 506 |
+
| 0.7595 | 221 | 0.1498 |
|
| 507 |
+
| 0.7629 | 222 | 0.1557 |
|
| 508 |
+
| 0.7663 | 223 | 0.1651 |
|
| 509 |
+
| 0.7698 | 224 | 0.1446 |
|
| 510 |
+
| 0.7732 | 225 | 0.1519 |
|
| 511 |
+
| 0.7766 | 226 | 0.1453 |
|
| 512 |
+
| 0.7801 | 227 | 0.1561 |
|
| 513 |
+
| 0.7835 | 228 | 0.1557 |
|
| 514 |
+
| 0.7869 | 229 | 0.1493 |
|
| 515 |
+
| 0.7904 | 230 | 0.1476 |
|
| 516 |
+
| 0.7938 | 231 | 0.1453 |
|
| 517 |
+
| 0.7973 | 232 | 0.1312 |
|
| 518 |
+
| 0.8007 | 233 | 0.1531 |
|
| 519 |
+
| 0.8041 | 234 | 0.1498 |
|
| 520 |
+
| 0.8076 | 235 | 0.134 |
|
| 521 |
+
| 0.8110 | 236 | 0.1361 |
|
| 522 |
+
| 0.8144 | 237 | 0.1461 |
|
| 523 |
+
| 0.8179 | 238 | 0.148 |
|
| 524 |
+
| 0.8213 | 239 | 0.1465 |
|
| 525 |
+
| 0.8247 | 240 | 0.1452 |
|
| 526 |
+
| 0.8282 | 241 | 0.1399 |
|
| 527 |
+
| 0.8316 | 242 | 0.1291 |
|
| 528 |
+
| 0.8351 | 243 | 0.1354 |
|
| 529 |
+
| 0.8385 | 244 | 0.1719 |
|
| 530 |
+
| 0.8419 | 245 | 0.1555 |
|
| 531 |
+
| 0.8454 | 246 | 0.1472 |
|
| 532 |
+
| 0.8488 | 247 | 0.1516 |
|
| 533 |
+
| 0.8522 | 248 | 0.1579 |
|
| 534 |
+
| 0.8557 | 249 | 0.161 |
|
| 535 |
+
| 0.8591 | 250 | 0.1661 |
|
| 536 |
+
| 0.8625 | 251 | 0.155 |
|
| 537 |
+
| 0.8660 | 252 | 0.1706 |
|
| 538 |
+
| 0.8694 | 253 | 0.1527 |
|
| 539 |
+
| 0.8729 | 254 | 0.1695 |
|
| 540 |
+
| 0.8763 | 255 | 0.1904 |
|
| 541 |
+
| 0.8797 | 256 | 0.186 |
|
| 542 |
+
| 0.8832 | 257 | 0.1723 |
|
| 543 |
+
| 0.8866 | 258 | 0.1881 |
|
| 544 |
+
| 0.8900 | 259 | 0.1915 |
|
| 545 |
+
| 0.8935 | 260 | 0.1969 |
|
| 546 |
+
| 0.8969 | 261 | 0.1967 |
|
| 547 |
+
| 0.9003 | 262 | 0.2038 |
|
| 548 |
+
| 0.9038 | 263 | 0.1917 |
|
| 549 |
+
| 0.9072 | 264 | 0.19 |
|
| 550 |
+
| 0.9107 | 265 | 0.2161 |
|
| 551 |
+
| 0.9141 | 266 | 0.222 |
|
| 552 |
+
| 0.9175 | 267 | 0.2361 |
|
| 553 |
+
| 0.9210 | 268 | 0.2538 |
|
| 554 |
+
| 0.9244 | 269 | 0.2408 |
|
| 555 |
+
| 0.9278 | 270 | 0.2372 |
|
| 556 |
+
| 0.9313 | 271 | 0.2292 |
|
| 557 |
+
| 0.9347 | 272 | 0.238 |
|
| 558 |
+
| 0.9381 | 273 | 0.2243 |
|
| 559 |
+
| 0.9416 | 274 | 0.2443 |
|
| 560 |
+
| 0.9450 | 275 | 0.2435 |
|
| 561 |
+
| 0.9485 | 276 | 0.2476 |
|
| 562 |
+
| 0.9519 | 277 | 0.2259 |
|
| 563 |
+
| 0.9553 | 278 | 0.2327 |
|
| 564 |
+
| 0.9588 | 279 | 0.2345 |
|
| 565 |
+
| 0.9622 | 280 | 0.2413 |
|
| 566 |
+
|
| 567 |
+
</details>
|
| 568 |
+
|
| 569 |
+
### Framework Versions
|
| 570 |
+
- Python: 3.11.12
|
| 571 |
+
- Sentence Transformers: 5.0.0
|
| 572 |
+
- Transformers: 4.53.1
|
| 573 |
+
- PyTorch: 2.8.0+cu128
|
| 574 |
+
- Accelerate: 1.5.2
|
| 575 |
+
- Datasets: 2.21.0
|
| 576 |
+
- Tokenizers: 0.21.1
|
| 577 |
+
|
| 578 |
+
## Citation
|
| 579 |
+
|
| 580 |
+
### BibTeX
|
| 581 |
+
|
| 582 |
+
#### Sentence Transformers
|
| 583 |
+
```bibtex
|
| 584 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 585 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 586 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 587 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 588 |
+
month = "11",
|
| 589 |
+
year = "2019",
|
| 590 |
+
publisher = "Association for Computational Linguistics",
|
| 591 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 592 |
+
}
|
| 593 |
+
```
|
| 594 |
+
|
| 595 |
+
<!--
|
| 596 |
+
## Glossary
|
| 597 |
+
|
| 598 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 599 |
+
-->
|
| 600 |
+
|
| 601 |
+
<!--
|
| 602 |
+
## Model Card Authors
|
| 603 |
+
|
| 604 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 605 |
+
-->
|
| 606 |
+
|
| 607 |
+
<!--
|
| 608 |
+
## Model Card Contact
|
| 609 |
+
|
| 610 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 611 |
+
-->
|
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 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"LABEL_0": 0
|
| 19 |
+
},
|
| 20 |
+
"layer_types": [
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 40960,
|
| 51 |
+
"max_window_layers": 28,
|
| 52 |
+
"model_type": "qwen3",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 28,
|
| 55 |
+
"num_key_value_heads": 8,
|
| 56 |
+
"pad_token_id": 151643,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_scaling": null,
|
| 59 |
+
"rope_theta": 1000000,
|
| 60 |
+
"sentence_transformers": {
|
| 61 |
+
"activation_fn": "torch.nn.modules.activation.Sigmoid",
|
| 62 |
+
"version": "5.0.0"
|
| 63 |
+
},
|
| 64 |
+
"sliding_window": null,
|
| 65 |
+
"tie_word_embeddings": true,
|
| 66 |
+
"torch_dtype": "float32",
|
| 67 |
+
"transformers_version": "4.53.1",
|
| 68 |
+
"use_cache": true,
|
| 69 |
+
"use_sliding_window": false,
|
| 70 |
+
"vocab_size": 151669
|
| 71 |
+
}
|
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 sha256:8768cb13c91eca7dcf4b21741856c9a012b382634206149299a2625398beea76
|
| 3 |
+
size 2383145520
|
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 sha256:0bc04542e8e8fa70d398aea108486408a0320c9d5b460b448358363cd06382ac
|
| 3 |
+
size 11422922
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"model_max_length": 40960,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|