Add new SentenceTransformer model
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +10 -0
- README.md +785 -0
- adapter_config.json +50 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +28 -0
- chat_template.jinja +85 -0
- config_sentence_transformers.json +14 -0
- merges.txt +0 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -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 +1,785 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- sentence-transformers
|
| 4 |
+
- sentence-similarity
|
| 5 |
+
- feature-extraction
|
| 6 |
+
- dense
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
- dataset_size:1310129
|
| 9 |
+
- loss:MultipleNegativesRankingLoss
|
| 10 |
+
base_model: unsloth/Qwen3-Embedding-0.6B
|
| 11 |
+
widget:
|
| 12 |
+
- source_sentence: 닥터브로너스 [페이셜&바디워시] 닥터브로너스 퓨어 캐스틸 솝 475ml 12종 택1
|
| 13 |
+
sentences:
|
| 14 |
+
- 露得清卸妆油
|
| 15 |
+
- Versace Man Eau Fraiche
|
| 16 |
+
- ピュアキャスティールソープ
|
| 17 |
+
- source_sentence: 베르사체 베르사체 맨오프레쉬 30ml 단품/기획 택1
|
| 18 |
+
sentences:
|
| 19 |
+
- ピーリングジェル
|
| 20 |
+
- Versace Bright
|
| 21 |
+
- Man Eau Fraiche single
|
| 22 |
+
- source_sentence: 랑방 랑방 루머 2 로즈 50ml
|
| 23 |
+
sentences:
|
| 24 |
+
- 캐스틸 솝 475ml
|
| 25 |
+
- 랑방 루머
|
| 26 |
+
- 防晒霜
|
| 27 |
+
- source_sentence: 케어존 케어존 데일리&패밀리 선크림 80ml (SPF50+/PA+++)
|
| 28 |
+
sentences:
|
| 29 |
+
- 伊丽莎白雅顿 100毫升
|
| 30 |
+
- Rumeur Rose perfume
|
| 31 |
+
- 패밀리 선크림
|
| 32 |
+
- source_sentence: 랑방 랑방 메리미 EDP 50ml
|
| 33 |
+
sentences:
|
| 34 |
+
- マリーミー EDP
|
| 35 |
+
- 浪凡 EDP
|
| 36 |
+
- ケアゾーン デイリー日焼け止め
|
| 37 |
+
datasets:
|
| 38 |
+
- dkqjrm/olive-product
|
| 39 |
+
pipeline_tag: sentence-similarity
|
| 40 |
+
library_name: sentence-transformers
|
| 41 |
+
---
|
| 42 |
+
|
| 43 |
+
# SentenceTransformer based on unsloth/Qwen3-Embedding-0.6B
|
| 44 |
+
|
| 45 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [unsloth/Qwen3-Embedding-0.6B](https://huggingface.co/unsloth/Qwen3-Embedding-0.6B) on the [olive-product](https://huggingface.co/datasets/dkqjrm/olive-product) dataset. 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.
|
| 46 |
+
|
| 47 |
+
## Model Details
|
| 48 |
+
|
| 49 |
+
### Model Description
|
| 50 |
+
- **Model Type:** Sentence Transformer
|
| 51 |
+
- **Base model:** [unsloth/Qwen3-Embedding-0.6B](https://huggingface.co/unsloth/Qwen3-Embedding-0.6B) <!-- at revision f2fddb42505bde9feaf19f0967b01dce52e764c6 -->
|
| 52 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 53 |
+
- **Output Dimensionality:** 1024 dimensions
|
| 54 |
+
- **Similarity Function:** Cosine Similarity
|
| 55 |
+
- **Training Dataset:**
|
| 56 |
+
- [olive-product](https://huggingface.co/datasets/dkqjrm/olive-product)
|
| 57 |
+
<!-- - **Language:** Unknown -->
|
| 58 |
+
<!-- - **License:** Unknown -->
|
| 59 |
+
|
| 60 |
+
### Model Sources
|
| 61 |
+
|
| 62 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 63 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
|
| 64 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 65 |
+
|
| 66 |
+
### Full Model Architecture
|
| 67 |
+
|
| 68 |
+
```
|
| 69 |
+
SentenceTransformer(
|
| 70 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'PeftModelForFeatureExtraction'})
|
| 71 |
+
(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})
|
| 72 |
+
(2): Normalize()
|
| 73 |
+
)
|
| 74 |
+
```
|
| 75 |
+
|
| 76 |
+
## Usage
|
| 77 |
+
|
| 78 |
+
### Direct Usage (Sentence Transformers)
|
| 79 |
+
|
| 80 |
+
First install the Sentence Transformers library:
|
| 81 |
+
|
| 82 |
+
```bash
|
| 83 |
+
pip install -U sentence-transformers
|
| 84 |
+
```
|
| 85 |
+
|
| 86 |
+
Then you can load this model and run inference.
|
| 87 |
+
```python
|
| 88 |
+
from sentence_transformers import SentenceTransformer
|
| 89 |
+
|
| 90 |
+
# Download from the 🤗 Hub
|
| 91 |
+
model = SentenceTransformer("dkqjrm/lora_model")
|
| 92 |
+
# Run inference
|
| 93 |
+
sentences = [
|
| 94 |
+
'랑방 랑방 메리미 EDP 50ml',
|
| 95 |
+
'浪凡 EDP',
|
| 96 |
+
'マリーミー EDP',
|
| 97 |
+
]
|
| 98 |
+
embeddings = model.encode(sentences)
|
| 99 |
+
print(embeddings.shape)
|
| 100 |
+
# [3, 1024]
|
| 101 |
+
|
| 102 |
+
# Get the similarity scores for the embeddings
|
| 103 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 104 |
+
print(similarities)
|
| 105 |
+
# tensor([[1.0000, 0.6852, 0.6339],
|
| 106 |
+
# [0.6852, 1.0000, 0.3744],
|
| 107 |
+
# [0.6339, 0.3744, 1.0000]])
|
| 108 |
+
```
|
| 109 |
+
|
| 110 |
+
<!--
|
| 111 |
+
### Direct Usage (Transformers)
|
| 112 |
+
|
| 113 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 114 |
+
|
| 115 |
+
</details>
|
| 116 |
+
-->
|
| 117 |
+
|
| 118 |
+
<!--
|
| 119 |
+
### Downstream Usage (Sentence Transformers)
|
| 120 |
+
|
| 121 |
+
You can finetune this model on your own dataset.
|
| 122 |
+
|
| 123 |
+
<details><summary>Click to expand</summary>
|
| 124 |
+
|
| 125 |
+
</details>
|
| 126 |
+
-->
|
| 127 |
+
|
| 128 |
+
<!--
|
| 129 |
+
### Out-of-Scope Use
|
| 130 |
+
|
| 131 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 132 |
+
-->
|
| 133 |
+
|
| 134 |
+
<!--
|
| 135 |
+
## Bias, Risks and Limitations
|
| 136 |
+
|
| 137 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 138 |
+
-->
|
| 139 |
+
|
| 140 |
+
<!--
|
| 141 |
+
### Recommendations
|
| 142 |
+
|
| 143 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 144 |
+
-->
|
| 145 |
+
|
| 146 |
+
## Training Details
|
| 147 |
+
|
| 148 |
+
### Training Dataset
|
| 149 |
+
|
| 150 |
+
#### olive-product
|
| 151 |
+
|
| 152 |
+
* Dataset: [olive-product](https://huggingface.co/datasets/dkqjrm/olive-product) at [8d1f081](https://huggingface.co/datasets/dkqjrm/olive-product/tree/8d1f0813721299cb95f6d5cc09b2ef9317e8d06c)
|
| 153 |
+
* Size: 1,310,129 training samples
|
| 154 |
+
* Columns: <code>anchor</code> and <code>positive</code>
|
| 155 |
+
* Approximate statistics based on the first 1000 samples:
|
| 156 |
+
| | anchor | positive |
|
| 157 |
+
|:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
|
| 158 |
+
| type | string | string |
|
| 159 |
+
| details | <ul><li>min: 16 tokens</li><li>mean: 25.67 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 7.19 tokens</li><li>max: 38 tokens</li></ul> |
|
| 160 |
+
* Samples:
|
| 161 |
+
| anchor | positive |
|
| 162 |
+
|:-----------------------------------------|:-----------------------------------|
|
| 163 |
+
| <code>베르사체 베르사체 브라이트 크리스탈 50ml 택1</code> | <code>베르사체 브라이트 크리스탈 50ml 1</code> |
|
| 164 |
+
| <code>베르사체 베르사체 브라이트 크리스탈 50ml 택1</code> | <code>베르사체 브라이트</code> |
|
| 165 |
+
| <code>베르사체 베르사체 브라이트 크리스탈 50ml 택1</code> | <code>베르사체 크리스탈</code> |
|
| 166 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
| 167 |
+
```json
|
| 168 |
+
{
|
| 169 |
+
"scale": 20.0,
|
| 170 |
+
"similarity_fct": "cos_sim",
|
| 171 |
+
"gather_across_devices": false
|
| 172 |
+
}
|
| 173 |
+
```
|
| 174 |
+
|
| 175 |
+
### Training Hyperparameters
|
| 176 |
+
#### Non-Default Hyperparameters
|
| 177 |
+
|
| 178 |
+
- `per_device_train_batch_size`: 32
|
| 179 |
+
- `gradient_accumulation_steps`: 4
|
| 180 |
+
- `learning_rate`: 3e-05
|
| 181 |
+
- `num_train_epochs`: 2
|
| 182 |
+
- `lr_scheduler_type`: constant_with_warmup
|
| 183 |
+
- `warmup_ratio`: 0.03
|
| 184 |
+
- `fp16`: True
|
| 185 |
+
- `push_to_hub`: True
|
| 186 |
+
- `hub_model_id`: dkqjrm/qwen3-embedding-olive-lora
|
| 187 |
+
- `batch_sampler`: no_duplicates
|
| 188 |
+
|
| 189 |
+
#### All Hyperparameters
|
| 190 |
+
<details><summary>Click to expand</summary>
|
| 191 |
+
|
| 192 |
+
- `overwrite_output_dir`: False
|
| 193 |
+
- `do_predict`: False
|
| 194 |
+
- `eval_strategy`: no
|
| 195 |
+
- `prediction_loss_only`: True
|
| 196 |
+
- `per_device_train_batch_size`: 32
|
| 197 |
+
- `per_device_eval_batch_size`: 8
|
| 198 |
+
- `per_gpu_train_batch_size`: None
|
| 199 |
+
- `per_gpu_eval_batch_size`: None
|
| 200 |
+
- `gradient_accumulation_steps`: 4
|
| 201 |
+
- `eval_accumulation_steps`: None
|
| 202 |
+
- `torch_empty_cache_steps`: None
|
| 203 |
+
- `learning_rate`: 3e-05
|
| 204 |
+
- `weight_decay`: 0.0
|
| 205 |
+
- `adam_beta1`: 0.9
|
| 206 |
+
- `adam_beta2`: 0.999
|
| 207 |
+
- `adam_epsilon`: 1e-08
|
| 208 |
+
- `max_grad_norm`: 1.0
|
| 209 |
+
- `num_train_epochs`: 2
|
| 210 |
+
- `max_steps`: -1
|
| 211 |
+
- `lr_scheduler_type`: constant_with_warmup
|
| 212 |
+
- `lr_scheduler_kwargs`: None
|
| 213 |
+
- `warmup_ratio`: 0.03
|
| 214 |
+
- `warmup_steps`: 0
|
| 215 |
+
- `log_level`: passive
|
| 216 |
+
- `log_level_replica`: warning
|
| 217 |
+
- `log_on_each_node`: True
|
| 218 |
+
- `logging_nan_inf_filter`: True
|
| 219 |
+
- `save_safetensors`: True
|
| 220 |
+
- `save_on_each_node`: False
|
| 221 |
+
- `save_only_model`: False
|
| 222 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 223 |
+
- `no_cuda`: False
|
| 224 |
+
- `use_cpu`: False
|
| 225 |
+
- `use_mps_device`: False
|
| 226 |
+
- `seed`: 42
|
| 227 |
+
- `data_seed`: None
|
| 228 |
+
- `jit_mode_eval`: False
|
| 229 |
+
- `bf16`: False
|
| 230 |
+
- `fp16`: True
|
| 231 |
+
- `fp16_opt_level`: O1
|
| 232 |
+
- `half_precision_backend`: auto
|
| 233 |
+
- `bf16_full_eval`: False
|
| 234 |
+
- `fp16_full_eval`: False
|
| 235 |
+
- `tf32`: None
|
| 236 |
+
- `local_rank`: 0
|
| 237 |
+
- `ddp_backend`: None
|
| 238 |
+
- `tpu_num_cores`: None
|
| 239 |
+
- `tpu_metrics_debug`: False
|
| 240 |
+
- `debug`: []
|
| 241 |
+
- `dataloader_drop_last`: False
|
| 242 |
+
- `dataloader_num_workers`: 0
|
| 243 |
+
- `dataloader_prefetch_factor`: None
|
| 244 |
+
- `past_index`: -1
|
| 245 |
+
- `disable_tqdm`: False
|
| 246 |
+
- `remove_unused_columns`: True
|
| 247 |
+
- `label_names`: None
|
| 248 |
+
- `load_best_model_at_end`: False
|
| 249 |
+
- `ignore_data_skip`: False
|
| 250 |
+
- `fsdp`: []
|
| 251 |
+
- `fsdp_min_num_params`: 0
|
| 252 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 253 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 254 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 255 |
+
- `parallelism_config`: None
|
| 256 |
+
- `deepspeed`: None
|
| 257 |
+
- `label_smoothing_factor`: 0.0
|
| 258 |
+
- `optim`: adamw_torch_fused
|
| 259 |
+
- `optim_args`: None
|
| 260 |
+
- `adafactor`: False
|
| 261 |
+
- `group_by_length`: False
|
| 262 |
+
- `length_column_name`: length
|
| 263 |
+
- `project`: huggingface
|
| 264 |
+
- `trackio_space_id`: trackio
|
| 265 |
+
- `ddp_find_unused_parameters`: None
|
| 266 |
+
- `ddp_bucket_cap_mb`: None
|
| 267 |
+
- `ddp_broadcast_buffers`: False
|
| 268 |
+
- `dataloader_pin_memory`: True
|
| 269 |
+
- `dataloader_persistent_workers`: False
|
| 270 |
+
- `skip_memory_metrics`: True
|
| 271 |
+
- `use_legacy_prediction_loop`: False
|
| 272 |
+
- `push_to_hub`: True
|
| 273 |
+
- `resume_from_checkpoint`: None
|
| 274 |
+
- `hub_model_id`: dkqjrm/qwen3-embedding-olive-lora
|
| 275 |
+
- `hub_strategy`: every_save
|
| 276 |
+
- `hub_private_repo`: None
|
| 277 |
+
- `hub_always_push`: False
|
| 278 |
+
- `hub_revision`: None
|
| 279 |
+
- `gradient_checkpointing`: False
|
| 280 |
+
- `gradient_checkpointing_kwargs`: None
|
| 281 |
+
- `include_inputs_for_metrics`: False
|
| 282 |
+
- `include_for_metrics`: []
|
| 283 |
+
- `eval_do_concat_batches`: True
|
| 284 |
+
- `fp16_backend`: auto
|
| 285 |
+
- `push_to_hub_model_id`: None
|
| 286 |
+
- `push_to_hub_organization`: None
|
| 287 |
+
- `mp_parameters`:
|
| 288 |
+
- `auto_find_batch_size`: False
|
| 289 |
+
- `full_determinism`: False
|
| 290 |
+
- `torchdynamo`: None
|
| 291 |
+
- `ray_scope`: last
|
| 292 |
+
- `ddp_timeout`: 1800
|
| 293 |
+
- `torch_compile`: False
|
| 294 |
+
- `torch_compile_backend`: None
|
| 295 |
+
- `torch_compile_mode`: None
|
| 296 |
+
- `include_tokens_per_second`: False
|
| 297 |
+
- `include_num_input_tokens_seen`: no
|
| 298 |
+
- `neftune_noise_alpha`: None
|
| 299 |
+
- `optim_target_modules`: None
|
| 300 |
+
- `batch_eval_metrics`: False
|
| 301 |
+
- `eval_on_start`: False
|
| 302 |
+
- `use_liger_kernel`: False
|
| 303 |
+
- `liger_kernel_config`: None
|
| 304 |
+
- `eval_use_gather_object`: False
|
| 305 |
+
- `average_tokens_across_devices`: True
|
| 306 |
+
- `prompts`: None
|
| 307 |
+
- `batch_sampler`: no_duplicates
|
| 308 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 309 |
+
- `router_mapping`: {}
|
| 310 |
+
- `learning_rate_mapping`: {}
|
| 311 |
+
|
| 312 |
+
</details>
|
| 313 |
+
|
| 314 |
+
### Training Logs
|
| 315 |
+
<details><summary>Click to expand</summary>
|
| 316 |
+
|
| 317 |
+
| Epoch | Step | Training Loss |
|
| 318 |
+
|:------:|:-----:|:-------------:|
|
| 319 |
+
| 0.0049 | 50 | 1.5027 |
|
| 320 |
+
| 0.0098 | 100 | 0.8366 |
|
| 321 |
+
| 0.0147 | 150 | 0.6713 |
|
| 322 |
+
| 0.0195 | 200 | 0.5863 |
|
| 323 |
+
| 0.0244 | 250 | 0.53 |
|
| 324 |
+
| 0.0293 | 300 | 0.4562 |
|
| 325 |
+
| 0.0342 | 350 | 0.4061 |
|
| 326 |
+
| 0.0391 | 400 | 0.3899 |
|
| 327 |
+
| 0.0440 | 450 | 0.3417 |
|
| 328 |
+
| 0.0488 | 500 | 0.3367 |
|
| 329 |
+
| 0.0537 | 550 | 0.2948 |
|
| 330 |
+
| 0.0586 | 600 | 0.281 |
|
| 331 |
+
| 0.0635 | 650 | 0.2808 |
|
| 332 |
+
| 0.0684 | 700 | 0.2414 |
|
| 333 |
+
| 0.0733 | 750 | 0.2448 |
|
| 334 |
+
| 0.0782 | 800 | 0.2307 |
|
| 335 |
+
| 0.0830 | 850 | 0.2174 |
|
| 336 |
+
| 0.0879 | 900 | 0.2129 |
|
| 337 |
+
| 0.0928 | 950 | 0.2139 |
|
| 338 |
+
| 0.0977 | 1000 | 0.198 |
|
| 339 |
+
| 0.1026 | 1050 | 0.1797 |
|
| 340 |
+
| 0.1075 | 1100 | 0.1923 |
|
| 341 |
+
| 0.1124 | 1150 | 0.1887 |
|
| 342 |
+
| 0.1172 | 1200 | 0.1789 |
|
| 343 |
+
| 0.1221 | 1250 | 0.1833 |
|
| 344 |
+
| 0.1270 | 1300 | 0.168 |
|
| 345 |
+
| 0.1319 | 1350 | 0.1683 |
|
| 346 |
+
| 0.1368 | 1400 | 0.1536 |
|
| 347 |
+
| 0.1417 | 1450 | 0.1632 |
|
| 348 |
+
| 0.1465 | 1500 | 0.155 |
|
| 349 |
+
| 0.1514 | 1550 | 0.1533 |
|
| 350 |
+
| 0.1563 | 1600 | 0.1442 |
|
| 351 |
+
| 0.1612 | 1650 | 0.1407 |
|
| 352 |
+
| 0.1661 | 1700 | 0.1396 |
|
| 353 |
+
| 0.1710 | 1750 | 0.1388 |
|
| 354 |
+
| 0.1759 | 1800 | 0.1375 |
|
| 355 |
+
| 0.1807 | 1850 | 0.1356 |
|
| 356 |
+
| 0.1856 | 1900 | 0.1335 |
|
| 357 |
+
| 0.1905 | 1950 | 0.1296 |
|
| 358 |
+
| 0.1954 | 2000 | 0.1281 |
|
| 359 |
+
| 0.2003 | 2050 | 0.1379 |
|
| 360 |
+
| 0.2052 | 2100 | 0.1213 |
|
| 361 |
+
| 0.2101 | 2150 | 0.1209 |
|
| 362 |
+
| 0.2149 | 2200 | 0.1142 |
|
| 363 |
+
| 0.2198 | 2250 | 0.1305 |
|
| 364 |
+
| 0.2247 | 2300 | 0.115 |
|
| 365 |
+
| 0.2296 | 2350 | 0.1125 |
|
| 366 |
+
| 0.2345 | 2400 | 0.1159 |
|
| 367 |
+
| 0.2394 | 2450 | 0.1131 |
|
| 368 |
+
| 0.2442 | 2500 | 0.1133 |
|
| 369 |
+
| 0.2491 | 2550 | 0.1126 |
|
| 370 |
+
| 0.2540 | 2600 | 0.109 |
|
| 371 |
+
| 0.2589 | 2650 | 0.1135 |
|
| 372 |
+
| 0.2638 | 2700 | 0.0986 |
|
| 373 |
+
| 0.2687 | 2750 | 0.1127 |
|
| 374 |
+
| 0.2736 | 2800 | 0.114 |
|
| 375 |
+
| 0.2784 | 2850 | 0.1079 |
|
| 376 |
+
| 0.2833 | 2900 | 0.1106 |
|
| 377 |
+
| 0.2882 | 2950 | 0.1112 |
|
| 378 |
+
| 0.2931 | 3000 | 0.1006 |
|
| 379 |
+
| 0.2980 | 3050 | 0.1051 |
|
| 380 |
+
| 0.3029 | 3100 | 0.1105 |
|
| 381 |
+
| 0.3078 | 3150 | 0.1046 |
|
| 382 |
+
| 0.3126 | 3200 | 0.1011 |
|
| 383 |
+
| 0.3175 | 3250 | 0.0962 |
|
| 384 |
+
| 0.3224 | 3300 | 0.1002 |
|
| 385 |
+
| 0.3273 | 3350 | 0.1066 |
|
| 386 |
+
| 0.3322 | 3400 | 0.0907 |
|
| 387 |
+
| 0.3371 | 3450 | 0.0894 |
|
| 388 |
+
| 0.3419 | 3500 | 0.1002 |
|
| 389 |
+
| 0.3468 | 3550 | 0.0894 |
|
| 390 |
+
| 0.3517 | 3600 | 0.0897 |
|
| 391 |
+
| 0.3566 | 3650 | 0.0995 |
|
| 392 |
+
| 0.3615 | 3700 | 0.0949 |
|
| 393 |
+
| 0.3664 | 3750 | 0.0914 |
|
| 394 |
+
| 0.3713 | 3800 | 0.0929 |
|
| 395 |
+
| 0.3761 | 3850 | 0.0841 |
|
| 396 |
+
| 0.3810 | 3900 | 0.0847 |
|
| 397 |
+
| 0.3859 | 3950 | 0.0964 |
|
| 398 |
+
| 0.3908 | 4000 | 0.0937 |
|
| 399 |
+
| 0.3957 | 4050 | 0.0874 |
|
| 400 |
+
| 0.4006 | 4100 | 0.0911 |
|
| 401 |
+
| 0.4055 | 4150 | 0.093 |
|
| 402 |
+
| 0.4103 | 4200 | 0.0867 |
|
| 403 |
+
| 0.4152 | 4250 | 0.0841 |
|
| 404 |
+
| 0.4201 | 4300 | 0.083 |
|
| 405 |
+
| 0.4250 | 4350 | 0.0908 |
|
| 406 |
+
| 0.4299 | 4400 | 0.0829 |
|
| 407 |
+
| 0.4348 | 4450 | 0.0871 |
|
| 408 |
+
| 0.4396 | 4500 | 0.0799 |
|
| 409 |
+
| 0.4445 | 4550 | 0.0777 |
|
| 410 |
+
| 0.4494 | 4600 | 0.0873 |
|
| 411 |
+
| 0.4543 | 4650 | 0.0805 |
|
| 412 |
+
| 0.4592 | 4700 | 0.0851 |
|
| 413 |
+
| 0.4641 | 4750 | 0.0855 |
|
| 414 |
+
| 0.4690 | 4800 | 0.0763 |
|
| 415 |
+
| 0.4738 | 4850 | 0.082 |
|
| 416 |
+
| 0.4787 | 4900 | 0.0699 |
|
| 417 |
+
| 0.4836 | 4950 | 0.0802 |
|
| 418 |
+
| 0.4885 | 5000 | 0.0807 |
|
| 419 |
+
| 0.4934 | 5050 | 0.0746 |
|
| 420 |
+
| 0.4983 | 5100 | 0.0705 |
|
| 421 |
+
| 0.5032 | 5150 | 0.0707 |
|
| 422 |
+
| 0.5080 | 5200 | 0.0827 |
|
| 423 |
+
| 0.5129 | 5250 | 0.0808 |
|
| 424 |
+
| 0.5178 | 5300 | 0.0835 |
|
| 425 |
+
| 0.5227 | 5350 | 0.0782 |
|
| 426 |
+
| 0.5276 | 5400 | 0.0698 |
|
| 427 |
+
| 0.5325 | 5450 | 0.0755 |
|
| 428 |
+
| 0.5373 | 5500 | 0.0743 |
|
| 429 |
+
| 0.5422 | 5550 | 0.0744 |
|
| 430 |
+
| 0.5471 | 5600 | 0.0724 |
|
| 431 |
+
| 0.5520 | 5650 | 0.0781 |
|
| 432 |
+
| 0.5569 | 5700 | 0.0712 |
|
| 433 |
+
| 0.5618 | 5750 | 0.0738 |
|
| 434 |
+
| 0.5667 | 5800 | 0.0692 |
|
| 435 |
+
| 0.5715 | 5850 | 0.0747 |
|
| 436 |
+
| 0.5764 | 5900 | 0.0686 |
|
| 437 |
+
| 0.5813 | 5950 | 0.0761 |
|
| 438 |
+
| 0.5862 | 6000 | 0.0696 |
|
| 439 |
+
| 0.5911 | 6050 | 0.0681 |
|
| 440 |
+
| 0.5960 | 6100 | 0.0714 |
|
| 441 |
+
| 0.6008 | 6150 | 0.0682 |
|
| 442 |
+
| 0.6057 | 6200 | 0.0746 |
|
| 443 |
+
| 0.6106 | 6250 | 0.0638 |
|
| 444 |
+
| 0.6155 | 6300 | 0.0672 |
|
| 445 |
+
| 0.6204 | 6350 | 0.0727 |
|
| 446 |
+
| 0.6253 | 6400 | 0.0711 |
|
| 447 |
+
| 0.6302 | 6450 | 0.0716 |
|
| 448 |
+
| 0.6350 | 6500 | 0.0609 |
|
| 449 |
+
| 0.6399 | 6550 | 0.066 |
|
| 450 |
+
| 0.6448 | 6600 | 0.0709 |
|
| 451 |
+
| 0.6497 | 6650 | 0.0687 |
|
| 452 |
+
| 0.6546 | 6700 | 0.0629 |
|
| 453 |
+
| 0.6595 | 6750 | 0.0693 |
|
| 454 |
+
| 0.6644 | 6800 | 0.0678 |
|
| 455 |
+
| 0.6692 | 6850 | 0.0612 |
|
| 456 |
+
| 0.6741 | 6900 | 0.0653 |
|
| 457 |
+
| 0.6790 | 6950 | 0.0642 |
|
| 458 |
+
| 0.6839 | 7000 | 0.068 |
|
| 459 |
+
| 0.6888 | 7050 | 0.0626 |
|
| 460 |
+
| 0.6937 | 7100 | 0.0623 |
|
| 461 |
+
| 0.6985 | 7150 | 0.0622 |
|
| 462 |
+
| 0.7034 | 7200 | 0.0661 |
|
| 463 |
+
| 0.7083 | 7250 | 0.0597 |
|
| 464 |
+
| 0.7132 | 7300 | 0.0584 |
|
| 465 |
+
| 0.7181 | 7350 | 0.0595 |
|
| 466 |
+
| 0.7230 | 7400 | 0.0647 |
|
| 467 |
+
| 0.7279 | 7450 | 0.0664 |
|
| 468 |
+
| 0.7327 | 7500 | 0.0682 |
|
| 469 |
+
| 0.7376 | 7550 | 0.0621 |
|
| 470 |
+
| 0.7425 | 7600 | 0.0603 |
|
| 471 |
+
| 0.7474 | 7650 | 0.0617 |
|
| 472 |
+
| 0.7523 | 7700 | 0.0554 |
|
| 473 |
+
| 0.7572 | 7750 | 0.056 |
|
| 474 |
+
| 0.7621 | 7800 | 0.0594 |
|
| 475 |
+
| 0.7669 | 7850 | 0.0594 |
|
| 476 |
+
| 0.7718 | 7900 | 0.0618 |
|
| 477 |
+
| 0.7767 | 7950 | 0.0638 |
|
| 478 |
+
| 0.7816 | 8000 | 0.0556 |
|
| 479 |
+
| 0.7865 | 8050 | 0.0608 |
|
| 480 |
+
| 0.7914 | 8100 | 0.0624 |
|
| 481 |
+
| 0.7962 | 8150 | 0.0621 |
|
| 482 |
+
| 0.8011 | 8200 | 0.0653 |
|
| 483 |
+
| 0.8060 | 8250 | 0.0648 |
|
| 484 |
+
| 0.8109 | 8300 | 0.0533 |
|
| 485 |
+
| 0.8158 | 8350 | 0.0584 |
|
| 486 |
+
| 0.8207 | 8400 | 0.0552 |
|
| 487 |
+
| 0.8256 | 8450 | 0.066 |
|
| 488 |
+
| 0.8304 | 8500 | 0.0616 |
|
| 489 |
+
| 0.8353 | 8550 | 0.0648 |
|
| 490 |
+
| 0.8402 | 8600 | 0.0618 |
|
| 491 |
+
| 0.8451 | 8650 | 0.0587 |
|
| 492 |
+
| 0.8500 | 8700 | 0.0616 |
|
| 493 |
+
| 0.8549 | 8750 | 0.0544 |
|
| 494 |
+
| 0.8598 | 8800 | 0.0637 |
|
| 495 |
+
| 0.8646 | 8850 | 0.0621 |
|
| 496 |
+
| 0.8695 | 8900 | 0.0574 |
|
| 497 |
+
| 0.8744 | 8950 | 0.0587 |
|
| 498 |
+
| 0.8793 | 9000 | 0.0606 |
|
| 499 |
+
| 0.8842 | 9050 | 0.0595 |
|
| 500 |
+
| 0.8891 | 9100 | 0.0627 |
|
| 501 |
+
| 0.8939 | 9150 | 0.0564 |
|
| 502 |
+
| 0.8988 | 9200 | 0.0542 |
|
| 503 |
+
| 0.9037 | 9250 | 0.0538 |
|
| 504 |
+
| 0.9086 | 9300 | 0.055 |
|
| 505 |
+
| 0.9135 | 9350 | 0.0562 |
|
| 506 |
+
| 0.9184 | 9400 | 0.0547 |
|
| 507 |
+
| 0.9233 | 9450 | 0.0514 |
|
| 508 |
+
| 0.9281 | 9500 | 0.0574 |
|
| 509 |
+
| 0.9330 | 9550 | 0.0503 |
|
| 510 |
+
| 0.9379 | 9600 | 0.0647 |
|
| 511 |
+
| 0.9428 | 9650 | 0.0554 |
|
| 512 |
+
| 0.9477 | 9700 | 0.0532 |
|
| 513 |
+
| 0.9526 | 9750 | 0.056 |
|
| 514 |
+
| 0.9575 | 9800 | 0.0554 |
|
| 515 |
+
| 0.9623 | 9850 | 0.0535 |
|
| 516 |
+
| 0.9672 | 9900 | 0.0553 |
|
| 517 |
+
| 0.9721 | 9950 | 0.0581 |
|
| 518 |
+
| 0.9770 | 10000 | 0.05 |
|
| 519 |
+
| 0.9819 | 10050 | 0.0571 |
|
| 520 |
+
| 0.9868 | 10100 | 0.0534 |
|
| 521 |
+
| 0.9916 | 10150 | 0.0462 |
|
| 522 |
+
| 0.9965 | 10200 | 0.0508 |
|
| 523 |
+
| 1.0014 | 10250 | 0.0506 |
|
| 524 |
+
| 1.0063 | 10300 | 0.0548 |
|
| 525 |
+
| 1.0111 | 10350 | 0.0476 |
|
| 526 |
+
| 1.0160 | 10400 | 0.0504 |
|
| 527 |
+
| 1.0209 | 10450 | 0.0433 |
|
| 528 |
+
| 1.0258 | 10500 | 0.0499 |
|
| 529 |
+
| 1.0307 | 10550 | 0.0453 |
|
| 530 |
+
| 1.0356 | 10600 | 0.0494 |
|
| 531 |
+
| 1.0404 | 10650 | 0.0456 |
|
| 532 |
+
| 1.0453 | 10700 | 0.0499 |
|
| 533 |
+
| 1.0502 | 10750 | 0.049 |
|
| 534 |
+
| 1.0551 | 10800 | 0.0464 |
|
| 535 |
+
| 1.0600 | 10850 | 0.0483 |
|
| 536 |
+
| 1.0649 | 10900 | 0.0487 |
|
| 537 |
+
| 1.0698 | 10950 | 0.0461 |
|
| 538 |
+
| 1.0746 | 11000 | 0.0433 |
|
| 539 |
+
| 1.0795 | 11050 | 0.0474 |
|
| 540 |
+
| 1.0844 | 11100 | 0.0485 |
|
| 541 |
+
| 1.0893 | 11150 | 0.0462 |
|
| 542 |
+
| 1.0942 | 11200 | 0.0396 |
|
| 543 |
+
| 1.0991 | 11250 | 0.0479 |
|
| 544 |
+
| 1.1040 | 11300 | 0.0471 |
|
| 545 |
+
| 1.1088 | 11350 | 0.0473 |
|
| 546 |
+
| 1.1137 | 11400 | 0.0482 |
|
| 547 |
+
| 1.1186 | 11450 | 0.0412 |
|
| 548 |
+
| 1.1235 | 11500 | 0.0455 |
|
| 549 |
+
| 1.1284 | 11550 | 0.0448 |
|
| 550 |
+
| 1.1333 | 11600 | 0.0531 |
|
| 551 |
+
| 1.1381 | 11650 | 0.0466 |
|
| 552 |
+
| 1.1430 | 11700 | 0.0527 |
|
| 553 |
+
| 1.1479 | 11750 | 0.0465 |
|
| 554 |
+
| 1.1528 | 11800 | 0.0536 |
|
| 555 |
+
| 1.1577 | 11850 | 0.0474 |
|
| 556 |
+
| 1.1626 | 11900 | 0.0515 |
|
| 557 |
+
| 1.1675 | 11950 | 0.0429 |
|
| 558 |
+
| 1.1723 | 12000 | 0.0464 |
|
| 559 |
+
| 1.1772 | 12050 | 0.0463 |
|
| 560 |
+
| 1.1821 | 12100 | 0.0491 |
|
| 561 |
+
| 1.1870 | 12150 | 0.0433 |
|
| 562 |
+
| 1.1919 | 12200 | 0.0466 |
|
| 563 |
+
| 1.1968 | 12250 | 0.0522 |
|
| 564 |
+
| 1.2017 | 12300 | 0.0463 |
|
| 565 |
+
| 1.2065 | 12350 | 0.0528 |
|
| 566 |
+
| 1.2114 | 12400 | 0.0451 |
|
| 567 |
+
| 1.2163 | 12450 | 0.0449 |
|
| 568 |
+
| 1.2212 | 12500 | 0.0475 |
|
| 569 |
+
| 1.2261 | 12550 | 0.0468 |
|
| 570 |
+
| 1.2310 | 12600 | 0.0456 |
|
| 571 |
+
| 1.2358 | 12650 | 0.0411 |
|
| 572 |
+
| 1.2407 | 12700 | 0.0439 |
|
| 573 |
+
| 1.2456 | 12750 | 0.0434 |
|
| 574 |
+
| 1.2505 | 12800 | 0.0475 |
|
| 575 |
+
| 1.2554 | 12850 | 0.0468 |
|
| 576 |
+
| 1.2603 | 12900 | 0.046 |
|
| 577 |
+
| 1.2652 | 12950 | 0.0467 |
|
| 578 |
+
| 1.2700 | 13000 | 0.0429 |
|
| 579 |
+
| 1.2749 | 13050 | 0.0437 |
|
| 580 |
+
| 1.2798 | 13100 | 0.048 |
|
| 581 |
+
| 1.2847 | 13150 | 0.0429 |
|
| 582 |
+
| 1.2896 | 13200 | 0.0507 |
|
| 583 |
+
| 1.2945 | 13250 | 0.0426 |
|
| 584 |
+
| 1.2994 | 13300 | 0.0408 |
|
| 585 |
+
| 1.3042 | 13350 | 0.0468 |
|
| 586 |
+
| 1.3091 | 13400 | 0.0389 |
|
| 587 |
+
| 1.3140 | 13450 | 0.0458 |
|
| 588 |
+
| 1.3189 | 13500 | 0.044 |
|
| 589 |
+
| 1.3238 | 13550 | 0.0417 |
|
| 590 |
+
| 1.3287 | 13600 | 0.0437 |
|
| 591 |
+
| 1.3335 | 13650 | 0.0427 |
|
| 592 |
+
| 1.3384 | 13700 | 0.0444 |
|
| 593 |
+
| 1.3433 | 13750 | 0.0496 |
|
| 594 |
+
| 1.3482 | 13800 | 0.0443 |
|
| 595 |
+
| 1.3531 | 13850 | 0.0421 |
|
| 596 |
+
| 1.3580 | 13900 | 0.0431 |
|
| 597 |
+
| 1.3629 | 13950 | 0.0474 |
|
| 598 |
+
| 1.3677 | 14000 | 0.0423 |
|
| 599 |
+
| 1.3726 | 14050 | 0.0437 |
|
| 600 |
+
| 1.3775 | 14100 | 0.038 |
|
| 601 |
+
| 1.3824 | 14150 | 0.0457 |
|
| 602 |
+
| 1.3873 | 14200 | 0.0459 |
|
| 603 |
+
| 1.3922 | 14250 | 0.0421 |
|
| 604 |
+
| 1.3970 | 14300 | 0.0482 |
|
| 605 |
+
| 1.4019 | 14350 | 0.0496 |
|
| 606 |
+
| 1.4068 | 14400 | 0.0436 |
|
| 607 |
+
| 1.4117 | 14450 | 0.0437 |
|
| 608 |
+
| 1.4166 | 14500 | 0.0463 |
|
| 609 |
+
| 1.4215 | 14550 | 0.04 |
|
| 610 |
+
| 1.4264 | 14600 | 0.046 |
|
| 611 |
+
| 1.4312 | 14650 | 0.0451 |
|
| 612 |
+
| 1.4361 | 14700 | 0.044 |
|
| 613 |
+
| 1.4410 | 14750 | 0.0436 |
|
| 614 |
+
| 1.4459 | 14800 | 0.0411 |
|
| 615 |
+
| 1.4508 | 14850 | 0.0453 |
|
| 616 |
+
| 1.4557 | 14900 | 0.0402 |
|
| 617 |
+
| 1.4606 | 14950 | 0.0437 |
|
| 618 |
+
| 1.4654 | 15000 | 0.0451 |
|
| 619 |
+
| 1.4703 | 15050 | 0.0454 |
|
| 620 |
+
| 1.4752 | 15100 | 0.0433 |
|
| 621 |
+
| 1.4801 | 15150 | 0.0399 |
|
| 622 |
+
| 1.4850 | 15200 | 0.0389 |
|
| 623 |
+
| 1.4899 | 15250 | 0.0451 |
|
| 624 |
+
| 1.4947 | 15300 | 0.0417 |
|
| 625 |
+
| 1.4996 | 15350 | 0.0411 |
|
| 626 |
+
| 1.5045 | 15400 | 0.0415 |
|
| 627 |
+
| 1.5094 | 15450 | 0.044 |
|
| 628 |
+
| 1.5143 | 15500 | 0.045 |
|
| 629 |
+
| 1.5192 | 15550 | 0.0414 |
|
| 630 |
+
| 1.5241 | 15600 | 0.0439 |
|
| 631 |
+
| 1.5289 | 15650 | 0.0381 |
|
| 632 |
+
| 1.5338 | 15700 | 0.0425 |
|
| 633 |
+
| 1.5387 | 15750 | 0.0439 |
|
| 634 |
+
| 1.5436 | 15800 | 0.0405 |
|
| 635 |
+
| 1.5485 | 15850 | 0.0407 |
|
| 636 |
+
| 1.5534 | 15900 | 0.04 |
|
| 637 |
+
| 1.5583 | 15950 | 0.0404 |
|
| 638 |
+
| 1.5631 | 16000 | 0.0392 |
|
| 639 |
+
| 1.5680 | 16050 | 0.0432 |
|
| 640 |
+
| 1.5729 | 16100 | 0.0374 |
|
| 641 |
+
| 1.5778 | 16150 | 0.044 |
|
| 642 |
+
| 1.5827 | 16200 | 0.0429 |
|
| 643 |
+
| 1.5876 | 16250 | 0.0394 |
|
| 644 |
+
| 1.5924 | 16300 | 0.0446 |
|
| 645 |
+
| 1.5973 | 16350 | 0.0389 |
|
| 646 |
+
| 1.6022 | 16400 | 0.0429 |
|
| 647 |
+
| 1.6071 | 16450 | 0.0442 |
|
| 648 |
+
| 1.6120 | 16500 | 0.0394 |
|
| 649 |
+
| 1.6169 | 16550 | 0.0403 |
|
| 650 |
+
| 1.6218 | 16600 | 0.0414 |
|
| 651 |
+
| 1.6266 | 16650 | 0.0386 |
|
| 652 |
+
| 1.6315 | 16700 | 0.0401 |
|
| 653 |
+
| 1.6364 | 16750 | 0.0415 |
|
| 654 |
+
| 1.6413 | 16800 | 0.0427 |
|
| 655 |
+
| 1.6462 | 16850 | 0.0412 |
|
| 656 |
+
| 1.6511 | 16900 | 0.0404 |
|
| 657 |
+
| 1.6560 | 16950 | 0.0402 |
|
| 658 |
+
| 1.6608 | 17000 | 0.0394 |
|
| 659 |
+
| 1.6657 | 17050 | 0.0429 |
|
| 660 |
+
| 1.6706 | 17100 | 0.0452 |
|
| 661 |
+
| 1.6755 | 17150 | 0.0438 |
|
| 662 |
+
| 1.6804 | 17200 | 0.0433 |
|
| 663 |
+
| 1.6853 | 17250 | 0.0393 |
|
| 664 |
+
| 1.6901 | 17300 | 0.0405 |
|
| 665 |
+
| 1.6950 | 17350 | 0.044 |
|
| 666 |
+
| 1.6999 | 17400 | 0.042 |
|
| 667 |
+
| 1.7048 | 17450 | 0.0401 |
|
| 668 |
+
| 1.7097 | 17500 | 0.0417 |
|
| 669 |
+
| 1.7146 | 17550 | 0.0351 |
|
| 670 |
+
| 1.7195 | 17600 | 0.0367 |
|
| 671 |
+
| 1.7243 | 17650 | 0.0436 |
|
| 672 |
+
| 1.7292 | 17700 | 0.0392 |
|
| 673 |
+
| 1.7341 | 17750 | 0.04 |
|
| 674 |
+
| 1.7390 | 17800 | 0.0415 |
|
| 675 |
+
| 1.7439 | 17850 | 0.0418 |
|
| 676 |
+
| 1.7488 | 17900 | 0.0366 |
|
| 677 |
+
| 1.7537 | 17950 | 0.0433 |
|
| 678 |
+
| 1.7585 | 18000 | 0.0391 |
|
| 679 |
+
| 1.7634 | 18050 | 0.0377 |
|
| 680 |
+
| 1.7683 | 18100 | 0.0398 |
|
| 681 |
+
| 1.7732 | 18150 | 0.0396 |
|
| 682 |
+
| 1.7781 | 18200 | 0.0404 |
|
| 683 |
+
| 1.7830 | 18250 | 0.0405 |
|
| 684 |
+
| 1.7878 | 18300 | 0.0381 |
|
| 685 |
+
| 1.7927 | 18350 | 0.04 |
|
| 686 |
+
| 1.7976 | 18400 | 0.0404 |
|
| 687 |
+
| 1.8025 | 18450 | 0.0348 |
|
| 688 |
+
| 1.8074 | 18500 | 0.0397 |
|
| 689 |
+
| 1.8123 | 18550 | 0.042 |
|
| 690 |
+
| 1.8172 | 18600 | 0.0454 |
|
| 691 |
+
| 1.8220 | 18650 | 0.0384 |
|
| 692 |
+
| 1.8269 | 18700 | 0.0387 |
|
| 693 |
+
| 1.8318 | 18750 | 0.042 |
|
| 694 |
+
| 1.8367 | 18800 | 0.0413 |
|
| 695 |
+
| 1.8416 | 18850 | 0.0403 |
|
| 696 |
+
| 1.8465 | 18900 | 0.0417 |
|
| 697 |
+
| 1.8514 | 18950 | 0.0386 |
|
| 698 |
+
| 1.8562 | 19000 | 0.0417 |
|
| 699 |
+
| 1.8611 | 19050 | 0.0396 |
|
| 700 |
+
| 1.8660 | 19100 | 0.039 |
|
| 701 |
+
| 1.8709 | 19150 | 0.0403 |
|
| 702 |
+
| 1.8758 | 19200 | 0.0402 |
|
| 703 |
+
| 1.8807 | 19250 | 0.044 |
|
| 704 |
+
| 1.8855 | 19300 | 0.0413 |
|
| 705 |
+
| 1.8904 | 19350 | 0.0379 |
|
| 706 |
+
| 1.8953 | 19400 | 0.042 |
|
| 707 |
+
| 1.9002 | 19450 | 0.0389 |
|
| 708 |
+
| 1.9051 | 19500 | 0.0399 |
|
| 709 |
+
| 1.9100 | 19550 | 0.0405 |
|
| 710 |
+
| 1.9149 | 19600 | 0.0414 |
|
| 711 |
+
| 1.9197 | 19650 | 0.0406 |
|
| 712 |
+
| 1.9246 | 19700 | 0.037 |
|
| 713 |
+
| 1.9295 | 19750 | 0.0406 |
|
| 714 |
+
| 1.9344 | 19800 | 0.0433 |
|
| 715 |
+
| 1.9393 | 19850 | 0.0357 |
|
| 716 |
+
| 1.9442 | 19900 | 0.038 |
|
| 717 |
+
| 1.9490 | 19950 | 0.0444 |
|
| 718 |
+
| 1.9539 | 20000 | 0.0406 |
|
| 719 |
+
| 1.9588 | 20050 | 0.0343 |
|
| 720 |
+
| 1.9637 | 20100 | 0.0414 |
|
| 721 |
+
| 1.9686 | 20150 | 0.0359 |
|
| 722 |
+
| 1.9735 | 20200 | 0.0421 |
|
| 723 |
+
| 1.9784 | 20250 | 0.0352 |
|
| 724 |
+
| 1.9832 | 20300 | 0.0406 |
|
| 725 |
+
| 1.9881 | 20350 | 0.0403 |
|
| 726 |
+
| 1.9930 | 20400 | 0.0396 |
|
| 727 |
+
| 1.9979 | 20450 | 0.0378 |
|
| 728 |
+
|
| 729 |
+
</details>
|
| 730 |
+
|
| 731 |
+
### Framework Versions
|
| 732 |
+
- Python: 3.12.12
|
| 733 |
+
- Sentence Transformers: 5.2.1
|
| 734 |
+
- Transformers: 4.57.6
|
| 735 |
+
- PyTorch: 2.10.0+cu128
|
| 736 |
+
- Accelerate: 1.12.0
|
| 737 |
+
- Datasets: 4.3.0
|
| 738 |
+
- Tokenizers: 0.22.2
|
| 739 |
+
|
| 740 |
+
## Citation
|
| 741 |
+
|
| 742 |
+
### BibTeX
|
| 743 |
+
|
| 744 |
+
#### Sentence Transformers
|
| 745 |
+
```bibtex
|
| 746 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 747 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 748 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 749 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 750 |
+
month = "11",
|
| 751 |
+
year = "2019",
|
| 752 |
+
publisher = "Association for Computational Linguistics",
|
| 753 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 754 |
+
}
|
| 755 |
+
```
|
| 756 |
+
|
| 757 |
+
#### MultipleNegativesRankingLoss
|
| 758 |
+
```bibtex
|
| 759 |
+
@misc{henderson2017efficient,
|
| 760 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
| 761 |
+
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},
|
| 762 |
+
year={2017},
|
| 763 |
+
eprint={1705.00652},
|
| 764 |
+
archivePrefix={arXiv},
|
| 765 |
+
primaryClass={cs.CL}
|
| 766 |
+
}
|
| 767 |
+
```
|
| 768 |
+
|
| 769 |
+
<!--
|
| 770 |
+
## Glossary
|
| 771 |
+
|
| 772 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 773 |
+
-->
|
| 774 |
+
|
| 775 |
+
<!--
|
| 776 |
+
## Model Card Authors
|
| 777 |
+
|
| 778 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 779 |
+
-->
|
| 780 |
+
|
| 781 |
+
<!--
|
| 782 |
+
## Model Card Contact
|
| 783 |
+
|
| 784 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 785 |
+
-->
|
adapter_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": {
|
| 6 |
+
"base_model_class": "Qwen3Model",
|
| 7 |
+
"parent_library": "transformers.models.qwen3.modeling_qwen3",
|
| 8 |
+
"unsloth_fixed": true
|
| 9 |
+
},
|
| 10 |
+
"base_model_name_or_path": "unsloth/Qwen3-Embedding-0.6B",
|
| 11 |
+
"bias": "none",
|
| 12 |
+
"corda_config": null,
|
| 13 |
+
"ensure_weight_tying": false,
|
| 14 |
+
"eva_config": null,
|
| 15 |
+
"exclude_modules": null,
|
| 16 |
+
"fan_in_fan_out": false,
|
| 17 |
+
"inference_mode": true,
|
| 18 |
+
"init_lora_weights": true,
|
| 19 |
+
"layer_replication": null,
|
| 20 |
+
"layers_pattern": null,
|
| 21 |
+
"layers_to_transform": null,
|
| 22 |
+
"loftq_config": {},
|
| 23 |
+
"lora_alpha": 128,
|
| 24 |
+
"lora_bias": false,
|
| 25 |
+
"lora_dropout": 0,
|
| 26 |
+
"megatron_config": null,
|
| 27 |
+
"megatron_core": "megatron.core",
|
| 28 |
+
"modules_to_save": null,
|
| 29 |
+
"peft_type": "LORA",
|
| 30 |
+
"peft_version": "0.18.1",
|
| 31 |
+
"qalora_group_size": 16,
|
| 32 |
+
"r": 64,
|
| 33 |
+
"rank_pattern": {},
|
| 34 |
+
"revision": null,
|
| 35 |
+
"target_modules": [
|
| 36 |
+
"gate_proj",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"q_proj",
|
| 39 |
+
"k_proj",
|
| 40 |
+
"v_proj",
|
| 41 |
+
"up_proj",
|
| 42 |
+
"down_proj"
|
| 43 |
+
],
|
| 44 |
+
"target_parameters": null,
|
| 45 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 46 |
+
"trainable_token_indices": null,
|
| 47 |
+
"use_dora": false,
|
| 48 |
+
"use_qalora": false,
|
| 49 |
+
"use_rslora": false
|
| 50 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e36c44d6a67b847867b4fe98a805aebbb4e65aed84a8e98fbe9de930d710eacd
|
| 3 |
+
size 161530808
|
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_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "SentenceTransformer",
|
| 3 |
+
"__version__": {
|
| 4 |
+
"sentence_transformers": "5.2.1",
|
| 5 |
+
"transformers": "4.57.6",
|
| 6 |
+
"pytorch": "2.10.0+cu128"
|
| 7 |
+
},
|
| 8 |
+
"prompts": {
|
| 9 |
+
"query": "",
|
| 10 |
+
"document": ""
|
| 11 |
+
},
|
| 12 |
+
"default_prompt_name": null,
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "left",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|