Commit
•
f4e32a8
0
Parent(s):
Duplicate from universalml0/finetuned_embedding_model_e5-large-multilingual-large
Browse files- .gitattributes +36 -0
- 1_Pooling/config.json +10 -0
- README.md +477 -0
- config.json +28 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
.gitattributes
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz 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": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,477 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: intfloat/multilingual-e5-large-instruct
|
3 |
+
datasets: []
|
4 |
+
language: []
|
5 |
+
library_name: sentence-transformers
|
6 |
+
pipeline_tag: sentence-similarity
|
7 |
+
tags:
|
8 |
+
- sentence-transformers
|
9 |
+
- sentence-similarity
|
10 |
+
- feature-extraction
|
11 |
+
- generated_from_trainer
|
12 |
+
- dataset_size:45199
|
13 |
+
- loss:MultipleNegativesRankingLoss
|
14 |
+
widget:
|
15 |
+
- source_sentence: प्रधानमन्त्री नरेन्द्र मोदी सरकारका असफलताहरू के के हुन्?
|
16 |
+
sentences:
|
17 |
+
- पूर्वोत्तर राज्यहरूका मुख्य समस्याहरू के के हुन् र तिनीहरूको केन्द्रीय सरकारसँग
|
18 |
+
असन्तोष के हो?
|
19 |
+
- पूर्णांक के हो?
|
20 |
+
- नरेन्द्र मोदी सरकारले कुन क्षेत्रमा असफल भएको छ?
|
21 |
+
- source_sentence: 'मैले विचार गर्नुपर्ने कलेजहरू के के हुन्, विचार गर्नुपर्ने कारकहरू:
|
22 |
+
केएमसी म्यानिपल वा केएमसी मंगोलमा?'
|
23 |
+
sentences:
|
24 |
+
- मंगलोर शान्त वा हिंस्रक स्थान हो?
|
25 |
+
- पुरुषहरूको तुलनामा महिलाहरूको लागि यौनिक आनन्द बढी हुन्छ कि हुँदैन?
|
26 |
+
- के कसैले केएमसी मानिपाल र मंगलोरको संक्षिप्त तुलना गर्न सक्छ?
|
27 |
+
- source_sentence: म कसरी मेरो अङ्ग्रेजी भाषा सुधार गर्न सक्छु?
|
28 |
+
sentences:
|
29 |
+
- म कसरी एक नेचुरल अंग्रेजी वक्ता बन्न सक्छु?
|
30 |
+
- म जहाँ कुनै मूल अंग्रेजी वक्ताहरू छन् जो मेरो साथ मित्र बन्न चाहन्छन् र मलाई मद्दत
|
31 |
+
गर्न चाहन्छन्?
|
32 |
+
- ने टी २०१ 6 को लागि निजी कलेजहरूको लागि एमबीबीएसको लागि के कटअफ हुनेछ?
|
33 |
+
- source_sentence: समय यात्रा सम्भव छ कि छैन? यदि छ भने, कसरी?
|
34 |
+
sentences:
|
35 |
+
- अन्धकारमय वेब सुरक्षित छ कि छैन ब्राउज गर्न?
|
36 |
+
- यदि कुनै बितेको समय राम्रो थियो र समयको यात्रा सम्भव थियो भने म किन वर्तमान समयमा
|
37 |
+
बाँचिरहेको छु?
|
38 |
+
- भविष्यमा समय यात्रा सम्भव हुनेछ कि छैन?
|
39 |
+
- source_sentence: म कसरी बिस्तारै तौल घटाउन सक्छु?
|
40 |
+
sentences:
|
41 |
+
- कसरी कुनै केटाले त्यो केटीसँग बदला लिन सक्छ जसले उसलाई धोका दिएको छ?
|
42 |
+
- कस्तो प्रकारको आहार कसैले आहार नचाहने व्यक्तिका लागि उत्तम हुन्छ?
|
43 |
+
- वजन घटाउनको लागि कुनै राम्रो आहार हो?
|
44 |
+
---
|
45 |
+
|
46 |
+
# SentenceTransformer based on intfloat/multilingual-e5-large-instruct
|
47 |
+
|
48 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) on the universalml0/nepali_embedding_dataset 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.
|
49 |
+
|
50 |
+
## Model Details
|
51 |
+
|
52 |
+
### Model Description
|
53 |
+
- **Model Type:** Sentence Transformer
|
54 |
+
- **Base model:** [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) <!-- at revision baa7be480a7de1539afce709c8f13f833a510e0a -->
|
55 |
+
- **Maximum Sequence Length:** 512 tokens
|
56 |
+
- **Output Dimensionality:** 1024 tokens
|
57 |
+
- **Similarity Function:** Cosine Similarity
|
58 |
+
- **Training Dataset:**
|
59 |
+
- universalml0/nepali_embedding_dataset
|
60 |
+
<!-- - **Language:** Unknown -->
|
61 |
+
<!-- - **License:** Unknown -->
|
62 |
+
|
63 |
+
### Model Sources
|
64 |
+
|
65 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
66 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
67 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
68 |
+
|
69 |
+
### Full Model Architecture
|
70 |
+
|
71 |
+
```
|
72 |
+
SentenceTransformer(
|
73 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
|
74 |
+
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
75 |
+
(2): Normalize()
|
76 |
+
)
|
77 |
+
```
|
78 |
+
|
79 |
+
## Usage
|
80 |
+
|
81 |
+
### Direct Usage (Sentence Transformers)
|
82 |
+
|
83 |
+
First install the Sentence Transformers library:
|
84 |
+
|
85 |
+
```bash
|
86 |
+
pip install -U sentence-transformers
|
87 |
+
```
|
88 |
+
|
89 |
+
Then you can load this model and run inference.
|
90 |
+
```python
|
91 |
+
from sentence_transformers import SentenceTransformer
|
92 |
+
|
93 |
+
# Download from the 🤗 Hub
|
94 |
+
model = SentenceTransformer("universalml0/finetuned_embedding_model_e5-large-multilingual-large")
|
95 |
+
# Run inference
|
96 |
+
sentences = [
|
97 |
+
'म कसरी बिस्तारै तौल घटाउन सक्छु?',
|
98 |
+
'वजन घटाउनको लागि कुनै राम्रो आहार हो?',
|
99 |
+
'कस्तो प्रकारको आहार कसैले आहार नचाहने व्यक्तिका लागि उत्तम हुन्छ?',
|
100 |
+
]
|
101 |
+
embeddings = model.encode(sentences)
|
102 |
+
print(embeddings.shape)
|
103 |
+
# [3, 1024]
|
104 |
+
|
105 |
+
# Get the similarity scores for the embeddings
|
106 |
+
similarities = model.similarity(embeddings, embeddings)
|
107 |
+
print(similarities.shape)
|
108 |
+
# [3, 3]
|
109 |
+
```
|
110 |
+
|
111 |
+
<!--
|
112 |
+
### Direct Usage (Transformers)
|
113 |
+
|
114 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
115 |
+
|
116 |
+
</details>
|
117 |
+
-->
|
118 |
+
|
119 |
+
<!--
|
120 |
+
### Downstream Usage (Sentence Transformers)
|
121 |
+
|
122 |
+
You can finetune this model on your own dataset.
|
123 |
+
|
124 |
+
<details><summary>Click to expand</summary>
|
125 |
+
|
126 |
+
</details>
|
127 |
+
-->
|
128 |
+
|
129 |
+
<!--
|
130 |
+
### Out-of-Scope Use
|
131 |
+
|
132 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
133 |
+
-->
|
134 |
+
|
135 |
+
<!--
|
136 |
+
## Bias, Risks and Limitations
|
137 |
+
|
138 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
139 |
+
-->
|
140 |
+
|
141 |
+
<!--
|
142 |
+
### Recommendations
|
143 |
+
|
144 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
145 |
+
-->
|
146 |
+
|
147 |
+
## Training Details
|
148 |
+
|
149 |
+
### Training Dataset
|
150 |
+
|
151 |
+
#### universalml0/nepali_embedding_dataset
|
152 |
+
|
153 |
+
* Dataset: universalml0/nepali_embedding_dataset
|
154 |
+
* Size: 45,199 training samples
|
155 |
+
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
156 |
+
* Approximate statistics based on the first 1000 samples:
|
157 |
+
| | anchor | positive | negative |
|
158 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
|
159 |
+
| type | string | string | string |
|
160 |
+
| details | <ul><li>min: 7 tokens</li><li>mean: 17.53 tokens</li><li>max: 486 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 17.68 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 18.9 tokens</li><li>max: 156 tokens</li></ul> |
|
161 |
+
* Samples:
|
162 |
+
| anchor | positive | negative |
|
163 |
+
|:----------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------|
|
164 |
+
| <code>भारतीय सरकारले ५०० र १००० रुपयाको नोटमाथि प्रतिबन्ध लगाउनुको कारण के थियो?</code> | <code>भारतीय सरकारले ५०० र १००० को नोटलाई निष्क्रिय पारेको छ तर तिनीहरूलाई ५०० र २००० को नोटहरूसँग प्रतिस्थापन गरेको छ। के यो विरोधाभासी छैन?</code> | <code>भारतीय सरकारले किन चाहेको भए सीमित मात्रामा नोटहरू मुद्रण गर्न र बजेट घाटा क्लियर गर्न सक्दैन? विशेष गरी, किन कुनै पनि देशले यो गर्न सक्दैन?</code> |
|
165 |
+
| <code>भारतीय हुनुको अनुभूति कस्तो हुन्छ?</code> | <code>भारतीय हुनुको अनुभूति कस्तो हुन्छ?</code> | <code>भारतीय महिला हुनुको अनुभव कस्तो हुन्छ?</code> |
|
166 |
+
| <code>के कुनै व्यक्तिले edWisor मार्फत कुनै नौकरी पाएको छ?</code> | <code>एडवाइजर वैध छ र के कसैले यस मार्फत कुनै नौकरी पाएको छ?</code> | <code>एलिटमसको माध्यमबाट कसैले काम पाएको छ?</code> |
|
167 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
168 |
+
```json
|
169 |
+
{
|
170 |
+
"scale": 20.0,
|
171 |
+
"similarity_fct": "cos_sim"
|
172 |
+
}
|
173 |
+
```
|
174 |
+
|
175 |
+
### Training Hyperparameters
|
176 |
+
#### Non-Default Hyperparameters
|
177 |
+
|
178 |
+
- `per_device_train_batch_size`: 4
|
179 |
+
- `learning_rate`: 1e-06
|
180 |
+
- `num_train_epochs`: 1
|
181 |
+
- `warmup_ratio`: 0.3
|
182 |
+
- `bf16`: True
|
183 |
+
- `batch_sampler`: no_duplicates
|
184 |
+
|
185 |
+
#### All Hyperparameters
|
186 |
+
<details><summary>Click to expand</summary>
|
187 |
+
|
188 |
+
- `overwrite_output_dir`: False
|
189 |
+
- `do_predict`: False
|
190 |
+
- `eval_strategy`: no
|
191 |
+
- `prediction_loss_only`: True
|
192 |
+
- `per_device_train_batch_size`: 4
|
193 |
+
- `per_device_eval_batch_size`: 8
|
194 |
+
- `per_gpu_train_batch_size`: None
|
195 |
+
- `per_gpu_eval_batch_size`: None
|
196 |
+
- `gradient_accumulation_steps`: 1
|
197 |
+
- `eval_accumulation_steps`: None
|
198 |
+
- `torch_empty_cache_steps`: None
|
199 |
+
- `learning_rate`: 1e-06
|
200 |
+
- `weight_decay`: 0.0
|
201 |
+
- `adam_beta1`: 0.9
|
202 |
+
- `adam_beta2`: 0.999
|
203 |
+
- `adam_epsilon`: 1e-08
|
204 |
+
- `max_grad_norm`: 1.0
|
205 |
+
- `num_train_epochs`: 1
|
206 |
+
- `max_steps`: -1
|
207 |
+
- `lr_scheduler_type`: linear
|
208 |
+
- `lr_scheduler_kwargs`: {}
|
209 |
+
- `warmup_ratio`: 0.3
|
210 |
+
- `warmup_steps`: 0
|
211 |
+
- `log_level`: passive
|
212 |
+
- `log_level_replica`: warning
|
213 |
+
- `log_on_each_node`: True
|
214 |
+
- `logging_nan_inf_filter`: True
|
215 |
+
- `save_safetensors`: True
|
216 |
+
- `save_on_each_node`: False
|
217 |
+
- `save_only_model`: False
|
218 |
+
- `restore_callback_states_from_checkpoint`: False
|
219 |
+
- `no_cuda`: False
|
220 |
+
- `use_cpu`: False
|
221 |
+
- `use_mps_device`: False
|
222 |
+
- `seed`: 42
|
223 |
+
- `data_seed`: None
|
224 |
+
- `jit_mode_eval`: False
|
225 |
+
- `use_ipex`: False
|
226 |
+
- `bf16`: True
|
227 |
+
- `fp16`: False
|
228 |
+
- `fp16_opt_level`: O1
|
229 |
+
- `half_precision_backend`: auto
|
230 |
+
- `bf16_full_eval`: False
|
231 |
+
- `fp16_full_eval`: False
|
232 |
+
- `tf32`: None
|
233 |
+
- `local_rank`: 0
|
234 |
+
- `ddp_backend`: None
|
235 |
+
- `tpu_num_cores`: None
|
236 |
+
- `tpu_metrics_debug`: False
|
237 |
+
- `debug`: []
|
238 |
+
- `dataloader_drop_last`: False
|
239 |
+
- `dataloader_num_workers`: 0
|
240 |
+
- `dataloader_prefetch_factor`: None
|
241 |
+
- `past_index`: -1
|
242 |
+
- `disable_tqdm`: False
|
243 |
+
- `remove_unused_columns`: True
|
244 |
+
- `label_names`: None
|
245 |
+
- `load_best_model_at_end`: False
|
246 |
+
- `ignore_data_skip`: False
|
247 |
+
- `fsdp`: []
|
248 |
+
- `fsdp_min_num_params`: 0
|
249 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
250 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
251 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
252 |
+
- `deepspeed`: None
|
253 |
+
- `label_smoothing_factor`: 0.0
|
254 |
+
- `optim`: adamw_torch
|
255 |
+
- `optim_args`: None
|
256 |
+
- `adafactor`: False
|
257 |
+
- `group_by_length`: False
|
258 |
+
- `length_column_name`: length
|
259 |
+
- `ddp_find_unused_parameters`: None
|
260 |
+
- `ddp_bucket_cap_mb`: None
|
261 |
+
- `ddp_broadcast_buffers`: False
|
262 |
+
- `dataloader_pin_memory`: True
|
263 |
+
- `dataloader_persistent_workers`: False
|
264 |
+
- `skip_memory_metrics`: True
|
265 |
+
- `use_legacy_prediction_loop`: False
|
266 |
+
- `push_to_hub`: False
|
267 |
+
- `resume_from_checkpoint`: None
|
268 |
+
- `hub_model_id`: None
|
269 |
+
- `hub_strategy`: every_save
|
270 |
+
- `hub_private_repo`: False
|
271 |
+
- `hub_always_push`: False
|
272 |
+
- `gradient_checkpointing`: False
|
273 |
+
- `gradient_checkpointing_kwargs`: None
|
274 |
+
- `include_inputs_for_metrics`: False
|
275 |
+
- `eval_do_concat_batches`: True
|
276 |
+
- `fp16_backend`: auto
|
277 |
+
- `push_to_hub_model_id`: None
|
278 |
+
- `push_to_hub_organization`: None
|
279 |
+
- `mp_parameters`:
|
280 |
+
- `auto_find_batch_size`: False
|
281 |
+
- `full_determinism`: False
|
282 |
+
- `torchdynamo`: None
|
283 |
+
- `ray_scope`: last
|
284 |
+
- `ddp_timeout`: 1800
|
285 |
+
- `torch_compile`: False
|
286 |
+
- `torch_compile_backend`: None
|
287 |
+
- `torch_compile_mode`: None
|
288 |
+
- `dispatch_batches`: None
|
289 |
+
- `split_batches`: None
|
290 |
+
- `include_tokens_per_second`: False
|
291 |
+
- `include_num_input_tokens_seen`: False
|
292 |
+
- `neftune_noise_alpha`: None
|
293 |
+
- `optim_target_modules`: None
|
294 |
+
- `batch_eval_metrics`: False
|
295 |
+
- `eval_on_start`: False
|
296 |
+
- `eval_use_gather_object`: False
|
297 |
+
- `batch_sampler`: no_duplicates
|
298 |
+
- `multi_dataset_batch_sampler`: proportional
|
299 |
+
|
300 |
+
</details>
|
301 |
+
|
302 |
+
### Training Logs
|
303 |
+
<details><summary>Click to expand</summary>
|
304 |
+
|
305 |
+
| Epoch | Step | Training Loss |
|
306 |
+
|:------:|:-----:|:-------------:|
|
307 |
+
| 0.0088 | 100 | 0.8671 |
|
308 |
+
| 0.0177 | 200 | 0.8234 |
|
309 |
+
| 0.0265 | 300 | 0.8223 |
|
310 |
+
| 0.0354 | 400 | 0.7423 |
|
311 |
+
| 0.0442 | 500 | 0.6605 |
|
312 |
+
| 0.0531 | 600 | 0.5558 |
|
313 |
+
| 0.0619 | 700 | 0.4076 |
|
314 |
+
| 0.0708 | 800 | 0.3617 |
|
315 |
+
| 0.0796 | 900 | 0.3087 |
|
316 |
+
| 0.0885 | 1000 | 0.2747 |
|
317 |
+
| 0.0973 | 1100 | 0.2409 |
|
318 |
+
| 0.1062 | 1200 | 0.229 |
|
319 |
+
| 0.1150 | 1300 | 0.209 |
|
320 |
+
| 0.1239 | 1400 | 0.2556 |
|
321 |
+
| 0.1327 | 1500 | 0.2536 |
|
322 |
+
| 0.1416 | 1600 | 0.2092 |
|
323 |
+
| 0.1504 | 1700 | 0.2464 |
|
324 |
+
| 0.1593 | 1800 | 0.1727 |
|
325 |
+
| 0.1681 | 1900 | 0.281 |
|
326 |
+
| 0.1770 | 2000 | 0.2289 |
|
327 |
+
| 0.1858 | 2100 | 0.2065 |
|
328 |
+
| 0.1947 | 2200 | 0.1751 |
|
329 |
+
| 0.2035 | 2300 | 0.231 |
|
330 |
+
| 0.2124 | 2400 | 0.2127 |
|
331 |
+
| 0.2212 | 2500 | 0.1908 |
|
332 |
+
| 0.2301 | 2600 | 0.2131 |
|
333 |
+
| 0.2389 | 2700 | 0.1704 |
|
334 |
+
| 0.2478 | 2800 | 0.1923 |
|
335 |
+
| 0.2566 | 2900 | 0.1635 |
|
336 |
+
| 0.2655 | 3000 | 0.2061 |
|
337 |
+
| 0.2743 | 3100 | 0.1843 |
|
338 |
+
| 0.2832 | 3200 | 0.1443 |
|
339 |
+
| 0.2920 | 3300 | 0.1513 |
|
340 |
+
| 0.3009 | 3400 | 0.1879 |
|
341 |
+
| 0.3097 | 3500 | 0.2372 |
|
342 |
+
| 0.3186 | 3600 | 0.1542 |
|
343 |
+
| 0.3274 | 3700 | 0.2523 |
|
344 |
+
| 0.3363 | 3800 | 0.2055 |
|
345 |
+
| 0.3451 | 3900 | 0.1474 |
|
346 |
+
| 0.3540 | 4000 | 0.1647 |
|
347 |
+
| 0.3628 | 4100 | 0.1615 |
|
348 |
+
| 0.3717 | 4200 | 0.1271 |
|
349 |
+
| 0.3805 | 4300 | 0.1451 |
|
350 |
+
| 0.3894 | 4400 | 0.1887 |
|
351 |
+
| 0.3982 | 4500 | 0.1334 |
|
352 |
+
| 0.4071 | 4600 | 0.1962 |
|
353 |
+
| 0.4159 | 4700 | 0.1695 |
|
354 |
+
| 0.4248 | 4800 | 0.1561 |
|
355 |
+
| 0.4336 | 4900 | 0.1146 |
|
356 |
+
| 0.4425 | 5000 | 0.1381 |
|
357 |
+
| 0.4513 | 5100 | 0.1452 |
|
358 |
+
| 0.4602 | 5200 | 0.2388 |
|
359 |
+
| 0.4690 | 5300 | 0.1951 |
|
360 |
+
| 0.4779 | 5400 | 0.1142 |
|
361 |
+
| 0.4867 | 5500 | 0.182 |
|
362 |
+
| 0.4956 | 5600 | 0.1968 |
|
363 |
+
| 0.5044 | 5700 | 0.1744 |
|
364 |
+
| 0.5133 | 5800 | 0.1868 |
|
365 |
+
| 0.5221 | 5900 | 0.1452 |
|
366 |
+
| 0.5310 | 6000 | 0.1345 |
|
367 |
+
| 0.5398 | 6100 | 0.1318 |
|
368 |
+
| 0.5487 | 6200 | 0.218 |
|
369 |
+
| 0.5575 | 6300 | 0.2118 |
|
370 |
+
| 0.5664 | 6400 | 0.1972 |
|
371 |
+
| 0.5752 | 6500 | 0.0935 |
|
372 |
+
| 0.5841 | 6600 | 0.1991 |
|
373 |
+
| 0.5929 | 6700 | 0.1252 |
|
374 |
+
| 0.6018 | 6800 | 0.1128 |
|
375 |
+
| 0.6106 | 6900 | 0.1585 |
|
376 |
+
| 0.6195 | 7000 | 0.2293 |
|
377 |
+
| 0.6283 | 7100 | 0.2104 |
|
378 |
+
| 0.6372 | 7200 | 0.1416 |
|
379 |
+
| 0.6460 | 7300 | 0.2004 |
|
380 |
+
| 0.6549 | 7400 | 0.1446 |
|
381 |
+
| 0.6637 | 7500 | 0.1171 |
|
382 |
+
| 0.6726 | 7600 | 0.1386 |
|
383 |
+
| 0.6814 | 7700 | 0.1291 |
|
384 |
+
| 0.6903 | 7800 | 0.1546 |
|
385 |
+
| 0.6991 | 7900 | 0.1484 |
|
386 |
+
| 0.7080 | 8000 | 0.129 |
|
387 |
+
| 0.7168 | 8100 | 0.1873 |
|
388 |
+
| 0.7257 | 8200 | 0.1333 |
|
389 |
+
| 0.7345 | 8300 | 0.1713 |
|
390 |
+
| 0.7434 | 8400 | 0.1016 |
|
391 |
+
| 0.7522 | 8500 | 0.1519 |
|
392 |
+
| 0.7611 | 8600 | 0.1851 |
|
393 |
+
| 0.7699 | 8700 | 0.144 |
|
394 |
+
| 0.7788 | 8800 | 0.1488 |
|
395 |
+
| 0.7876 | 8900 | 0.1568 |
|
396 |
+
| 0.7965 | 9000 | 0.1672 |
|
397 |
+
| 0.8053 | 9100 | 0.1236 |
|
398 |
+
| 0.8142 | 9200 | 0.0973 |
|
399 |
+
| 0.8230 | 9300 | 0.1491 |
|
400 |
+
| 0.8319 | 9400 | 0.2251 |
|
401 |
+
| 0.8407 | 9500 | 0.1433 |
|
402 |
+
| 0.8496 | 9600 | 0.2634 |
|
403 |
+
| 0.8584 | 9700 | 0.1723 |
|
404 |
+
| 0.8673 | 9800 | 0.2373 |
|
405 |
+
| 0.8761 | 9900 | 0.1065 |
|
406 |
+
| 0.8850 | 10000 | 0.1578 |
|
407 |
+
| 0.8938 | 10100 | 0.1127 |
|
408 |
+
| 0.9027 | 10200 | 0.1632 |
|
409 |
+
| 0.9115 | 10300 | 0.19 |
|
410 |
+
| 0.9204 | 10400 | 0.0958 |
|
411 |
+
| 0.9292 | 10500 | 0.1029 |
|
412 |
+
| 0.9381 | 10600 | 0.1183 |
|
413 |
+
| 0.9469 | 10700 | 0.1779 |
|
414 |
+
| 0.9558 | 10800 | 0.1571 |
|
415 |
+
| 0.9646 | 10900 | 0.1666 |
|
416 |
+
| 0.9735 | 11000 | 0.1405 |
|
417 |
+
| 0.9823 | 11100 | 0.147 |
|
418 |
+
| 0.9912 | 11200 | 0.1428 |
|
419 |
+
| 1.0 | 11300 | 0.1724 |
|
420 |
+
|
421 |
+
</details>
|
422 |
+
|
423 |
+
### Framework Versions
|
424 |
+
- Python: 3.9.5
|
425 |
+
- Sentence Transformers: 3.0.1
|
426 |
+
- Transformers: 4.44.2
|
427 |
+
- PyTorch: 2.3.0+cu121
|
428 |
+
- Accelerate: 0.33.0
|
429 |
+
- Datasets: 2.21.0
|
430 |
+
- Tokenizers: 0.19.1
|
431 |
+
|
432 |
+
## Citation
|
433 |
+
|
434 |
+
### BibTeX
|
435 |
+
|
436 |
+
#### Sentence Transformers
|
437 |
+
```bibtex
|
438 |
+
@inproceedings{reimers-2019-sentence-bert,
|
439 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
440 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
441 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
442 |
+
month = "11",
|
443 |
+
year = "2019",
|
444 |
+
publisher = "Association for Computational Linguistics",
|
445 |
+
url = "https://arxiv.org/abs/1908.10084",
|
446 |
+
}
|
447 |
+
```
|
448 |
+
|
449 |
+
#### MultipleNegativesRankingLoss
|
450 |
+
```bibtex
|
451 |
+
@misc{henderson2017efficient,
|
452 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
453 |
+
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},
|
454 |
+
year={2017},
|
455 |
+
eprint={1705.00652},
|
456 |
+
archivePrefix={arXiv},
|
457 |
+
primaryClass={cs.CL}
|
458 |
+
}
|
459 |
+
```
|
460 |
+
|
461 |
+
<!--
|
462 |
+
## Glossary
|
463 |
+
|
464 |
+
*Clearly define terms in order to be accessible across audiences.*
|
465 |
+
-->
|
466 |
+
|
467 |
+
<!--
|
468 |
+
## Model Card Authors
|
469 |
+
|
470 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
471 |
+
-->
|
472 |
+
|
473 |
+
<!--
|
474 |
+
## Model Card Contact
|
475 |
+
|
476 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
477 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "intfloat/multilingual-e5-large-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.44.2",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.44.2",
|
5 |
+
"pytorch": "2.3.0+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9896ca3aa5099620001a7eba78c5dbf064c5b531ca15184e4913f40ef1549cd0
|
3 |
+
size 2239607176
|
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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
|
3 |
+
size 17082987
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_token": "<pad>",
|
52 |
+
"sep_token": "</s>",
|
53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
54 |
+
"unk_token": "<unk>"
|
55 |
+
}
|