初始化项目,由ModelHub XC社区提供模型
Model: sultanbi/e5-base-kazakh Source: Original Platform
This commit is contained in:
commit
0b04fcff27
12 files changed
+430
No files matched your search
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"word_embedding_dimension": 768,
|
||||
"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
|
||||
}
|
||||
@@ -0,0 +1,208 @@
|
||||
---
|
||||
language:
|
||||
- multilingual
|
||||
- af
|
||||
- am
|
||||
- ar
|
||||
- as
|
||||
- az
|
||||
- be
|
||||
- bg
|
||||
- bn
|
||||
- br
|
||||
- bs
|
||||
- ca
|
||||
- cs
|
||||
- cy
|
||||
- da
|
||||
- de
|
||||
- el
|
||||
- en
|
||||
- eo
|
||||
- es
|
||||
- et
|
||||
- eu
|
||||
- fa
|
||||
- fi
|
||||
- fr
|
||||
- fy
|
||||
- ga
|
||||
- gd
|
||||
- gl
|
||||
- gu
|
||||
- ha
|
||||
- he
|
||||
- hi
|
||||
- hr
|
||||
- hu
|
||||
- hy
|
||||
- id
|
||||
- is
|
||||
- it
|
||||
- ja
|
||||
- jv
|
||||
- ka
|
||||
- kk
|
||||
- km
|
||||
- kn
|
||||
- ko
|
||||
- ku
|
||||
- ky
|
||||
- la
|
||||
- lo
|
||||
- lt
|
||||
- lv
|
||||
- mg
|
||||
- mk
|
||||
- ml
|
||||
- mn
|
||||
- mr
|
||||
- ms
|
||||
- my
|
||||
- ne
|
||||
- nl
|
||||
- 'no'
|
||||
- om
|
||||
- or
|
||||
- pa
|
||||
- pl
|
||||
- ps
|
||||
- pt
|
||||
- ro
|
||||
- ru
|
||||
- sa
|
||||
- sd
|
||||
- si
|
||||
- sk
|
||||
- sl
|
||||
- so
|
||||
- sq
|
||||
- sr
|
||||
- su
|
||||
- sv
|
||||
- sw
|
||||
- ta
|
||||
- te
|
||||
- th
|
||||
- tl
|
||||
- tr
|
||||
- ug
|
||||
- uk
|
||||
- ur
|
||||
- uz
|
||||
- vi
|
||||
- xh
|
||||
- yi
|
||||
- zh
|
||||
license: mit
|
||||
library_name: sentence-transformers
|
||||
tags:
|
||||
- kazakh
|
||||
- sentence-transformers
|
||||
- transformers
|
||||
- multilingual
|
||||
- sentence-similarity
|
||||
- feature-extraction
|
||||
---
|
||||
|
||||
|
||||
# sultanbi/e5-base-kazakh
|
||||
|
||||
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on a translated [Kazakh version of the SNLI dataset](https://huggingface.co/datasets/sultanbi/snli-kazakh). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
- **Model Type:** Sentence Transformer
|
||||
- **Base model:** [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) <!-- at revision 835193815a3936a24a0ee7dc9e3d48c1fbb19c55 -->
|
||||
- **Maximum Sequence Length:** 128 tokens
|
||||
- **Output Dimensionality:** 768 dimensions
|
||||
- **Similarity Function:** Cosine Similarity
|
||||
|
||||
### Full Model Architecture
|
||||
|
||||
```
|
||||
SentenceTransformer(
|
||||
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
|
||||
(1): Pooling({'word_embedding_dimension': 768, '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})
|
||||
(2): Normalize()
|
||||
)
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
### Direct Usage (Sentence Transformers)
|
||||
|
||||
First install the Sentence Transformers library:
|
||||
|
||||
```bash
|
||||
pip install -U sentence-transformers
|
||||
```
|
||||
|
||||
Then you can load this model and run inference.
|
||||
```python
|
||||
from sentence_transformers import SentenceTransformer
|
||||
|
||||
# Download from the 🤗 Hub
|
||||
model = SentenceTransformer("sultanbi/e5-base-kazakh")
|
||||
# Run inference
|
||||
sentences = [
|
||||
'query: Ақ көйлек киген аққұба әйел гүлді ағашта ақ құсты ұстап отыр.',
|
||||
'query: Балалар күлімсіреп, камераға қол бұлғап тұр.',
|
||||
'query: Үш бала көл жағасында тұр.',
|
||||
]
|
||||
embeddings = model.encode(sentences)
|
||||
print(embeddings.shape)
|
||||
# [3, 768]
|
||||
|
||||
# Get the similarity scores for the embeddings
|
||||
similarities = model.similarity(embeddings, embeddings)
|
||||
print(similarities.shape)
|
||||
# [3, 3]
|
||||
```
|
||||
## Evaluation
|
||||
|
||||
### Evaluation and comparison against multilingual-e5-base in kazakh tasks
|
||||
|
||||
| Task / Dataset | Metric | multilingual-e5-base | e5-base-kazakh | Δ (absolute) | Description |
|
||||
| ------------------------- | :----------------: | :------------------: | :---------------: | :-----------: | ---------------------------------------------------------- |
|
||||
| Kazakh SNLI (validation set) retrieval | R@1 | 0.433 | 0.887 | +0.454 | Monolingual semantic retrieval on translated SNLI (validation set) |
|
||||
| | R@5 | 0.619 | 0.984 | +0.365 | |
|
||||
| | R@10 | 0.710 | 0.994 | +0.284 | |
|
||||
| STS-B (val, Kazakh) | Pearson | 0.708 | 0.817 | +0.109 | Semantic similarity correlation (machine-translated STS-B) |
|
||||
| | Spearman | 0.721 | 0.825 | +0.104 | | |
|
||||
| Triplet Accuracy | — | 0.802 | 0.941 | +0.139 | Monolingual entailment discrimination |
|
||||
|
||||
### Framework Versions
|
||||
- Python: 3.11.13
|
||||
- Sentence Transformers: 4.1.0
|
||||
- Transformers: 4.52.4
|
||||
- PyTorch: 2.6.0+cu124
|
||||
- Accelerate: 1.8.1
|
||||
- Datasets: 3.6.0
|
||||
- Tokenizers: 0.21.2
|
||||
|
||||
## Citation
|
||||
|
||||
### BibTeX
|
||||
|
||||
```bibtex
|
||||
@article{wang2024multilingual,
|
||||
title={Multilingual E5 Text Embeddings: A Technical Report},
|
||||
author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
|
||||
journal={arXiv preprint arXiv:2402.05672},
|
||||
year={2024}
|
||||
}
|
||||
```
|
||||
|
||||
```bibtex
|
||||
@inproceedings{reimers-2019-sentence-bert,
|
||||
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
||||
author = "Reimers, Nils and Gurevych, Iryna",
|
||||
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
||||
month = "11",
|
||||
year = "2019",
|
||||
publisher = "Association for Computational Linguistics",
|
||||
url = "https://arxiv.org/abs/1908.10084",
|
||||
}
|
||||
```
|
||||
+27
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"architectures": [
|
||||
"XLMRobertaModel"
|
||||
],
|
||||
"attention_probs_dropout_prob": 0.1,
|
||||
"bos_token_id": 0,
|
||||
"classifier_dropout": null,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout_prob": 0.1,
|
||||
"hidden_size": 768,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3072,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 514,
|
||||
"model_type": "xlm-roberta",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 12,
|
||||
"output_past": true,
|
||||
"pad_token_id": 1,
|
||||
"position_embedding_type": "absolute",
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.52.4",
|
||||
"type_vocab_size": 1,
|
||||
"use_cache": true,
|
||||
"vocab_size": 250002
|
||||
}
|
||||
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"__version__": {
|
||||
"sentence_transformers": "4.1.0",
|
||||
"transformers": "4.52.4",
|
||||
"pytorch": "2.6.0+cu124"
|
||||
},
|
||||
"prompts": {},
|
||||
"default_prompt_name": null,
|
||||
"similarity_fn_name": "cosine"
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2efd54ba9021d1a9d1e245fbfc45f60432b5efb5f94a27ed5bcfa12b3c9a1dde
|
||||
size 1112197096
|
||||
@@ -0,0 +1,20 @@
|
||||
[
|
||||
{
|
||||
"idx": 0,
|
||||
"name": "0",
|
||||
"path": "",
|
||||
"type": "sentence_transformers.models.Transformer"
|
||||
},
|
||||
{
|
||||
"idx": 1,
|
||||
"name": "1",
|
||||
"path": "1_Pooling",
|
||||
"type": "sentence_transformers.models.Pooling"
|
||||
},
|
||||
{
|
||||
"idx": 2,
|
||||
"name": "2",
|
||||
"path": "2_Normalize",
|
||||
"type": "sentence_transformers.models.Normalize"
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"max_seq_length": 128,
|
||||
"do_lower_case": false
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
||||
size 5069051
|
||||
@@ -0,0 +1,51 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"cls_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"mask_token": {
|
||||
"content": "<mask>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"sep_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
|
||||
size 17082987
|
||||
@@ -0,0 +1,55 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"250001": {
|
||||
"content": "<mask>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"cls_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"extra_special_tokens": {},
|
||||
"mask_token": "<mask>",
|
||||
"model_max_length": 512,
|
||||
"pad_token": "<pad>",
|
||||
"sep_token": "</s>",
|
||||
"tokenizer_class": "XLMRobertaTokenizer",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
Reference in new issue
Block a user