初始化项目，由ModelHub XC社区提供模型
Model: rasyosef/embedding-amharic-base Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
10
1_Pooling/config.json
Normal file
10
1_Pooling/config.json
Normal file
@@ -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
|
||||
}
|
||||
305
README.md
Normal file
305
README.md
Normal file
@@ -0,0 +1,305 @@
|
||||
---
|
||||
language:
|
||||
- am
|
||||
license: mit
|
||||
tags:
|
||||
- sentence-transformers
|
||||
- sentence-similarity
|
||||
- feature-extraction
|
||||
- generated_from_trainer
|
||||
- dataset_size:245876
|
||||
- loss:MatryoshkaLoss
|
||||
- loss:MultipleNegativesRankingLoss
|
||||
base_model: rasyosef/roberta-base-amharic
|
||||
widget:
|
||||
- source_sentence: በኢትዮጵያ ለመጀመሪያ ጊዜ ወታደራዊ ስልጠና የወሰዱ ዕጩ ዲፕሎማቶች ተመረቁ
|
||||
sentences:
|
||||
- የውጭ ጉዳይ ሚኒስቴር ከሜጀር ጄነራል ሀየሎም አርአያ ወታደራዊ አካዳሚ ጋር በመተባበር በኢትዮጵያ ለመጀመሪያ ጊዜ ወታደራዊ
|
||||
ስልጠና የወሰዱ ዲፕሎማቶችን አስመረቀ፡፡በወታደራዊ አካዳሚው ትላንት በተካሄደ የምርቃት ሥነ- ስርዓት ስልጠናውን ላገኙ 89
|
||||
ዕጩ ድፕሎማቶች የምስክር ወረቀት ተበረክቷል።
|
||||
- አዲስ አበባ፣ የካቲት 19፣ 2012 (ኤፍ.ቢ.ሲ) የኢፌዴሪ አየር ኃይል ለከፍተኛ መኮንኖች የማዕረግ እድገት ሰጥቷል።አየር
|
||||
ኃይሉ በዛሬው እለት በቢሾፍቱ በሚገኘው የኢፌዴሪ አየር ኃይል ጠቅላይ መምሪያ ባካሄደው ስነ ስርዓት ላይ የኢፌዴሪ ጦር ኃይሎች
|
||||
ምክተል ኤታማዦር ሹም ጄኔራል ብርሃኑ ጁላ እና የኢፌዴሪ አየር ኃይል ዋና አዛዥ ሜጀር ጄኔራል ይልማ መርዳሳን ጨምሮ ከፍተኛ
|
||||
አመራሮች ተገኝተዋል።በስነ ስርዓቱ ላይ 106 ለሚሆኑ መኮንኖች በአየር ኃይል ዋና አዛዥ ሜጀር ጄኔራል ይልማ መርዳሳ የተለያዩ
|
||||
የማዕረግ እድገቶችን ሰጥተዋል።
|
||||
- source_sentence: ኢትዮጵያ ኢንተርኔትን በመዝጋቷ ከ130 ሚሊዮን ዶላር በላይ አጣች
|
||||
sentences:
|
||||
- የአሜሪካ ድምፅ ባለፉት ሰባ አምስት ዓመታት ውስጥ በዓለም ዙሪያ ያሉ የተለያዩ አድማጮችና ተመልካቾች ከሌሎች ምንጮች ሊያገኟቸው
|
||||
የማይችሏቸውን መረጃዎች ለዓለም ሲያደርስ መቆየቱን ዋና ዳይሬክተሯ አማንዳ ቤኔት ገልፀዋል።
|
||||
- የተቋሙ ጥናት የኢንተርኔን መዘጋት በሃገራት ምጣኔ ሐብት ላይ ያደረሰውን ጉዳት በተለያዩ መለኪያዎች የገመተ ሲሆን፤ በዚህም
|
||||
መሰረት ኢትዮጵያ ለ36 ቀናት ያህል ኢንተርኔትን በዘጋችበት እንዲሁም ለሰባት ቀናት ያህል በነበረው የማኅበራዊ ሚዲያ መናወጥ\
|
||||
ወቅት በጥቅሉ ከ130 ሚሊዮን ዶላር በላይ አጥታለች ይላል።
|
||||
|
||||
pipeline_tag: text-retrieval
|
||||
library_name: sentence-transformers
|
||||
metrics:
|
||||
- cosine_accuracy@1
|
||||
- cosine_accuracy@3
|
||||
- cosine_accuracy@5
|
||||
- cosine_accuracy@10
|
||||
- cosine_precision@1
|
||||
- cosine_precision@3
|
||||
- cosine_precision@5
|
||||
- cosine_precision@10
|
||||
- cosine_recall@1
|
||||
- cosine_recall@3
|
||||
- cosine_recall@5
|
||||
- cosine_recall@10
|
||||
- cosine_ndcg@10
|
||||
- cosine_mrr@10
|
||||
- cosine_map@100
|
||||
model-index:
|
||||
- name: RoBERTa Amharic Embed Base
|
||||
results:
|
||||
- task:
|
||||
type: information-retrieval
|
||||
name: Information Retrieval
|
||||
dataset:
|
||||
name: dim 768
|
||||
type: dim_768
|
||||
metrics:
|
||||
- type: cosine_recall@5
|
||||
value: 0.869800820152314
|
||||
name: Cosine Recall@5
|
||||
- type: cosine_recall@10
|
||||
value: 0.9050966608084359
|
||||
name: Cosine Recall@10
|
||||
- type: cosine_ndcg@10
|
||||
value: 0.8036666074756674
|
||||
name: Cosine Ndcg@10
|
||||
- type: cosine_mrr@10
|
||||
value: 0.7707977655033881
|
||||
name: Cosine Mrr@10
|
||||
- task:
|
||||
type: information-retrieval
|
||||
name: Information Retrieval
|
||||
dataset:
|
||||
name: dim 256
|
||||
type: dim_256
|
||||
metrics:
|
||||
- type: cosine_recall@5
|
||||
value: 0.8646748681898067
|
||||
name: Cosine Recall@5
|
||||
- type: cosine_recall@10
|
||||
value: 0.9020210896309314
|
||||
name: Cosine Recall@10
|
||||
- type: cosine_ndcg@10
|
||||
value: 0.7977610383416281
|
||||
name: Cosine Ndcg@10
|
||||
- type: cosine_mrr@10
|
||||
value: 0.764035577128722
|
||||
name: Cosine Mrr@10
|
||||
datasets:
|
||||
- rasyosef/Amharic-Passage-Retrieval-Dataset-V2
|
||||
---
|
||||
|
||||
# Embedding-Amharic-Base
|
||||
|
||||
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [rasyosef/roberta-base-amharic](https://huggingface.co/rasyosef/roberta-base-amharic). 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.
|
||||
|
||||
It was introduced in the paper [The Multilingual Curse at the Retrieval Layer: Evidence from Amharic](https://huggingface.co/papers/2605.24556).
|
||||
|
||||
- **Code:** [GitHub Repository](https://github.com/rasyosef/amharic-neural-ir)
|
||||
- **Paper:** [The Multilingual Curse at the Retrieval Layer: Evidence from Amharic](https://huggingface.co/papers/2605.24556)
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
- **Model Type:** Sentence Transformer
|
||||
- **Base model:** [rasyosef/roberta-base-amharic](https://huggingface.co/rasyosef/roberta-base-amharic) <!-- at revision b1a3d2c267262e2b82c83be9d4e59db762a5e931 -->
|
||||
- **Maximum Sequence Length:** 510 tokens
|
||||
- **Output Dimensionality:** 768 dimensions
|
||||
- **Similarity Function:** Cosine Similarity
|
||||
<!-- - **Training Dataset:** Unknown -->
|
||||
- **Language:** am
|
||||
- **License:** mit
|
||||
|
||||
### Full Model Architecture
|
||||
|
||||
```
|
||||
SentenceTransformer(
|
||||
(0): Transformer({'max_seq_length': 510, '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
|
||||
|
||||
model = SentenceTransformer("rasyosef/embedding-amharic-base")
|
||||
|
||||
# What is the capital of Ethiopia? / France
|
||||
queries = ['የኢትዮጵያ ዋና ከተማ ማናት?', 'የፈረንሳይ ዋና ከተማ ማናት?']
|
||||
|
||||
# Addis Ababa, Gondar, Paris, London, Washington D.C.
|
||||
documents = ['አዲስ አበባ', 'ጎንደር', 'ፓሪስ', 'ለንደን', 'ዋሽንግተን ዲሲ']
|
||||
|
||||
# Compute embeddings
|
||||
query_embeddings = model.encode_query(queries) # [2, 768]
|
||||
document_embeddings = model.encode_document(documents) # [5, 768]
|
||||
|
||||
# Calculate semantic similarity
|
||||
similarities = model.similarity(
|
||||
query_embeddings,
|
||||
document_embeddings
|
||||
)
|
||||
|
||||
print(similarities)
|
||||
# tensor([[0.5075, 0.3114, 0.0798, 0.1967, 0.1340],
|
||||
# [0.1777, 0.0770, 0.5714, 0.2596, 0.1076]])
|
||||
```
|
||||
|
||||
<!--
|
||||
### Direct Usage (Transformers)
|
||||
|
||||
<details><summary>Click to see the direct usage in Transformers</summary>
|
||||
|
||||
</details>
|
||||
-->
|
||||
|
||||
<!--
|
||||
### Downstream Usage (Sentence Transformers)
|
||||
|
||||
You can finetune this model on your own dataset.
|
||||
|
||||
<details><summary>Click to expand</summary>
|
||||
|
||||
</details>
|
||||
-->
|
||||
|
||||
<!--
|
||||
### Out-of-Scope Use
|
||||
|
||||
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
||||
-->
|
||||
|
||||
## Evaluation
|
||||
|
||||
### Metrics
|
||||
|
||||
#### Information Retrieval
|
||||
|
||||
* Dataset: `dim_768`
|
||||
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
|
||||
```json
|
||||
{
|
||||
"truncate_dim": 768
|
||||
}
|
||||
```
|
||||
|
||||
| Metric | Value |
|
||||
|:--------------------|:-----------|
|
||||
| cosine_recall@5 | 0.8698 |
|
||||
| cosine_recall@10 | 0.9051 |
|
||||
| **cosine_ndcg@10** | **0.8037** |
|
||||
| cosine_mrr@10 | 0.7708 |
|
||||
|
||||
#### Information Retrieval
|
||||
|
||||
* Dataset: `dim_256`
|
||||
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
|
||||
```json
|
||||
{
|
||||
"truncate_dim": 256
|
||||
}
|
||||
```
|
||||
|
||||
| Metric | Value |
|
||||
|:--------------------|:-----------|
|
||||
| cosine_recall@5 | 0.8647 |
|
||||
| cosine_recall@10 | 0.902 |
|
||||
| **cosine_ndcg@10** | **0.7978** |
|
||||
| cosine_mrr@10 | 0.764 |
|
||||
|
||||
<!--
|
||||
## Bias, Risks and Limitations
|
||||
|
||||
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
||||
-->
|
||||
|
||||
<!--
|
||||
### Recommendations
|
||||
|
||||
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
||||
-->
|
||||
|
||||
## Training Details
|
||||
|
||||
<details>
|
||||
|
||||
### Training Hyperparameters
|
||||
#### Non-Default Hyperparameters
|
||||
|
||||
- `eval_strategy`: epoch
|
||||
- `per_device_train_batch_size`: 64
|
||||
- `per_device_eval_batch_size`: 64
|
||||
- `gradient_accumulation_steps`: 2
|
||||
- `learning_rate`: 6e-05
|
||||
- `num_train_epochs`: 6
|
||||
- `lr_scheduler_type`: cosine
|
||||
- `warmup_ratio`: 0.025
|
||||
- `fp16`: True
|
||||
- `load_best_model_at_end`: True
|
||||
- `optim`: adamw_torch_fused
|
||||
- `batch_sampler`: no_duplicates
|
||||
|
||||
### Training Logs
|
||||
| Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_256_cosine_ndcg@10 |
|
||||
|:-----:|:----:|:-------------:|:----------------------:|:----------------------:|
|
||||
| -1 | -1 | - | 0.0735 | 0.0582 |
|
||||
| 1.0 | 1921 | 0.6769 | 0.7826 | 0.7751 |
|
||||
| 2.0 | 3842 | 0.07 | 0.7894 | 0.7829 |
|
||||
| 3.0 | 5763 | 0.0254 | 0.8030 | 0.7953 |
|
||||
| 4.0 | 7684 | 0.0139 | 0.8037 | 0.7978 |
|
||||
|
||||
|
||||
### Framework Versions
|
||||
- Python: 3.11.13
|
||||
- Sentence Transformers: 4.1.0
|
||||
- Transformers: 4.52.4
|
||||
- PyTorch: 2.7.1+cu126
|
||||
- Accelerate: 1.7.0
|
||||
- Datasets: 3.6.0
|
||||
- Tokenizers: 0.21.1
|
||||
|
||||
</details>
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@inproceedings{alemneh2026amharicir,
|
||||
title = {The Multilingual Curse at the Retrieval Layer: Evidence from Amharic},
|
||||
author = {Alemneh, Yosef Worku and Mekonnen, Kidist Amde and de Rijke, Maarten},
|
||||
booktitle = {Proceedings of the 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM), ACL 2026},
|
||||
year = {2026},
|
||||
}
|
||||
```
|
||||
<!--
|
||||
## Glossary
|
||||
|
||||
*Clearly define terms in order to be accessible across audiences.*
|
||||
-->
|
||||
|
||||
<!--
|
||||
## Model Card Authors
|
||||
|
||||
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
||||
-->
|
||||
|
||||
<!--
|
||||
## Model Card Contact
|
||||
|
||||
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
||||
-->
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"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": 512,
|
||||
"model_type": "xlm-roberta",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 12,
|
||||
"output_past": true,
|
||||
"pad_token_id": 1,
|
||||
"position_embedding_type": "absolute",
|
||||
"tokenizer_class": "XLMRobertaTokenizerFast",
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.52.4",
|
||||
"type_vocab_size": 1,
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
10
config_sentence_transformers.json
Normal file
10
config_sentence_transformers.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"__version__": {
|
||||
"sentence_transformers": "4.1.0",
|
||||
"transformers": "4.52.4",
|
||||
"pytorch": "2.7.1+cu126"
|
||||
},
|
||||
"prompts": {},
|
||||
"default_prompt_name": null,
|
||||
"similarity_fn_name": "cosine"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:755500327293eea2d2ff77daae6acb3a0a1b2729c4463b1c3c679331a622d2ec
|
||||
size 442488672
|
||||
20
modules.json
Normal file
20
modules.json
Normal file
@@ -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"
|
||||
}
|
||||
]
|
||||
4
sentence_bert_config.json
Normal file
4
sentence_bert_config.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"max_seq_length": 510,
|
||||
"do_lower_case": false
|
||||
}
|
||||
51
special_tokens_map.json
Normal file
51
special_tokens_map.json
Normal file
@@ -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
|
||||
}
|
||||
}
|
||||
128176
tokenizer.json
Normal file
128176
tokenizer.json
Normal file
File diff suppressed because one or more lines are too long
55
tokenizer_config.json
Normal file
55
tokenizer_config.json
Normal file
@@ -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
|
||||
},
|
||||
"4": {
|
||||
"content": "<mask>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"cls_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"extra_special_tokens": {},
|
||||
"mask_token": "<mask>",
|
||||
"model_max_length": 510,
|
||||
"pad_token": "<pad>",
|
||||
"sep_token": "</s>",
|
||||
"tokenizer_class": "XLMRobertaTokenizerFast",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
Reference in New Issue
Block a user