You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

sentenceTransformer_nepali_embedding

This is a sentence-transformers model finetuned from jangedoo/all-MiniLM-L6-v2-nepali on the json dataset. It maps sentences & paragraphs to a 384-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: jangedoo/all-MiniLM-L6-v2-nepali
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- json
Language: nep
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("ritesh-07/fine_tuned_model_03")
# Run inference
sentences = [
    'राहदानी रद्द गर्न कस्तो सत्यताको घोषणा चाहिन्छ?',
    'राहदानी रद्द गर्न निवेदकले उल्लेखित विवरण साँचो भएको र प्रचलित कानून बमोजिम अपराध ठहरिने कुनै काम नगरेको सत्यताको घोषणा गर्नुपर्छ।',
    'नागरिकता टोलीले गलत तथ्य वा अपूर्ण जानकारी भएमा सर्जमिनको प्रतिवेदन रद्द गर्न सक्छ।',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Dataset: dim_384
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 384
}
```

Metric	Value
cosine_accuracy@1	0.2891
cosine_accuracy@3	0.5013
cosine_accuracy@5	0.6154
cosine_accuracy@10	0.7772
cosine_precision@1	0.2891
cosine_precision@3	0.1671
cosine_precision@5	0.1231
cosine_precision@10	0.0777
cosine_recall@1	0.2891
cosine_recall@3	0.5013
cosine_recall@5	0.6154
cosine_recall@10	0.7772
cosine_ndcg@10	0.5114
cosine_mrr@10	0.4288
cosine_map@100	0.4379

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 256
}
```

Metric	Value
cosine_accuracy@1	0.2971
cosine_accuracy@3	0.5225
cosine_accuracy@5	0.626
cosine_accuracy@10	0.7772
cosine_precision@1	0.2971
cosine_precision@3	0.1742
cosine_precision@5	0.1252
cosine_precision@10	0.0777
cosine_recall@1	0.2971
cosine_recall@3	0.5225
cosine_recall@5	0.626
cosine_recall@10	0.7772
cosine_ndcg@10	0.5196
cosine_mrr@10	0.4391
cosine_map@100	0.4483

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 128
}
```

Metric	Value
cosine_accuracy@1	0.2891
cosine_accuracy@3	0.504
cosine_accuracy@5	0.6127
cosine_accuracy@10	0.7772
cosine_precision@1	0.2891
cosine_precision@3	0.168
cosine_precision@5	0.1225
cosine_precision@10	0.0777
cosine_recall@1	0.2891
cosine_recall@3	0.504
cosine_recall@5	0.6127
cosine_recall@10	0.7772
cosine_ndcg@10	0.5134
cosine_mrr@10	0.4313
cosine_map@100	0.4398

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 64
}
```

Metric	Value
cosine_accuracy@1	0.2812
cosine_accuracy@3	0.4934
cosine_accuracy@5	0.6101
cosine_accuracy@10	0.7639
cosine_precision@1	0.2812
cosine_precision@3	0.1645
cosine_precision@5	0.122
cosine_precision@10	0.0764
cosine_recall@1	0.2812
cosine_recall@3	0.4934
cosine_recall@5	0.6101
cosine_recall@10	0.7639
cosine_ndcg@10	0.504
cosine_mrr@10	0.423
cosine_map@100	0.4317

Training Details

Training Dataset

json

Dataset: json
Size: 3,385 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 18 tokens
mean: 49.31 tokens
max: 103 tokens

min: 17 tokens
mean: 81.7 tokens
max: 256 tokens

	anchor	positive
type	string	string
details	min: 18 tokens mean: 49.31 tokens max: 103 tokens	min: 17 tokens mean: 81.7 tokens max: 256 tokens

Samples:

anchor	positive
`राहदानी नियमावली, २०७७ मा दस्तुर बुझाउने प्रक्रिया कस्तो छ?`	`राहदानी नियमावली, २०७७ मा दस्तुर तोकिएको बैङ्कमा बुझाई रसिद निवेदनमा संलग्न गर्नुपर्छ।`
`दफा ३ को उपदफा (६) मा विदेशी नागरिकसँग विवाह गरेकी नेपाली महिलाको सन्तानले कसरी नागरिकता प्राप्त गर्छ?`	दफा ३ को उपदफा (६) मा विदेशी नागरिकसँग विवाह गरेकी नेपाली महिला नागरिकबाट नेपालमा जन्मिएको व्यक्तिले, यदि निजको आमा र बाबु दुवै नेपाली नागरिक रहेछन् भने, वंशजको आधारमा नेपालको नागरिकता प्राप्त गर्नेछ।
`दफा ३ को उपदफा (४) मा कस्तो व्यवस्था थपिएको छ?`	दफा ३ को उपदफा (४) मा थपिएको व्यवस्था अनुसार, संवत् २०७२ साल असोज ३ गतेभन्दा अघि जन्मको आधारमा नेपालको नागरिकता प्राप्त गरेको नागरिकको सन्तानले, यदि बाबु र आमा दुवै नेपालको नागरिक रहेछन् भने, निजको उमेर सोह्र वर्ष पूरा भएपछि वंशजको आधारमा नेपालको नागरिकता प्राप्त गर्नेछ।

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        384,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: False
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 4
max_steps: -1
lr_scheduler_type: cosine
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: False
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: True
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_384_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
1.0	7	-	0.4635	0.4673	0.4674	0.4406
1.4528	10	2.6919	-	-	-	-
2.0	14	-	0.4977	0.5140	0.4963	0.4759
2.9057	20	1.0521	-	-	-	-
3.0	21	-	0.5111	0.5242	0.5130	0.5017
4.0	28	-	0.5114	0.5196	0.5134	0.504

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.11.13
Sentence Transformers: 4.1.0
Transformers: 4.54.0
PyTorch: 2.6.0+cu124
Accelerate: 1.9.0
Datasets: 4.0.0
Tokenizers: 0.21.2

Citation

BibTeX

Sentence Transformers

@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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    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},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Downloads last month: 1

Safetensors

Model size

22.7M params

Tensor type

F32

Model tree for ritesh-07/fine_tuned_model_03

Unable to build the model tree, the base model loops to the model itself. Learn more.

Evaluation results

Cosine Accuracy@1 on dim 384
self-reported

0.289
Cosine Accuracy@3 on dim 384
self-reported

0.501
Cosine Accuracy@5 on dim 384
self-reported

0.615
Cosine Accuracy@10 on dim 384
self-reported

0.777
Cosine Precision@1 on dim 384
self-reported

0.289
Cosine Precision@3 on dim 384
self-reported

0.167
Cosine Precision@5 on dim 384
self-reported

0.123
Cosine Precision@10 on dim 384
self-reported

0.078
Cosine Recall@1 on dim 384
self-reported

0.289
Cosine Recall@3 on dim 384
self-reported

0.501