This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. 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: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity

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, 'architecture': '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("along26/distilroberta-base-manglish-sentence-transformer")
# Run inference
sentences = [
    "To construct a factor analysis model, we will follow these steps:\n\n1. Collect the data: In this case, we have the survey data from 50 students rating their satisfaction level on a scale of 1 to 10 for three aspects: academics (A), social life (S), and campus facilities (F).\n\n2. Create a correlation matrix: Calculate the correlation coefficients between each pair of variables (A, S, and F) using the collected data. The correlation matrix will look like this:\n\n```\n      A      S      F\nA  1.000  r(A,S) r(A,F)\nS  r(A,S) 1.000  r(S,F)\nF  r(A,F) r(S,F) 1.000\n```\n\nwhere r(A,S), r(A,F), and r(S,F) are the correlation coefficients between academics and social life, academics and campus facilities, and social life and campus facilities, respectively.\n\n3. Determine the number of factors: To decide how many underlying factors can explain the correlations, we can use various methods, such as the Kaiser criterion (eigenvalues greater than 1), scree plot, or parallel analysis. For this example, let's use the Kaiser criterion.\n\n4. Extract the factors: Perform a factor analysis using a software or statistical tool (e.g., R, Python, SPSS) to extract the factors based on the chosen number of factors. The software will provide factor loadings, which represent the correlation between the original variables and the extracted factors.\n\n5. Interpret the factors: Analyze the factor loadings to understand the meaning of the extracted factors. If the loadings are high (e.g., greater than 0.5) for a particular variable, it means that the variable is strongly correlated with that factor.\n\nLet's assume we have calculated the correlation coefficients and performed the factor analysis. The results show that there is one underlying factor that explains the strong correlations between the three aspects (academics, social life, and campus facilities). This factor could be interpreted as the overall satisfaction with the college experience.\n\nIn conclusion, based on the factor analysis model, the three aspects of college experience (academics, social life, and campus facilities) are strongly correlated with each other, and one underlying factor can explain these correlations, which might represent the overall satisfaction with the college experience.",
    'U',
    'Suppose you have a dataset with 5 variables and you want to reduce the number of variables to 2. Using factor analysis, determine the two most important factors that explain the variation in the data. Include the factor loadings for each variable on each factor.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000, -1.0000,  1.0000],
#         [-1.0000,  1.0000, -1.0000],
#         [ 1.0000, -1.0000,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 424,311 training samples
Columns: sentence_0, sentence_1, and sentence_2
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 sentence_2
type string string string
details
min: 9 tokens
mean: 150.71 tokens
max: 256 tokens
min: 3 tokens
mean: 3.0 tokens
max: 3 tokens
min: 11 tokens
mean: 147.14 tokens
max: 256 tokens

Samples:

sentence_0	sentence_1	sentence_2
`Sebagai pengguna, saya ingin tahu sama ada terdapat sebarang usaha atau tindakan yang diambil oleh kerajaan atau badan kehakiman Malaysia untuk menangani kebimbangan ini tentang kadar perbicaraan yang perlahan dan meningkatkan kepercayaan orang ramai dalam proses tersebut?`	`E`	`Mengapa kadar perbicaraan dan prosiding undang-undang berkaitan 1MDB yang perlahan mencetuskan kekecewaan dan kritikan dalam kalangan rakyat Malaysia?`
Pertama, mari kita layan 2 orang yang mesti duduk bersama sebagai satu unit. Jadi sekarang, kami mempunyai 4 unit untuk disusun (pasangan dan 3 individu yang lain).[object Object][object Object]Terdapat 4! (4 faktorial) cara menyusun 4 unit ini, iaitu 4! = 4 × 3 × 2 × 1 = 24 cara.[object Object][object Object]Kini, dalam pasangan itu, terdapat 2! (2 faktorial) cara untuk menyusun 2 orang, iaitu 2! = 2 × 1 = 2 cara.[object Object][object Object]Jadi, untuk mencari jumlah cara untuk menempatkan 5 orang, kita darabkan bilangan cara untuk menyusun 4 unit dengan bilangan cara untuk mengatur orang dalam pasangan:[object Object][object Object]Jumlah cara = 24 (susunan 4 unit) × 2 (susunan dalam pasangan) = 48 cara.	`E`	Apabila mengatur orang di sekitar meja bulat, kita biasanya menganggap satu orang sebagai titik rujukan untuk mengelakkan mengira susunan yang sama beberapa kali disebabkan oleh putaran. Oleh itu, kami mempunyai 7 orang kawan yang tinggal untuk mengatur meja.[object Object][object Object]Bilangan cara untuk mengatur 7 rakan ini ialah 7! (7 faktorial), iaitu:[object Object][object Object]7! = 7 × 6 × 5 × 4 × 3 × 2 × 1 = 5,040[object Object][object Object]Oleh itu, terdapat 5,040 cara yang berbeza untuk duduk 8 rakan di sekitar meja bulat.
`How have Malaysia's international partners and institutions responded to the 1MDB scandal and Najib Razak's prosecution, and what impact has this had on the country's reputation and standing in the global community?`	`B`	`How has the international community responded to the 1MDB scandal and the allegations of corruption against Najib Razak, and what impact has this had on Malaysia's reputation as a whole?`

Loss: TripletLoss with these parameters:
json
1{ 2 "distance_metric": "TripletDistanceMetric.EUCLIDEAN", 3 "triplet_margin": 5 4}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 3
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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
bf16: False
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
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: False
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}
parallelism_config: 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
project: huggingface
trackio_space_id: trackio
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: no
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: True
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.0377	500	4.1322
0.0754	1000	3.2877
0.1131	1500	3.0609
0.1508	2000	3.047
0.1885	2500	3.0408
0.2262	3000	3.0383
0.2640	3500	3.0354
0.3017	4000	3.0329
0.3394	4500	3.0303
0.3771	5000	3.0269
0.4148	5500	3.023
0.4525	6000	3.0181
0.4902	6500	3.0128
0.5279	7000	3.0091
0.5656	7500	3.0066
0.6033	8000	3.0062
0.6410	8500	3.004
0.6787	9000	3.0032
0.7164	9500	3.0027
0.7541	10000	3.0022
0.7919	10500	3.0021
0.8296	11000	3.0016
0.8673	11500	3.0014
0.9050	12000	3.0012
0.9427	12500	3.001
0.9804	13000	3.0009
1.0181	13500	3.0008
1.0558	14000	3.0007
1.0935	14500	3.0011
1.1312	15000	3.0006
1.1689	15500	3.0005
1.2066	16000	3.0005
1.2443	16500	3.0004
1.2821	17000	3.0004
1.3198	17500	3.0004
1.3575	18000	3.0003
1.3952	18500	3.0003
1.4329	19000	3.0005
1.4706	19500	3.0003
1.5083	20000	3.0002
1.5460	20500	3.0002
1.5837	21000	3.0002
1.6214	21500	3.0002
1.6591	22000	3.0004
1.6968	22500	3.0002
1.7345	23000	3.0002
1.7722	23500	3.0001
1.8100	24000	3.0001
1.8477	24500	3.0001
1.8854	25000	3.0005
1.9231	25500	3.0001
1.9608	26000	3.0002
1.9985	26500	3.0002
2.0362	27000	3.0001
2.0739	27500	3.0001
2.1116	28000	3.0001
2.1493	28500	3.0001
2.1870	29000	3.0001
2.2247	29500	3.0001
2.2624	30000	3.0002
2.3002	30500	3.0001
2.3379	31000	3.0001
2.3756	31500	3.0001
2.4133	32000	3.0001
2.4510	32500	3.0001
2.4887	33000	3.0001
2.5264	33500	3.0001
2.5641	34000	3.0001
2.6018	34500	3.0001
2.6395	35000	3.0001
2.6772	35500	3.0003
2.7149	36000	3.0001
2.7526	36500	3.0001
2.7903	37000	3.0001
2.8281	37500	3.0003
2.8658	38000	3.0001
2.9035	38500	3.0001
2.9412	39000	3.0001
2.9789	39500	3.0001

Framework Versions

Python: 3.12.12
Sentence Transformers: 5.1.2
Transformers: 4.57.1
PyTorch: 2.8.0+cu126
Accelerate: 1.11.0
Datasets: 4.0.0
Tokenizers: 0.22.1

Citation

BibTeX

Sentence Transformers

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",
}

TripletLoss

bibtex

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

	sentence_0	sentence_1	sentence_2
type	string	string	string
details	min: 9 tokens mean: 150.71 tokens max: 256 tokens	min: 3 tokens mean: 3.0 tokens max: 3 tokens	min: 11 tokens mean: 147.14 tokens max: 256 tokens