SentenceTransformer based on sentence-transformers/distiluse-base-multilingual-cased-v1

This is a sentence-transformers model finetuned from sentence-transformers/distiluse-base-multilingual-cased-v1. It maps sentences & paragraphs to a 512-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/distiluse-base-multilingual-cased-v1
Maximum Sequence Length: 128 tokens
Output Dimensionality: 512 tokens
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': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel 
  (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): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)

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("sentence_transformers_model_id")
# Run inference
sentences = [
    'EDUCATION\nBA in Management Information Systems\nDuy Tan University (2021 - Expected completion 05/2025)\nGPA: 3.6/4.0\nTECHNICAL SKILLS\nFrontend:\n\nLanguages ??& Frameworks: HTML, CSS, JavaScript, TypeScript\nLibraries & Tools: TailwindCSS, React.js, Next.js\nBackend:\n\nMain Framework: NestJS, ExpressJS\nDatabase & ORM: PostgreSQL, MongoDB, TypeOrm, Mongoose\nCloud Services: AWS, Elasticsearch\n\nMessaging & Streaming: KafkaJS, WebSocket\n\nContainer & Deployment: Docker\n\nOther Tools:\n\nVersion Control: Git, GitHub\nCI/CD: Vercel\nPERSONAL PROJECTS\nNestgres\nGitHub Repository: Learning Project with NestJS and PostgreSQL. Integrate AWS S3 for file storage, Docker for containerization, and Elasticsearch for advanced search. This project helped me gain a deep understanding of building a scalable backend system and handling big data.\n\nSimple Todo\nLive Demo: A simple to-do list application to reinforce my knowledge of React, including component architecture, state management, and efficient rendering.\n\nNestactube\nGitHub Repository: A full-stack video platform combining NestJS and React, serving video streaming from backend to frontend. Focusing on handling large media files and ensuring smooth video playback.\n\nMindForge\nGitHub Repository - Live Demo: Clone of Notion with note creation and editing features. Using Convex for secure data storage and Clerk for user authentication. The project helped me develop a friendly interface and handle complex data structures.\n\nAWARDS & ACHIEVEMENTS\nExcellent Academic Performance - 2022, 2023\nBoeing Scholarship - 2022, 2023\nThird Prize - Duy Tan Informatics Competition, 2023\nThird Prize - Informatics Olympiad (non-specialist group), 2023\nCERTIFICATIONS\nFoundations of User Experience (UX) Design',
    "Skills and Qualifications Required:\n\nQualifications:\n\nBachelor's degree in Computer Science, Computer Networking or related fields from Universities such as University of Science, University of Natural Sciences, University of Information Technology, Vietnam National University, Ho Chi Minh City, or Vietnam National University, Hanoi.\nOnly candidates with academic background and practical experience directly related to Information Technology will be considered (candidates from short-term or non-major programs will not be accepted).\nGrade Point Average (GPA):\n\nMinimum GPA: 7.0 (on a scale of 10) or 2.8 (on a scale of 4)\n\nTechnical Skills:\n\nStrong programming skills with C/C++, along with knowledge of object-oriented programming.\nHave practical experience (1 year or more) working with C/C++.\nBasic knowledge of operating systems such as Windows, Linux, and MacOS.\nUnderstanding of network protocols and security principles. Strong team working skills and problem solving ability.",
    "Qualifications:\n\nExpected Skills:\n\nProgramming Languages: Proficiency in C# and experience working with Unity3D.\nGame Development: Solid understanding of game mechanics, UI/UX, and physics.\nCybersecurity Tools: Experience with cyber security tools with a defensive/offensive mindset.\nPerformance Optimization: Solid skills in game optimization and memory management.\nVersion Management Knowledge: Familiarity with Git or similar version control systems.\nPreferred Skills:\n\nAR/VR development experience is a plus.\nKnowledge of multi-player and networking concepts, along with creativity.\nEducation:\n\nBachelor's degree in Computer Science, Game Development, or related field, or equivalent hands-on experience.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

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

Training Details

Training Dataset

Unnamed Dataset

Size: 5,108 training samples
Columns: sentence_0, sentence_1, and label

Approximate statistics based on the first 1000 samples:

	sentence_0	sentence_1	label
type	string	string	float
details	min: 44 tokens mean: 106.09 tokens max: 128 tokens	min: 46 tokens mean: 117.55 tokens max: 128 tokens	min: 0.5 mean: 0.66 max: 0.74

Samples:

sentence_0	sentence_1	label
EDUCATION Software Engineer (CMU) Duy Tan University, 09/2021 - Present GPA: 3.6/4.0 OUTSTANDING PROJECTS Fashion Store Website Time: 17/01 - 25/02 Role: Backend Developer Features: Register, log in, log out (customer rights) Log in and manage with admin rights Add, edit, delete products and vouchers (admin) Display product and voucher list Technology: Frontend: Customer page & admin dashboard (edit from available template) Backend: Typescript (NestJS) Database: MongoDB (Mongoose) GitHub Link: Fashion Store Project SKILLS Front-end: HTML, CSS, JavaScript, Bootstrap 5, ReactJS Back-end: ExpressJS, NestJS (TypeScript) Database: MySQL, MongoDB OTHER TOOLS & TECHNOLOGIES Tools: Git (GitHub), Docker, Postman Other languages: C# (ASP.NET), Java (Spring Boot) LANGUAGES English: Good communication and reading skills	Professional Qualifications: Experience: Minimum 2 years of experience working with Java, proficient in Spring Boot. Frontend Framework: Proficient in using one of the Frontend frameworks (such as Vue, React,...) to develop interactive user interfaces. Database: Experience working with relational databases such as MS SQL Server, Oracle, PostgreSQL, MongoDB. Microservice Architecture: Experience with microservice architecture and containerization technologies such as Kubernetes/Docker. Multitasking: Ability to handle multitasking, multithreading, multiprocessing, and mechanisms such as hash tables, file processing mechanisms. API Integration: Experience in integrating/developing RESTful, SOAP, TCP/IP APIs. Operating System: Experience working with Enterprise Linux and Windows Server operating systems.	`0.65`
`EDUCATION HISTORY University of Roseton Master of Science in Software Engineering`	Graduated: 2020 Best Thesis Awardee Berou Solutions Scholarship Recipient De Loureigh University Bachelor of Science in Computer Science	Graduated: 2016 (Cum Laude) Founder of DLU Programming Club Hackathon Champion Beechtown 2015 RELEVANT SKILLS Programming Languages: JavaScript, C/C++, Java, Python, Kotlin, Go Core Skills: Problem Solving, Team Communication
`EDUCATION Bachelor of Science in Computer Science Rutgers University ? New Brunswick, NJ 2008 - 2012 SKILLS HTML CSS JavaScript React jQuery Angular.js Vue.js Enzyme Jest Git`	ABBANK Skill requirements: Minimum 5 years of experience as a BA in CLIMS system. Experience in lending activities. Experience in developing test scenarios and test plans for software projects. Understanding of software development processes. Ensure compliance with application development standards and quality processes. Ability to analyze and resolve complex technical issues, provide feasible and timely solutions. Effective communication and teamwork skills when collaborating with different functional groups. Focus on Agile implementation and willingness to learn and grow from experience. Education requirements: University degree in IT, banking, finance or related fields. Language requirements: Being able to communicate in English is an advantage.	`0.62`

Loss: CosineSimilarityLoss with these parameters:

{
    "loss_fct": "torch.nn.modules.loss.MSELoss"
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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: 16
per_device_eval_batch_size: 16
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
use_ipex: 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}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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
dispatch_batches: None
split_batches: 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
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss
1.5625	500	0.0023

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.2.1
Transformers: 4.44.2
PyTorch: 2.5.0+cu121
Accelerate: 0.34.2
Datasets: 3.1.0
Tokenizers: 0.19.1

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",
}

truongcongminh
/

AI_captone1