metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:500
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/multi-qa-MiniLM-L6-cos-v1
widget:
  - source_sentence: Can I get academic adjustments for mental health reasons?
    sentences:
      - >-
        Yes, appropriate academic accommodations can be arranged through the
        disability services office with documentation from mental health
        professionals.
      - >-
        Yes, many companies conduct online aptitude tests, coding challenges, or
        domain-specific assessments as part of their selection process.
      - The hostel offers Wi-Fi, mess services, laundry, and recreational areas.
  - source_sentence: What are the hostel meal timings?
    sentences:
      - >-
        Career services include career counseling, resume workshops, interview
        coaching, networking events, alumni mentoring, and job search assistance
        for all students.
      - >-
        Fee concession applications can be submitted with financial
        documentation to demonstrate need. Merit-based and need-based
        concessions may be available.
      - >-
        Mess timings are typically breakfast 7:30-9:30 AM, lunch 12:00-2:00 PM,
        and dinner 7:00-9:00 PM. Special arrangements may be made during exams.
  - source_sentence: Is there a bond signing for certain jobs?
    sentences:
      - >-
        Yes, detailed placement statistics including company-wise data, salary
        ranges, and sector-wise placement percentages are available on the
        placement portal.
      - >-
        Some companies may require service agreements or bonds. All terms and
        conditions are clearly communicated during the pre-placement talk.
      - >-
        Emergency services are available 24/7 through campus security (extension
        911), medical emergencies (campus health center), and crisis
        intervention services.
  - source_sentence: Where is the medical center located?
    sentences:
      - >-
        Most companies require no active backlogs for placement eligibility.
        Clear all backlogs before the placement season to ensure maximum
        opportunities.
      - >-
        The campus medical center is located near the main administrative
        building and provides basic healthcare services during working hours.
      - >-
        Yes, photocopy and printing services are available at the library,
        administrative building, and near the main canteen with reasonable
        rates.
  - source_sentence: Are there mock interviews before placements?
    sentences:
      - >-
        Yes, mock interviews are conducted regularly to help students practice
        and improve their interview skills before actual placement interviews.
      - >-
        Overnight event permissions require advance approval from student
        affairs, security clearance, safety protocols, and may need faculty
        supervision for student organizations.
      - >-
        Final year students can typically choose 2-4 elective courses depending
        on their program. Check with your academic advisor for specific
        requirements.
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on sentence-transformers/multi-qa-MiniLM-L6-cos-v1

This is a sentence-transformers model finetuned from sentence-transformers/multi-qa-MiniLM-L6-cos-v1. 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/multi-qa-MiniLM-L6-cos-v1
Maximum Sequence Length: 512 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': 512, '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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'Are there mock interviews before placements?',
    'Yes, mock interviews are conducted regularly to help students practice and improve their interview skills before actual placement interviews.',
    'Overnight event permissions require advance approval from student affairs, security clearance, safety protocols, and may need faculty supervision for student organizations.',
]
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,  0.7937, -0.0089],
#         [ 0.7937,  1.0000,  0.0156],
#         [-0.0089,  0.0156,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 500 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 500 samples:
sentence_0 sentence_1
type string string
details
min: 7 tokens
mean: 11.04 tokens
max: 17 tokens

min: 13 tokens
mean: 26.67 tokens
max: 46 tokens

	sentence_0	sentence_1
type	string	string
details	min: 7 tokens mean: 11.04 tokens max: 17 tokens	min: 13 tokens mean: 26.67 tokens max: 46 tokens

Samples:

sentence_0	sentence_1
`What is the policy on retroactive course drops?`	`Retroactive drops are rare and require exceptional circumstances with documentation. Medical emergencies or administrative errors may qualify for consideration.`
`Can I get help for eating disorders?`	`Specialized counseling for eating disorders is available through the health center. Confidential support includes individual therapy and referrals to specialized treatment programs.`
`Are pets allowed in campus housing?`	`No, pets are not allowed in campus housing including hostels and faculty quarters due to health and safety regulations.`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 4
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: 4
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: 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: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Framework Versions

Python: 3.11.13
Sentence Transformers: 5.0.0
Transformers: 4.55.0
PyTorch: 2.6.0+cu124
Accelerate: 1.9.0
Datasets: 4.0.0
Tokenizers: 0.21.4

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",
}

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}
}