NAdine3 / README.md

yazied49

Initial upload

935b04f verified 9 months ago

preview code

raw

history blame contribute delete

18 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:20000
  - loss:CosineSimilarityLoss
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
widget:
  - source_sentence: >-
      Question: Is this describing a (1) directly correlative relationship, (2)
      conditionally causative relationship, (3) causative relationship, or (0)
      no relationship.
    sentences:
      - 'C: Iron deficiency anemia in the mother; normal Hb levels in the fetus'
      - This is a conditionally causative relationship
      - 'C: Decreasing carbohydrate intake, increasing fat intake'
  - source_sentence: Please summerize the given abstract to a title
    sentences:
      - 'BatteryLab: A Collaborative Platform for Power Monitoring'
      - >-
        hi ! good evening. i am chatbot answering your query. from the history,
        it seems that you might have sustained some kind of trivial trauma while
        cutting woods resulting in oozing of blood in the tissue forming a
        collection of blood (hematoma). usually, small collections of blood get
        absorbed of their own. however, this may not happen in cases where the
        blood clotting is hampered by the intake of blood thinners as is in your
        case and the same might also get infected causing more pain due to an
        abscess. if i were your doctor, i would consult your physician who
        started your blood thinning agent for consideration of discontinuing
        these medicines for some time till it heals up. if it does not even
        then, i would refer you to a general surgeon for a clinical examination
        and further management. i hope this information would help you in
        discussing with your family physician/treating doctor in further
        management of your problem. please do not hesitate to ask in case of any
        further doubts. thanks for choosing chatbot to clear doubts on your
        health problems. wishing you an early recovery. chatbot. if i were your
        doctor,
      - >-
        Effects of the psychoactive compounds in green tea on risky
        decision-making.
  - source_sentence: Answer this question truthfully
    sentences:
      - >-
        Laparoscopic stomach-partitioning gastrojejunostomy with reduced-port
        techniques for unresectable distal gastric cancer.
      - >-
        hi, thanks for posting the query, i would suggest you to get an x-ray of
        the tooth piece left in the socket, according to your clinical symptoms
        i suppose that you might have developed an infection in the region which
        is radiating in the nearby tooth region giving you such feeling, also
        take course of antibiotics and analgesics, maintain a good oral hygiene,
        take lukewarm saline and antiseptic mouthwash rinses, take an
        appointment with oral surgeon and get the piece removed. hope you find
        this as helpful, take care!
      - >-
        If you feel you are developing symptoms suggestive of Pneumocystis
        pneumonia contact your health professional.
  - source_sentence: >-
      If you are a doctor, please answer the medical questions based on the
      patient's description.
    sentences:
      - Hazard control for communicable disease transport at Ornge
      - >-
        hello and thank you for asking chatbot, i understand your concern. you
        are probably experiencing low blood pressure when you stand up, called
        orthostatic hypotension. as a result, not enough blood reaches your
        brain, and you feel lightheaded or dizzy. here are some advices
      - >-
        hi, thank you for posting your query. i have noted your symptoms. these
        are suggestive of sciatica, or nerve compression in the lower back
        region due to slipped disc in that location. disc prolapse leads to
        compression of the nerves, resulting in low back pain, leg pain and
        tingling. symptoms may increase on walking. the diagnosis can be
        confirmed by doing mri scan of the lumbosacral spine. good medical
        treatments are available for this condition. i hope my answer helps.
        please get back if you have any follow-up queries or if you require any
        additional information. wishing you good health, chatbot. ly/
  - source_sentence: Please summerize the given abstract to a title
    sentences:
      - >-
        Gastric mucormycosis with splenic invasion a rare abdominal complication
        of COVID-19 pneumonia
      - >-
        Russian-Language Mobile Apps for Reducing Alcohol Use: Systematic Search
        and Evaluation
      - Peacekeeping after Covid-19
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-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/paraphrase-multilingual-MiniLM-L12-v2
Maximum Sequence Length: 128 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': 128, '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})
)

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 = [
    'Please summerize the given abstract to a title',
    'Peacekeeping after Covid-19',
    'Russian-Language Mobile Apps for Reducing Alcohol Use: Systematic Search and Evaluation',
]
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]

Training Details

Training Dataset

Unnamed Dataset

Size: 20,000 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: 7 tokens
mean: 15.87 tokens
max: 81 tokens

min: 3 tokens
mean: 77.94 tokens
max: 128 tokens

min: 1.0
mean: 1.0
max: 1.0

	sentence_0	sentence_1	label
type	string	string	float
details	min: 7 tokens mean: 15.87 tokens max: 81 tokens	min: 3 tokens mean: 77.94 tokens max: 128 tokens	min: 1.0 mean: 1.0 max: 1.0

Samples:

sentence_0	sentence_1	label
`Please summerize the given abstract to a title`	`Impact of National Containment Measures on Decelerating the Increase in Daily New Cases of COVID-19 in 54 Countries and 4 Epicenters of the Pandemic: Comparative Observational Study`	`1.0`
`Answer this question truthfully`	Intracranial hypertension is defined as ICP greater than 20 mmHg. This condition occurs when there is increased pressure inside the skull, which can cause a range of symptoms and potentially lead to serious complications such as brain damage or herniation. Intracranial hypertension can be caused by a variety of factors, including head injury, brain tumors, infections, and certain medications. Treatment options may include medications to reduce pressure, surgery to relieve pressure or address underlying causes, or other supportive measures to manage symptoms and prevent complications.	`1.0`
`Answer this question truthfully`	The bone marrow is a rapidly proliferating population of cells that produces blood cells, including white blood cells, red blood cells, and platelets. 6-mercaptopurine and azathioprine are medications that are commonly used to treat autoimmune diseases and some types of cancer. However, because these drugs interfere with the production of new cells, they can also cause myelosuppression, which is a condition in which the bone marrow produces fewer blood cells than normal. This can lead to a variety of symptoms, including fatigue, weakness, and an increased risk of infection.	`1.0`

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
num_train_epochs: 1
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: 1
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}
tp_size: 0
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
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
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss
0.4	500	0.4093
0.8	1000	0.0074

Framework Versions

Python: 3.11.12
Sentence Transformers: 3.4.1
Transformers: 4.51.3
PyTorch: 2.6.0+cu124
Accelerate: 1.6.0
Datasets: 3.5.1
Tokenizers: 0.21.1

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",
}