Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
dense
Generated from Trainer
dataset_size:110608
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use blackmlengineer/skill-extractor-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use blackmlengineer/skill-extractor-v0.1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("blackmlengineer/skill-extractor-v0.1") sentences = [ "proficiency in Yiddish required for this position", "write Telugu", "Latvian", "Yiddish" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
|
Download README.md from blackmlengineer/skill-extractor-v0.1: direct link, hf CLI and curl.
- Browser
- Download file 17.9 kB
-
https://huggingface.co/blackmlengineer/skill-extractor-v0.1/resolve/main/README.md
- Command line
-
hf download hf://blackmlengineer/skill-extractor-v0.1/README.md
-
curl -L -o README.md https://huggingface.co/blackmlengineer/skill-extractor-v0.1/resolve/main/README.md
17.9 kB
metadata
language:
- en
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:110608
- loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
widget:
- source_sentence: proficiency in Yiddish required for this position
sentences:
- write Telugu
- Latvian
- Yiddish
- source_sentence: knowledge of international cinema is a necessity
sentences:
- SPARK
- Italian
- film studies
- source_sentence: experience with casting anode pins is a plus.
sentences:
- 'plan evaluation '
- synthetic natural environment
- cast cell covers
- source_sentence: Native speakers of Telugu are especially encouraged to apply.
sentences:
- Romanian
- Maltego
- Telugu
- source_sentence: looking for experienced animal hunters to join our team
sentences:
- animal hunting
- use databases
- electrical engineering
datasets:
- TechWolf/Synthetic-ESCO-skill-sentences
pipeline_tag: sentence-similarity
library_name: sentence-transformers
SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the synthetic-esco-skill-sentences dataset. It maps inputs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, 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
- Supported Modality: Text
- Training Dataset:
- Language: en
Model Sources
- Documentation: Sentence Transformers Documentation
- Repository: Sentence Transformers on GitHub
- Hugging Face: Sentence Transformers on Hugging Face
Full Model Architecture
SentenceTransformer(
(0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
(1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', 'include_prompt': True})
(2): Normalize({'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
)
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 = [
'looking for experienced animal hunters to join our team',
'animal hunting',
'electrical engineering',
]
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, 0.8278, -0.1120],
# [ 0.8278, 1.0000, -0.1666],
# [-0.1120, -0.1666, 1.0000]])
Training Details
Training Dataset
synthetic-esco-skill-sentences
- Dataset: synthetic-esco-skill-sentences at 09fc487
- Size: 110,608 training samples
- Columns:
anchorandpositive - Approximate statistics based on the first 100 samples:
anchor positive type string string modality text text details - min: 11 tokens
- mean: 19.69 tokens
- max: 30 tokens
- min: 3 tokens
- mean: 6.53 tokens
- max: 15 tokens
- Samples:
anchor positive Applicants should be skilled in examining legislative drafts for legal compliance and accuracy.examine legislative draftsCandidate must have knowledge in photographic film processing, including monitoring chemical baths.monitor film development bathswe are looking for an experienced meat grinder to join our teamgrind meat - Loss:
MultipleNegativesRankingLosswith these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim", "gather_across_devices": false, "directions": [ "query_to_doc" ], "partition_mode": "joint", "hardness_mode": null, "hardness_strength": 0.0 }
Evaluation Dataset
synthetic-esco-skill-sentences
- Dataset: synthetic-esco-skill-sentences at 09fc487
- Size: 27,652 evaluation samples
- Columns:
anchorandpositive - Approximate statistics based on the first 100 samples:
anchor positive type string string modality text text details - min: 11 tokens
- mean: 19.55 tokens
- max: 34 tokens
- min: 3 tokens
- mean: 5.96 tokens
- max: 10 tokens
- Samples:
anchor positive the position requires attention to detail and strong organizational skills in order to maintain accurate records of security incidents.document security incidents in the storeWe need someone with experience in export logistics to lead our transportation teamcoordinate export transportation activitiesThe ideal candidate will have experience in developing food policy that meets the social objectives of our company.develop food policy - Loss:
MultipleNegativesRankingLosswith these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim", "gather_across_devices": false, "directions": [ "query_to_doc" ], "partition_mode": "joint", "hardness_mode": null, "hardness_strength": 0.0 }
Training Hyperparameters
Non-Default Hyperparameters
per_device_train_batch_size: 128num_train_epochs: 50learning_rate: 0.0001weight_decay: 0.01per_device_eval_batch_size: 128dataloader_pin_memory: False
All Hyperparameters
Click to expand
per_device_train_batch_size: 128num_train_epochs: 50max_steps: -1learning_rate: 0.0001lr_scheduler_type: linearlr_scheduler_kwargs: Nonewarmup_steps: 0optim: adamw_torch_fusedoptim_args: Noneweight_decay: 0.01adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08optim_target_modules: Nonegradient_accumulation_steps: 1average_tokens_across_devices: Truemax_grad_norm: 1.0label_smoothing_factor: 0.0bf16: Falsefp16: Falsebf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Nonetorch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneuse_liger_kernel: Falseliger_kernel_config: Noneuse_cache: Falseneftune_noise_alpha: Nonetorch_empty_cache_steps: Noneauto_find_batch_size: Falselog_on_each_node: Truelogging_nan_inf_filter: Trueinclude_num_input_tokens_seen: nolog_level: passivelog_level_replica: warningdisable_tqdm: Falseproject: huggingfacetrackio_space_id: Nonetrackio_bucket_id: Nonetrackio_static_space_id: Noneper_device_eval_batch_size: 128prediction_loss_only: Trueeval_on_start: Falseeval_do_concat_batches: Trueeval_use_gather_object: Falseeval_accumulation_steps: Noneinclude_for_metrics: []batch_eval_metrics: Falsesave_only_model: Falsesave_on_each_node: Falseenable_jit_checkpoint: Falsepush_to_hub: Falsehub_private_repo: Nonehub_model_id: Nonehub_strategy: every_savehub_always_push: Falsehub_revision: Noneload_best_model_at_end: Falseignore_data_skip: Falserestore_callback_states_from_checkpoint: Falsefull_determinism: Falseseed: 42data_seed: Noneuse_cpu: Falseaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}parallelism_config: Nonedataloader_drop_last: Falsedataloader_num_workers: 0dataloader_pin_memory: Falsedataloader_persistent_workers: Falsedataloader_prefetch_factor: Nonedataloader_multiprocessing_context: Nonedataloader_in_order: Trueremove_unused_columns: Truelabel_names: Nonetrain_sampling_strategy: randomlength_column_name: lengthddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falseddp_static_graph: Noneddp_backend: Noneddp_timeout: 1800fsdp: Nonefsdp_config: Nonedeepspeed: Nonedebug: []skip_memory_metrics: Truedo_predict: Falseresume_from_checkpoint: Nonelocal_rank: -1prompts: Nonebatch_sampler: batch_samplermulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}warmup_ratio: None
Training Logs
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.1156 | 100 | - | 0.2757 |
| 0.2312 | 200 | - | 0.2636 |
| 0.3468 | 300 | - | 0.2548 |
| 0.4624 | 400 | - | 0.2484 |
| 0.5780 | 500 | 0.2929 | 0.2452 |
| 0.6936 | 600 | - | 0.2387 |
| 0.8092 | 700 | - | 0.2291 |
| 0.9249 | 800 | - | 0.2355 |
| 1.0405 | 900 | - | 0.2288 |
| 1.1561 | 1000 | 0.2378 | 0.2275 |
| 1.2717 | 1100 | - | 0.2263 |
| 1.3873 | 1200 | - | 0.2282 |
| 1.5029 | 1300 | - | 0.2228 |
| 1.6185 | 1400 | - | 0.2199 |
| 1.7341 | 1500 | 0.1797 | 0.2235 |
| 1.8497 | 1600 | - | 0.2181 |
| 1.9653 | 1700 | - | 0.2214 |
| 2.0809 | 1800 | - | 0.2164 |
| 2.1965 | 1900 | - | 0.2150 |
| 2.3121 | 2000 | 0.1466 | 0.2133 |
| 2.4277 | 2100 | - | 0.2122 |
| 2.5434 | 2200 | - | 0.2117 |
| 2.6590 | 2300 | - | 0.2118 |
| 2.7746 | 2400 | - | 0.2113 |
| 2.8902 | 2500 | 0.1352 | 0.2097 |
| 3.0058 | 2600 | - | 0.2075 |
| 3.1214 | 2700 | - | 0.2110 |
| 3.2370 | 2800 | - | 0.2114 |
| 3.3526 | 2900 | - | 0.2170 |
| 3.4682 | 3000 | 0.1012 | 0.2143 |
| 3.5838 | 3100 | - | 0.2110 |
Training Time
- Training: 20.9 minutes
- Evaluation: 13.3 minutes
- Total: 34.2 minutes
Framework Versions
- Python: 3.14.7
- Sentence Transformers: 6.2.0
- Transformers: 5.22.0
- PyTorch: 2.15.0
- Accelerate: 1.15.0
- Datasets: 5.1.0
- Tokenizers: 0.23.3
Additional Resources
- Training and Finetuning Embedding Models with Sentence Transformers: the end-to-end guide for training or finetuning Sentence Transformer models.
- Introduction to Matryoshka Embedding Models: variable-size embeddings that can be truncated with minimal quality loss.
- Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval: post-training compression of embedding vectors.
- Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video models through the same API.
- Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: train multimodal embedding models, with a Visual Document Retrieval walkthrough.
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{oord2019representationlearningcontrastivepredictive,
title={Representation Learning with Contrastive Predictive Coding},
author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
year={2019},
eprint={1807.03748},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/1807.03748},
}