clip-vit-L14-coco

CLIP ViT-L/14 model trained on COCO Captions

This is a sentence-transformers model finetuned from openai/clip-vit-large-patch14 on the coco_captions dataset. It maps sentences & paragraphs to a None-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: openai/clip-vit-large-patch14 <!-- at revision 32bd64288804d66eefd0ccbe215aa642df71cc41 -->
• Maximum Sequence Length: None tokens
• Output Dimensionality: None dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • coco_captions
• Language: en
• License: apache-2.0

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': 'get_text_features', 'method_output_name': None}, 'image': {'method': 'get_image_features', 'method_output_name': None}}, 'module_output_name': 'sentence_embedding', 'architecture': 'CLIPModel'})
)

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("tomaarsen/clip-vit-L14-coco")
# Run inference
sentences = [
    'A large desk by a window is neatly arranged.',
    'A long hot dog on a plate on a table.',
    'A lady sitting at an enormous dining table with lots of food.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000, -0.0302,  0.1619],
#         [-0.0302,  1.0000,  0.1578],
#         [ 0.1619,  0.1578,  1.0000]])

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Information Retrieval

• Datasets: coco-eval and coco-test
• Evaluated with <code>InformationRetrievalEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

coco_captions

• Dataset: coco_captions at a2ed90d
• Size: 10,000 training samples
• Columns: <code>image</code> and <code>caption</code>
• Approximate statistics based on the first 1000 samples:

  	image	caption
  type	PIL.JpegImagePlugin.JpegImageFile	string
  details	<ul><li></li></ul>	<ul><li>min: 28 characters</li><li>mean: 52.56 characters</li><li>max: 156 characters</li></ul>

• Samples:

  image	caption
  <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=640x480 at 0x1E8E850FDD0></code>	<code>A woman wearing a net on her head cutting a cake. </code>
  <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=640x480 at 0x1E8E8550590></code>	<code>A woman cutting a large white sheet cake.</code>
  <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=640x480 at 0x1E8E8563F50></code>	<code>A woman wearing a hair net cutting a large sheet cake.</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Evaluation Dataset

coco_captions

• Dataset: coco_captions at a2ed90d
• Size: 1,000 evaluation samples
• Columns: <code>image</code> and <code>caption</code>
• Approximate statistics based on the first 1000 samples:

  	image	caption
  type	PIL.JpegImagePlugin.JpegImageFile	string
  details	<ul><li></li></ul>	<ul><li>min: 27 characters</li><li>mean: 52.45 characters</li><li>max: 151 characters</li></ul>

• Samples:

  image	caption
  <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=500x336 at 0x1E8E82F5710></code>	<code>A child holding a flowered umbrella and petting a yak.</code>
  <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=500x336 at 0x1E8E8532B10></code>	<code>A young man holding an umbrella next to a herd of cattle.</code>
  <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=500x336 at 0x1E8E833CFD0></code>	<code>a young boy barefoot holding an umbrella touching the horn of a cow</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• bf16: True
• batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 2e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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
• use_cpu: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• bf16: True
• fp16: False
• half_precision_backend: None
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• 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_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• 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
• 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_for_metrics: []
• eval_do_concat_batches: True
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• 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: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Energy Consumed: 0.043 kWh
• Carbon Emitted: 0.012 kg of CO2
• Hours Used: 0.137 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.11.6
• Sentence Transformers: 5.2.0.dev0
• Transformers: 4.57.0.dev0
• PyTorch: 2.8.0+cu128
• Accelerate: 1.6.0
• Datasets: 3.6.0
• Tokenizers: 0.22.1

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",
}

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}
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->