This is a sentence-transformers model finetuned from sentence-transformers/clip-ViT-L-14 on the multimodal_lpt2 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: sentence-transformers/clip-ViT-L-14
Maximum Sequence Length: None tokens
Output Dimensionality: None dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- multimodal_lpt2

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): 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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("machinev/model")
# Run inference
sentences = [
    'the main power cable is not connected with LPT ',
    '/content/sample_data/images/LPT (4).jpeg',
    'the main power cable is not connected with LPT ',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

Evaluation

Metrics

Triplet

Datasets: yt-title-thumbnail-train and yt-title-thumbnail-validation
Evaluated with TripletEvaluator

Metric	yt-title-thumbnail-train	yt-title-thumbnail-validation
cosine_accuracy	0.0	0.0

Training Details

Training Dataset

multimodal_lpt2

Dataset: multimodal_lpt2 at 9f649f9
Size: 12 training samples
Columns: text, image_path, anchor, positive, and negative

Approximate statistics based on the first 12 samples:

	text	image_path	anchor	positive	negative
type	string	string	PIL.JpegImagePlugin.JpegImageFile	string	string
details	min: 11 tokens mean: 11.42 tokens max: 12 tokens	min: 18 tokens mean: 18.42 tokens max: 19 tokens		min: 11 tokens mean: 11.42 tokens max: 12 tokens	min: 11 tokens mean: 11.42 tokens max: 12 tokens

Samples:

text	image_path	anchor	positive	negative
`the main power cable is not connected with LPT`	`/content/sample_data/images/LPT (1).jpeg`	`<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=3024x4032 at 0x7D40680FFFD0>`	`the main power cable is not connected with LPT`	`the main power cable is not connected with LPT`
`the main power cable is connected with LPT`	`/content/sample_data/images/LPT (2).jpeg`	`<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=3024x4032 at 0x7D40680FDF90>`	`the main power cable is connected with LPT`	`the main power cable is connected with LPT`
`the main power cable is connected with LPT`	`/content/sample_data/images/LPT (3).jpeg`	`<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=3024x4032 at 0x7D4063F4C610>`	`the main power cable is connected with LPT`	`the main power cable is connected with LPT`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim" 4}

Evaluation Dataset

multimodal_lpt2

Dataset: multimodal_lpt2 at 9f649f9
Size: 12 evaluation samples
Columns: text, image_path, anchor, positive, and negative

Approximate statistics based on the first 12 samples:

	text	image_path	anchor	positive	negative
type	string	string	PIL.JpegImagePlugin.JpegImageFile	string	string
details	min: 11 tokens mean: 11.42 tokens max: 12 tokens	min: 18 tokens mean: 18.42 tokens max: 19 tokens		min: 11 tokens mean: 11.42 tokens max: 12 tokens	min: 11 tokens mean: 11.42 tokens max: 12 tokens

Samples:

text	image_path	anchor	positive	negative
`the main power cable is not connected with LPT`	`/content/sample_data/images/LPT (1).jpeg`	`<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=3024x4032 at 0x7D4063B84B50>`	`the main power cable is not connected with LPT`	`the main power cable is not connected with LPT`
`the main power cable is connected with LPT`	`/content/sample_data/images/LPT (2).jpeg`	`<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=3024x4032 at 0x7D4063F4D190>`	`the main power cable is connected with LPT`	`the main power cable is connected with LPT`
`the main power cable is connected with LPT`	`/content/sample_data/images/LPT (3).jpeg`	`<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=3024x4032 at 0x7D4063F4C7D0>`	`the main power cable is connected with LPT`	`the main power cable is connected with LPT`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim" 4}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
learning_rate: 0.0001
num_train_epochs: 2

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
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: 0.0001
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 2
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
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
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
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	yt-title-thumbnail-train_cosine_accuracy	yt-title-thumbnail-validation_cosine_accuracy
-1	-1	-	-	0.0	0.0
1.0	1	8.5381	7.5693	-	-
2.0	2	7.5693	7.1228	-	-

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.3
PyTorch: 2.5.1+cu124
Accelerate: 1.3.0
Datasets: 3.3.2
Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

bibtex

@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

bibtex

@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}
}