cliplarge-flickr30k-ptbr-5ep-novo

turing552/cliplarge-flickr30k-ptbr-5ep-novo

cliplarge-flickr30k-ptbr-5ep-novo is a zero-shot image classification model from turing552. Use it for the zero-shot image classification task on the model card, and read the license before you ship it in a product. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

6% of all-time downloads

All-time downloads

141

Public

Repo size

15.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.7 GB · 100%

At a glance

Task: Zero-Shot Image Classification
Library: transformers
Model type: clip
Access: Public
Created: Nov 13, 2025
Updated: Nov 13, 2025
SHA: cf6aafa9

Base models

openai/clip-vit-large-patch14

Model card

From the Hugging Face model README

cliplarge-flickr30k-ptbr-5ep-novo

This model is a fine-tuned version of openai/clip-vit-large-patch14 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1539

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.205	0.6803	500	0.2123
0.0756	1.3605	1000	0.1925
0.0463	2.0408	1500	0.1653
0.042	2.7211	2000	0.1704
0.02	3.4014	2500	0.1621
0.021	4.0816	3000	0.1510
0.0134	4.7619	3500	0.1539

Framework versions

Transformers 4.44.2
Pytorch 2.5.1+cu124
Datasets 4.4.1
Tokenizers 0.19.1

Task: Zero-Shot Image Classification
Library: transformers
Type: clip
Created: Nov 13, 2025
Updated: Nov 13, 2025