paligemma-adapter

gokulsabari/paligemma-adapter

paligemma-adapter is a image-text-to-text model from gokulsabari. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as gemma.

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

Downloads · 30 days

19% of all-time downloads

All-time downloads

Public

Parameters

2.9B

75.6 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors5.8 GB · 100%

At a glance

Task: Image-Text-to-Text
Library: transformers
License: gemma
Model type: paligemma
Access: Public
Created: Sep 3, 2024
Updated: Sep 6, 2024
SHA: ffa4c39c

Try a prompt

Base models

google/paligemma-3b-pt-224

Model card

From the Hugging Face model README

paligemma-adapter

This model is a fine-tuned version of google/paligemma-3b-pt-224 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9127

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: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
0.9767	1.0	8560	0.9846
0.9463	2.0	17120	0.9456
0.9415	3.0	25680	0.9300
0.9208	4.0	34240	0.9215
0.9138	5.0	42800	0.9163
0.9138	6.0	51360	0.9127

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu118
Datasets 2.20.0
Tokenizers 0.19.1

Task: Image-Text-to-Text
Library: transformers
Type: paligemma
License: gemma
Created: Sep 3, 2024
Updated: Sep 6, 2024