llava-1.5-7b-hf-ft-museum

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

llava-1.5-7b-hf-ft-museum-updated

This model is a fine-tuned version of llava-hf/llava-1.5-7b-hf on the The Metropolitan Museum of Art(https://www.metmuseum.org/art/collection) dataset.

Model description

This project designed to enrich museum experiences by enabling users to explore and comprehend museum artifacts through image-based queries.

Intended uses & limitations

Intended uses:

1. Enhance museum visitor experiences through interactive exploration via image-based queries.
2. Aid researchers and curators in retrieving information from museum artifacts.
3. Democratize access to museum knowledge by catering to a broader audience.

Limitation: The model is fine tuned on a subset of data from the Met's collection that pertains to Indian heritage.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1.4e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.19.1