dtian09

clip_llama

dtian09/clip_llama

clip_llama is a machine learning model from dtian09. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

The Flickr30k image dataset (either 10% or 50% of the training set) was firstly encoded using the CLIP image encoder, then the LlaMA3 8B transformer was fine-tuned on the encoded images plus their captions to predict…