You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

This model is fine-tuned based on the combination of the 10k low & high-level desc dataset and the total Adjusted ArxivQA dataset. During fine-tuning, the updated modules include LoRA Vision Encoder MLP 128, Project Layer, and LM LoRA 128.

LoRA Vision Encoder MLP 128:

lora_target_modules: 'mlp.fc1' 'mlp.fc2'

Project Layer:

Directly updated

LM LoRA 128:

lora_target_modules: 'attention.wqkv' 'attention.wo' 'feed_forward.w1' 'feed_forward.w2' 'feed_forward.w3'

Downloads last month: 1

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support