FMDMllama

Prompt

f"<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are an expert in financial misinformation detection.<|eot_id|> <|start_header_id|>user<|end_header_id|> {model_input} image information: {data['image_info']}<|eot_id|><|start_header_id|>assistant<|end_header_id|>"

Negative Prompt

f"<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are an expert in financial misinformation detection. <|eot_id|><|start_header_id|>user<|end_header_id|> {model_input} image information: {data['image_info']}<|eot_id|><|start_header_id|>assistant<|end_header_id|>"

Model description

The model is based on Llama-3.2-11B-Vision-Instruct to fine-tuned.

The lora_weight.zip is the lora model.

The test-datasets.zip is the test datasets.

The inference.py is the inference.

Download model

Download them in the Files & versions tab.