# BLIP2-7B
 if model_name == 'blip2-7b':
        from .test_blip2 import TestBlip2
        return TestBlip2(name='blip2_opt', model_type='pretrain_opt6.7b', config_path='/models/blip_configs/blip2_pretrain_opt6.7b.yaml', device=device)

# dataset: Activity, Object/existence, etc., currently does not support direct calls from hugging face
# MODEL: models defined in the models file
# DEVICE: GPU id, 0/1/2..., currently only single card can run
python eval.py \
    --model_name $MODEL \
    --annotation_path /${dataset}/annotations.json \
    --answer_path /answer/${dataset} \
    --batch_size 1 \
    --device $DEVICE

# dataset: Activity, Object/existence, etc.
# EVA_MODELS: a list of models to be evaluated (separated by spaces), for example "llava-13b-llama2 llava-1.5-13b llava-1.5-7b"
# $EVA_JUDGE_MODEL: gpt-4 (default), gpt-3.5-turbo, claude-2, etc.

export OPENAI_API_KEY= 
export ANTHROPIC_API_KEY=
export OPENAI_API_BASE=

python  gen_judgment.py \
    --data-folder data_egothink \
    --bench-name $dataset \
    --mode single \
    --model-list $EVA_MODELS \
    --judge-model $EVA_JUDGE_MODEL 
    --parallel 4
    --judge-file judge_prompts.jsonl

# EVA_MODELS: a list of models to be evaluated (separated by spaces), for example "llava-13b-llama2 llava-1.5-13b llava-1.5-7b"
# $EVA_JUDGE_MODEL: gpt-4 (default), gpt-3.5-turbo, claude-2, etc.
python show_result.py \
    --input-file {data_folder}/{bench-name}/model_judgment/{judge-model}_single.jsonl \
    --judge-model $EVA_JUDGE_MODEL \
    --model-list  $EVA_MODELS \
    --mode single