Image-to-Text
Transformers
Safetensors
Japanese
llava-jp
text-generation
vision
image-captioning
VQA
Inference Endpoints
ConvLLaVA-JP-1.3b-768 / generation_config.json
toshi456's picture
Upload 8 files
5d355b8 verified
raw
history blame
111 Bytes
{
"_from_model_config": true,
"bos_token_id": 7,
"eos_token_id": 7,
"transformers_version": "4.38.2"
}