4bit
/

Image-to-Text
Transformers
Safetensors
English
vlm
text-generation
image-captioning
visual-question-answering
Inference Endpoints
uform-gen / config.json
camenduru's picture
thanks to unum-cloud ❤
60b3795
{
"_name_or_path": "uform-gen",
"architectures": [
"VLMForCausalLM"
],
"center_crop": true,
"image_encoder_embedding_dim": 256,
"image_encoder_hidden_size": 768,
"image_encoder_num_heads": 12,
"image_encoder_num_layers": 12,
"image_encoder_patch_size": 16,
"image_encoder_pooling": "cls",
"image_pooler_intermediate_size": 5504,
"image_pooler_num_attn_heads": 16,
"image_pooler_num_latents": 196,
"image_size": 224,
"image_token_id": 32002,
"initializer_range": 0.02,
"model_type": "vlm",
"text_decoder_name_or_path": "princeton-nlp/Sheared-LLaMA-1.3B",
"tokenizer_name_or_path": "unum-cloud/uform-gen",
"torch_dtype": "float32",
"transformers_version": "4.36.2",
"use_cache": true
}