model_config.yaml

name: vit_gpt2_image2text
config_type: model
encoder:
  hidden_size: 768
  num_hidden_layers: 12
  num_attention_heads: 12
  intermediate_size: 3072
  hidden_act: gelu
  hidden_dropout_prob: 0.0
  attention_probs_dropout_prob: 0.0
  initializer_range: 0.02
  layer_norm_eps: 1.0e-12
  image_size: 224
  patch_size: 16
  num_channels: 3
  qkv_bias: true
  encoder_stride: 16
decoder:
  add_cross_attention: true
  vocab_size: 42001
  attn_pdrop: 0.1
  bos_token_id: 5
  embd_pdrop: 0.1
  eos_token_id: 5
  gradient_checkpointing: false
  initializer_range: 0.02
  layer_norm_epsilon: 1.0e-05
  model_type: gpt2
  n_ctx: 1024
  n_embd: 768
  n_head: 12
  n_inner: null
  n_layer: 12
  n_positions: 1024
  resid_pdrop: 0.1
  summary_activation: false
  summary_first_dropout: 0.1
  use_cache: true
generation:
  bos_token_id: 0
  decoder_start_token_id: 0
  early_stopping: true
  eos_token_id: 2
  length_penalty: 2.0
  max_new_tokens: 24
  no_repeat_ngram_size: 3
  num_beams: 4
  pad_token_id: 1