config.json

{
  "architectures": [
    "CXRRGModel"
  ],
  "auto_map": {
    "AutoModel": "modelling_cxrrg.CXRRGModel"
  },
  "decoder": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 1,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "end_of_section_token_ids": [
      3,
      2
    ],
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "silu",
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "img_token_id": 0,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_decoder": true,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 2048,
    "min_length": 0,
    "model_type": "llama",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 6,
    "num_key_value_heads": 12,
    "num_return_sequences": 1,
    "num_token_types": 3,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 4,
    "prefix": null,
    "pretraining_tp": 1,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "section_ids": [
      1,
      2
    ],
    "sep_token_id": null,
    "separator_token_ids": [
      3
    ],
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "token_type_embeddings": "add",
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 30000
  },
  "encoder": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_probs_dropout_prob": 0.0,
    "attn_drop_rate": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "conv_stem": false,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "depth": [
      5,
      8,
      20,
      7
    ],
    "diversity_penalty": 0.0,
    "do_sample": false,
    "drop_path_rate": 0.3,
    "drop_rate": 0.0,
    "early_stopping": false,
    "embed_dim": [
      64,
      128,
      320,
      512
    ],
    "encoder_no_repeat_ngram_size": 0,
    "encoder_stride": 16,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "head_dim": 64,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_mean": [
      0.485,
      0.456,
      0.406
    ],
    "image_size": 384,
    "image_std": [
      0.229,
      0.224,
      0.225
    ],
    "in_chans": 3,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-06,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "mlp_ratio": 4,
    "model_type": "vit",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_classes": 1000,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": [
      4,
      2,
      2,
      2
    ],
    "prefix": null,
    "problem_type": null,
    "projection_size": 768,
    "pruned_heads": {},
    "qk_scale": null,
    "qkv_bias": true,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "representation_size": null,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false
  },
  "is_encoder_decoder": true,
  "model_type": "vision-encoder-decoder",
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.39.0"
}