config.json

{
  "architectures": [
    "Kosmos2_5ForConditionalGeneration"
  ],
  "latent_query_num": 2048,
  "model_type": "kosmos-2.5",
  "text_config": {
    "_name_or_path": "",
    "activation_dropout": 0.0,
    "activation_function": "gelu",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.0,
    "attention_heads": 16,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "dropout": 0,
    "early_stopping": false,
    "embed_dim": 1536,
    "pad_token_id": 1,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "ffn_dim": 6144,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "init_std": 0.02,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "layerdrop": 0.0,
    "layers": 24,
    "max_length": 20,
    "max_position_embeddings": 4096,
    "min_length": 0,
    "model_type": "kosmos_2_5_text_model",
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "return_dict": true,
    "return_dict_in_generate": false,
    "scale_embedding": true,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "torch_dtype": null,
    "torchscript": false,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 108481
  },
  "torch_dtype": "float32",
  "transformers_version": "4.42.0.dev0",
  "vision_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "d_ff": 3968,
    "d_kv": 64,
    "decoder_start_token_id": null,
    "dense_act_fn": "gelu_new",
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout_rate": 0.0,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_size": 1536,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_factor": 1.0,
    "initializer_range": 1e-10,
    "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": 4096,
    "min_length": 0,
    "model_type": "kosmos_2_5_vision_model",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 24,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 18,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_embed_hidden_size": 768,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "seq_len": 4096,
    "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
  }
}