ptp / config.json
princeton-nlp's picture
update
d376ab5
raw
history blame
5.01 kB
{
"_commit_hash": null,
"add_mae_decoder": true,
"add_text_decoder": true,
"architectures": [
"PTPForConditionalGeneration"
],
"decoder_start_token_id": 0,
"eos_token_id": 1,
"image_mode": "RGB",
"initializer_factor": 1.0,
"initializer_range": 0.02,
"is_encoder_decoder": true,
"mae_weight": 1.0,
"model_type": "ptp",
"pad_token_id": 1,
"text_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_dropout": 0.1,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"d_ff": 3072,
"d_kv": 64,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"diversity_penalty": 0.0,
"do_sample": false,
"dropout_rate": 0.1,
"early_stopping": false,
"emb_layer_norm": true,
"encoder_hidden_size": 768,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 1,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_factor": 1.0,
"initializer_range": 0.02,
"is_decoder": true,
"is_encoder_decoder": false,
"is_glu": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-06,
"layer_norm_epsilon": 1e-06,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "ptp_text_decoder",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_heads": 12,
"num_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 1,
"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,
"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,
"transformers_version": "4.34.1",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": false,
"vocab_size": 50265
},
"text_weight": 1.0,
"torch_dtype": "float32",
"transformers_version": null,
"vision_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_probs_dropout_prob": 0.1,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_hidden_size": 512,
"decoder_intermediate_size": 2048,
"decoder_num_attention_heads": 16,
"decoder_num_hidden_layers": 8,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"embedding_layernorm": 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_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_mode": "RGB",
"image_size": [
16,
8176
],
"initializer_factor": 1.0,
"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-12,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "ptp_vision",
"no_repeat_ngram_size": 0,
"norm_pix_loss": true,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_channels": 3,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 16,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"qkv_bias": true,
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"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": "float32",
"torchscript": false,
"transformers_version": "4.34.1",
"typical_p": 1.0,
"use_bfloat16": false
}
}