| { |
| "architectures": [ |
| "VisionEncoderDecoderModel" |
| ], |
| "bos_token_id": 1, |
| "decoder": { |
| "_name_or_path": "ai-forever/rugpt3small_based_on_gpt2", |
| "activation_function": "gelu_new", |
| "add_cross_attention": true, |
| "architectures": [ |
| "GPT2LMHeadModel" |
| ], |
| "attn_pdrop": 0.1, |
| "bos_token_id": 1, |
| "chunk_size_feed_forward": 0, |
| "dtype": "float32", |
| "embd_pdrop": 0.1, |
| "eos_token_id": 2, |
| "gradient_checkpointing": false, |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "initializer_range": 0.02, |
| "is_decoder": true, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "layer_norm_epsilon": 1e-05, |
| "model_type": "gpt2", |
| "n_ctx": 2048, |
| "n_embd": 768, |
| "n_head": 12, |
| "n_inner": null, |
| "n_layer": 12, |
| "n_positions": 2048, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "pad_token_id": 0, |
| "problem_type": null, |
| "reorder_and_upcast_attn": false, |
| "resid_pdrop": 0.1, |
| "return_dict": true, |
| "scale_attn_by_inverse_layer_idx": false, |
| "scale_attn_weights": true, |
| "summary_activation": null, |
| "summary_first_dropout": 0.1, |
| "summary_proj_to_labels": true, |
| "summary_type": "cls_index", |
| "summary_use_proj": true, |
| "tie_word_embeddings": true, |
| "use_cache": true, |
| "vocab_size": 50264 |
| }, |
| "decoder_start_token_id": 1, |
| "dtype": "float32", |
| "encoder": { |
| "_name_or_path": "google/vit-base-patch16-224-in21k", |
| "architectures": [ |
| "ViTModel" |
| ], |
| "attention_probs_dropout_prob": 0.0, |
| "chunk_size_feed_forward": 0, |
| "dtype": "float32", |
| "encoder_stride": 16, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.0, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "image_size": 224, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_norm_eps": 1e-12, |
| "model_type": "vit", |
| "num_attention_heads": 12, |
| "num_channels": 3, |
| "num_hidden_layers": 12, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "patch_size": 16, |
| "pooler_act": "tanh", |
| "pooler_output_size": 768, |
| "problem_type": null, |
| "qkv_bias": true, |
| "return_dict": true |
| }, |
| "eos_token_id": 2, |
| "is_encoder_decoder": true, |
| "model_type": "vision-encoder-decoder", |
| "pad_token_id": 2, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.2.0", |
| "use_cache": false, |
| "vocab_size": 50264 |
| } |
|
|
