| { | |
| "architectures": [ | |
| "PlantArchitectureModel" | |
| ], | |
| "bos_token_id": 223, | |
| "decoder": { | |
| "_name_or_path": "gpt2-medium", | |
| "activation_function": "gelu_new", | |
| "add_cross_attention": true, | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "initializer_range": 0.02, | |
| "is_decoder": true, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "n_embd": 1024, | |
| "n_head": 16, | |
| "n_inner": null, | |
| "n_layer": 24, | |
| "n_positions": 8192, | |
| "n_special": 0, | |
| "predict_special_tokens": true, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "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, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 50 | |
| } | |
| }, | |
| "torch_dtype": "float32", | |
| "use_cache": true, | |
| "vocab_size": 227 | |
| }, | |
| "decoder_start_token_id": 223, | |
| "encoder": { | |
| "_name_or_path": "facebook/dinov2-small", | |
| "apply_layernorm": true, | |
| "architectures": [ | |
| "Dinov2Model" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "drop_path_rate": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 384, | |
| "image_size": 518, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-06, | |
| "layerscale_value": 1.0, | |
| "mlp_ratio": 4, | |
| "model_type": "dinov2", | |
| "num_attention_heads": 6, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "out_features": [ | |
| "stage12" | |
| ], | |
| "out_indices": [ | |
| 12 | |
| ], | |
| "patch_size": 14, | |
| "qkv_bias": true, | |
| "reshape_hidden_states": true, | |
| "stage_names": [ | |
| "stem", | |
| "stage1", | |
| "stage2", | |
| "stage3", | |
| "stage4", | |
| "stage5", | |
| "stage6", | |
| "stage7", | |
| "stage8", | |
| "stage9", | |
| "stage10", | |
| "stage11", | |
| "stage12" | |
| ], | |
| "torch_dtype": "float32", | |
| "use_mask_token": true, | |
| "use_swiglu_ffn": false | |
| }, | |
| "eos_token_id": 226, | |
| "is_encoder_decoder": true, | |
| "model_type": "vision-encoder-decoder", | |
| "pad_token_id": 225, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.55.2" | |
| } | |