hf-tiny-v2/tiny-random-VisionEncoderDecoderModel-vit-gpt2

1{2  "architectures": [3    "VisionEncoderDecoderModel"4  ],5  "decoder": {6    "_name_or_path": "/tmp/tmp2lxjeaeg/decoder/GPT2LMHeadModel",7    "activation_function": "gelu_new",8    "add_cross_attention": true,9    "architectures": [10      "GPT2LMHeadModel"11    ],12    "attn_pdrop": 0.1,13    "bos_token_id": 50256,14    "chunk_size_feed_forward": 0,15    "dtype": "float32",16    "embd_pdrop": 0.1,17    "eos_token_id": 50256,18    "id2label": {19      "0": "LABEL_0",20      "1": "LABEL_1"21    },22    "initializer_range": 0.02,23    "is_decoder": true,24    "is_encoder_decoder": false,25    "label2id": {26      "LABEL_0": 0,27      "LABEL_1": 128    },29    "layer_norm_epsilon": 1e-05,30    "model_type": "gpt2",31    "n_embd": 32,32    "n_head": 2,33    "n_inner": null,34    "n_layer": 2,35    "n_positions": 512,36    "output_attentions": false,37    "output_hidden_states": false,38    "pad_token_id": 0,39    "problem_type": null,40    "reorder_and_upcast_attn": false,41    "resid_pdrop": 0.1,42    "return_dict": true,43    "scale_attn_by_inverse_layer_idx": false,44    "scale_attn_weights": true,45    "summary_activation": null,46    "summary_first_dropout": 0.1,47    "summary_proj_to_labels": true,48    "summary_type": "cls_index",49    "summary_use_proj": true,50    "tie_word_embeddings": false,51    "use_cache": true,52    "vocab_size": 5025753  },54  "dtype": "float32",55  "encoder": {56    "_name_or_path": "/tmp/tmp2lxjeaeg/encoder/ViTModel",57    "architectures": [58      "ViTModel"59    ],60    "attention_probs_dropout_prob": 0.1,61    "chunk_size_feed_forward": 0,62    "dtype": "float32",63    "encoder_stride": 2,64    "hidden_act": "gelu",65    "hidden_dropout_prob": 0.1,66    "hidden_size": 32,67    "id2label": {68      "0": "LABEL_0",69      "1": "LABEL_1"70    },71    "image_size": 30,72    "initializer_range": 0.02,73    "intermediate_size": 37,74    "is_decoder": false,75    "is_encoder_decoder": false,76    "label2id": {77      "LABEL_0": 0,78      "LABEL_1": 179    },80    "layer_norm_eps": 1e-12,81    "model_type": "vit",82    "num_attention_heads": 4,83    "num_channels": 3,84    "num_hidden_layers": 2,85    "output_attentions": false,86    "output_hidden_states": false,87    "patch_size": 2,88    "pooler_act": "tanh",89    "pooler_output_size": 32,90    "problem_type": null,91    "qkv_bias": true,92    "return_dict": true93  },94  "is_encoder_decoder": true,95  "model_type": "vision-encoder-decoder",96  "tie_word_embeddings": false,97  "transformers_version": "5.16.0.dev0"98}99