Create config.json

config.json

@@ -0,0 +1,123 @@
+{
+  "_name_or_path": "clip-vit-large-patch14/",
+  "architectures": [
+    "CLIPVisionModel" 
+  ],
+    "model_type": "clip_vision_model",
+    "initializer_factor": 1.0,
+    "logit_scale_init_value": 2.6592,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+       "0": "0",
+       "1": "1",
+       "2": "2",
+       "3": "3",
+       "4": "4",
+       "5": "5",
+       "6": "6",
+       "7": "7",
+       "8": "8",
+       "9": "9",
+        "10": "draw_four",
+        "11": "draw_two",
+       "12": "reverse",
+        "13": "skip",
+        "14": "wild",
+        "15": "wild_draw_four",
+       "16": "NO_CARD" 
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "0": 0,
+        "1": 1,
+        "2": 2,
+        "3": 3,
+        "4": 4,
+        "5": 5,
+        "6": 6,
+        "7": 7,
+        "8": 8,
+        "9": 9,
+        "draw_four": 10,
+       "draw_two": 11,
+        "reverse": 12,
+        "skip": 13,
+        "wild": 14,
+       "wild_draw_four": 15,
+       "NO_CARD": 16
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": "single_label_classification",
+      "projection_dim" : 768,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "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": "4.16.0.dev0",
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+     "projection_dim": 768
+  }
+}