add model

config.json

@@ -0,0 +1,165 @@
+{
+ "_name_or_path": "SajjadAyoubi/clip-fa-vision",
+ "architectures": [
+ "CLIPVisionModel"
+ ],
+ "attention_dropout": 0.0,
+ "dropout": 0.0,
+ "hidden_act": "quick_gelu",
+ "hidden_size": 128,
+ "image_size": 224,
+ "initializer_factor": 1.0,
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "layer_norm_eps": 1e-05,
+ "model_type": "clip_vision_model",
+ "num_attention_heads": 2,
+ "num_channels": 3,
+ "num_hidden_layers": 2,
+ "patch_size": 32,
+ "projection_dim": 512,
+ "text_config": {
+ "_name_or_path": "",
+ "add_cross_attention": false,
+ "architectures": null,
+ "attention_dropout": 0.0,
+ "bad_words_ids": null,
+ "bos_token_id": 0,
+ "chunk_size_feed_forward": 0,
+ "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": 2,
+ "finetuning_task": null,
+ "forced_bos_token_id": null,
+ "forced_eos_token_id": null,
+ "gradient_checkpointing": false,
+ "hidden_act": "quick_gelu",
+ "hidden_size": 512,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1"
+ },
+ "initializer_factor": 1.0,
+ "initializer_range": 0.02,
+ "intermediate_size": 2048,
+ "is_decoder": false,
+ "is_encoder_decoder": false,
+ "label2id": {
+ "LABEL_0": 0,
+ "LABEL_1": 1
+ },
+ "layer_norm_eps": 1e-05,
+ "length_penalty": 1.0,
+ "max_length": 20,
+ "max_position_embeddings": 77,
+ "min_length": 0,
+ "model_type": "clip_text_model",
+ "no_repeat_ngram_size": 0,
+ "num_attention_heads": 8,
+ "num_beam_groups": 1,
+ "num_beams": 1,
+ "num_hidden_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,
+ "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,
+ "torchscript": false,
+ "transformers_version": "4.7.0.dev0",
+ "use_bfloat16": false,
+ "vocab_size": 49408
+ },
+ "text_config_dict": null,
+ "torch_dtype": "float32",
+ "transformers_version": "4.42.0.dev0",
+ "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,
+ "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,
+ "gradient_checkpointing": false,
+ "hidden_act": "quick_gelu",
+ "hidden_size": 768,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1"
+ },
+ "image_size": 224,
+ "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-05,
+ "length_penalty": 1.0,
+ "max_length": 20,
+ "min_length": 0,
+ "model_type": "clip_vision_model",
+ "no_repeat_ngram_size": 0,
+ "num_attention_heads": 2,
+ "num_beam_groups": 1,
+ "num_beams": 1,
+ "num_hidden_layers": 12,
+ "num_return_sequences": 1,
+ "output_attentions": false,
+ "output_hidden_states": false,
+ "output_scores": false,
+ "pad_token_id": null,
+ "patch_size": 32,
+ "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,
+ "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,
+ "torchscript": false,
+ "transformers_version": "4.7.0.dev0",
+ "use_bfloat16": false
+ },
+ "vision_config_dict": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc29d3d808c02c363d92bbe2bb45f5f653762384ea5fce18d521d5659e56bf78
+size 8455048

preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+ "_valid_processor_keys": [
+ "images",
+ "do_resize",
+ "size",
+ "resample",
+ "do_center_crop",
+ "crop_size",
+ "do_rescale",
+ "rescale_factor",
+ "do_normalize",
+ "image_mean",
+ "image_std",
+ "do_convert_rgb",
+ "return_tensors",
+ "data_format",
+ "input_data_format"
+ ],
+ "crop_size": {
+ "height": 224,
+ "width": 224
+ },
+ "do_center_crop": true,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.48145466,
+ 0.4578275,
+ 0.40821073
+ ],
+ "image_processor_type": "CLIPImageProcessor",
+ "image_std": [
+ 0.26862954,
+ 0.26130258,
+ 0.27577711
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "shortest_edge": 224
+ }
+}