Upload model

config.json

@@ -8,14 +8,18 @@
   "model_type": "clip",
   "projection_dim": 512,
   "text_config": {
-    "_name_or_path": "",
+    "_name_or_path": "amir7d0/clip-text-fa",
     "add_cross_attention": false,
-    "architectures": null,
+    "architectures": [
+      "RobertaModel"
+    ],
     "attention_dropout": 0.0,
+    "attention_probs_dropout_prob": 0.1,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
     "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
     "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
@@ -28,7 +32,9 @@
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
-    "hidden_act": "quick_gelu",
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
     "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
@@ -36,30 +42,30 @@
     },
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "intermediate_size": 2048,
+    "intermediate_size": 3072,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layer_norm_eps": 1e-05,
+    "layer_norm_eps": 1e-12,
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 0,
+    "max_position_embeddings": 514,
     "min_length": 0,
     "model_type": "clip_text_model",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 8,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 0,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
     "pad_token_id": 1,
-    "patch_size": 1,
+    "position_embedding_type": "absolute",
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
@@ -77,26 +83,105 @@
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": null,
+    "torch_dtype": "float32",
     "torchscript": false,
     "transformers_version": "4.24.0",
+    "type_vocab_size": 1,
     "typical_p": 1.0,
     "use_bfloat16": false,
-    "vocab_size": 0
+    "use_cache": true,
+    "vocab_size": 42000
   },
   "text_config_dict": {
+    "_name_or_path": "amir7d0/clip-text-fa",
+    "add_cross_attention": false,
+    "architectures": [
+      "RobertaModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
     "hidden_size": 768,
-    "max_position_embeddings": 0,
-    "num_hidden_layers": 0,
-    "patch_size": 1,
-    "vocab_size": 0
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "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-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 514,
+    "min_length": 0,
+    "model_type": "roberta",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "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,
+    "position_embedding_type": "absolute",
+    "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,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.24.0",
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 42000
   },
   "torch_dtype": "float32",
   "transformers_version": null,
   "vision_config": {
-    "_name_or_path": "",
+    "_name_or_path": "amir7d0/clip-vit-fa",
     "add_cross_attention": false,
-    "architectures": null,
+    "architectures": [
+      "CLIPVisionModel"
+    ],
     "attention_dropout": 0.0,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
@@ -133,7 +218,6 @@
     "layer_norm_eps": 1e-05,
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 0,
     "min_length": 0,
     "model_type": "clip_vision_model",
     "no_repeat_ngram_size": 0,
@@ -141,15 +225,16 @@
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_channels": 3,
-    "num_hidden_layers": 0,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
     "pad_token_id": null,
-    "patch_size": 1,
+    "patch_size": 32,
     "prefix": null,
     "problem_type": null,
+    "projection_dim": 512,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
@@ -159,25 +244,380 @@
     "suppress_tokens": null,
     "task_specific_params": null,
     "temperature": 1.0,
+    "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,
     "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": null,
+    "torch_dtype": "float32",
     "torchscript": false,
     "transformers_version": "4.24.0",
     "typical_p": 1.0,
     "use_bfloat16": false,
-    "vocab_size": 0
+    "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": 12,
+      "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
   },
   "vision_config_dict": {
-    "hidden_size": 1024,
-    "intermediate_size": 4096,
-    "num_attention_heads": 16,
-    "num_hidden_layers": 24,
-    "patch_size": 14,
-    "projection_dim": 768
+    "_name_or_path": "amir7d0/clip-vit-fa",
+    "add_cross_attention": false,
+    "architectures": [
+      "CLIPVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": 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,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "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": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "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,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "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,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.24.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "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": 12,
+      "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
   }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334d43676e94c5ad5cfea0f171255a8e827dedbf33186ecff93155bed24127d4
-size 823159263
+oid sha256:72e2aa2c90242720595c6e78515ca21e9e704c96d60f51215157ccc1172ea5f0
+size 826305627