Update config.json

config.json

@@ -1,79 +1,64 @@
 {
   "_name_or_path": "sartifyllc/AViLaMa",
   "architectures": [
-    "CLIPModel"
+    "AViLaMa"
   ],
-  "initializer_factor": null,
-  "logit_scale_init_value": null,
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
   "model_type": "clip",
-  "projection_dim": 256,
+  "projection_dim": 512,
   "text_config": {
     "_name_or_path": "",
     "add_cross_attention": false,
-    "architectures": [
-      "BertModel"
-    ],
+    "architectures": null,
     "attention_dropout": 0.0,
     "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
     "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
-    "diversity_penalty": null,
+    "diversity_penalty": 0.0,
     "do_sample": false,
-    "dropout": 0.1,
+    "dropout": 0.0,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
+    "eos_token_id": 2,
     "finetuning_task": null,
-    "attention_probs_dropout_prob": 0.1,
-    "directionality": "bidi",
-    "gradient_checkpointing": false,
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 256,
-    "pooler_fc_size": 1024,
-    "pooler_num_attention_heads": 12,
-    "pooler_num_fc_layers": 3,
-    "pooler_size_per_head": 128,
-    "pooler_type": "first_token_transform",
-    "position_embedding_type": "absolute",
-    "type_vocab_size": 2,
-    "use_cache": true,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
-    "hidden_act": "gelu",
+    "hidden_act": "quick_gelu",
+    "hidden_size": 512,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "initializer_factor": null,
+    "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "intermediate_size": 3072,
+    "intermediate_size": 2048,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layer_norm_eps": 1e-12,
+    "layer_norm_eps": 1e-05,
     "length_penalty": 1.0,
-    "max_length": 200,
-    "max_position_embeddings": 512,
+    "max_length": 20,
+    "max_position_embeddings": 77,
     "min_length": 0,
-    "model_type": "bert",
-    "no_repeat_ngram_size": null,
-    "num_attention_heads": 12,
-    "num_beam_groups": null,
-    "num_beams": null,
+    "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": null,
+    "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 0,
+    "pad_token_id": 1,
     "prefix": null,
+    "projection_dim": 512,
     "problem_type": null,
     "pruned_heads": {},
     "remove_invalid_values": false,
@@ -81,10 +66,8 @@
     "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,
@@ -92,13 +75,11 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.7.0",
-    "typical_p": 1.0,
+    "transformers_version": "4.16.0.dev0",
     "use_bfloat16": false,
-    "vocab_size": 501153
+    "vocab_size": 49408
   },
   "text_config_dict": null,
-  "torch_dtype": "float32",
   "transformers_version": null,
   "vision_config": {
     "_name_or_path": "",
@@ -106,7 +87,6 @@
     "architectures": null,
     "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,
@@ -117,17 +97,16 @@
     "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": 1024,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "image_size": 336,
+    "image_size": 224,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
     "intermediate_size": 3072,
@@ -146,7 +125,6 @@
     "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,
@@ -155,6 +133,7 @@
     "pad_token_id": null,
     "patch_size": 32,
     "prefix": null,
+    "projection_dim" : 512,
     "problem_type": null,
     "pruned_heads": {},
     "remove_invalid_values": false,
@@ -162,10 +141,8 @@
     "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,
@@ -173,10 +150,8 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.23.1",
-    "typical_p": 1.0,
+    "transformers_version": "4.16.0.dev0",
     "use_bfloat16": false
   },
   "vision_config_dict": null
-}
-
+}