Upload folder using huggingface_hub

config.json

@@ -4,51 +4,54 @@
     "CLIPModel"
   ],
   "initializer_factor": 1.0,
-  "logit_scale_init_value": 2.6592,
+  "logit_scale_init_value": 2.659260036932778,
   "model_type": "clip",
-  "projection_dim": 512,
+  "projection_dim": 256,
   "text_config": {
-    "_name_or_path": "sartifyllc/AViLaMa",
+    "_name_or_path": "",
     "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": 1,
-    "bos_token_id": 0,
+    "architectures": [
+      "BertModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
     "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": 1,
-    "decoder_start_token_id": 1,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
-    "dropout": 0.0,
+    "dropout": null,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
-    "finetuning_task": 1,
-    "forced_bos_token_id": 1,
-    "forced_eos_token_id": 1,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 512,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
     "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": 77,
+    "max_position_embeddings": 512,
     "min_length": 0,
-    "model_type": "clip_text_model",
+    "model_type": "bert",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 8,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_hidden_layers": 12,
@@ -56,60 +59,70 @@
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 1,
-    "prefix": 1,
-    "projection_dim": 512,
-    "problem_type": 1,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 256,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
-    "sep_token_id": 1,
-    "task_specific_params": 1,
+    "sep_token_id": null,
+    "task_specific_params": null,
     "temperature": 1.0,
+    "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
-    "tokenizer_class": 1,
+    "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": 1,
+    "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.16.0.dev0",
+    "transformers_version": "4.7.0",
+    "typical_p": 1.0,
     "use_bfloat16": false,
-    "vocab_size": 49408
+    "vocab_size": 501153
+  },
+  "text_config_dict": {
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_dim": 256
   },
-  "text_config_dict": 1,
-  "transformers_version": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.7.0",
   "vision_config": {
     "_name_or_path": "",
     "add_cross_attention": false,
-    "architectures": 1,
+    "architectures": null,
     "attention_dropout": 0.0,
-    "bad_words_ids": 1,
-    "bos_token_id": 1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
     "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": 1,
-    "decoder_start_token_id": 1,
+    "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": 1,
-    "finetuning_task": 1,
-    "forced_bos_token_id": 1,
-    "forced_eos_token_id": 1,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 768,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "image_size": 224,
+    "image_size": 336,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "intermediate_size": 3072,
+    "intermediate_size": 4096,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
@@ -122,19 +135,20 @@
     "min_length": 0,
     "model_type": "clip_vision_model",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
+    "num_attention_heads": 16,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 1,
-    "patch_size": 32,
+    "pad_token_id": null,
+    "patch_size": 14,
     "prefix": null,
-    "projection_dim" : 512,
     "problem_type": null,
+    "projection_dim": 256,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
@@ -143,6 +157,7 @@
     "sep_token_id": null,
     "task_specific_params": null,
     "temperature": 1.0,
+    "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
@@ -150,8 +165,17 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.16.0.dev0",
+    "transformers_version": "4.7.0",
+    "typical_p": 1.0,
     "use_bfloat16": false
   },
-  "vision_config_dict": null
+  "vision_config_dict": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 256
+  }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ee14d843191a40a7859a81b24961c03a7a687fe112ffa77290d4700cbfde935
-size 3100166464
+oid sha256:2f16f01f95434a23d49d014b12e5ee3029c96ea3f25d0474d66d5498beff4413
+size 3100166548

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4020d22d5b91f585dd982aa769f3208840a11236e2edcff94e3a7a85800c03ba
-size 3100328754
+oid sha256:86041968dabea9e419adf5f53d8e3d4dbee80068bcb451d261169d23fbc25483
+size 3100329078