Add files using upload-large-folder tool

safety_checker/config.json

@@ -8,30 +8,52 @@
   "model_type": "clip",
   "projection_dim": 64,
   "text_config": {
+    "add_cross_attention": false,
     "attention_dropout": 0.1,
     "bos_token_id": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
     "dropout": 0.1,
     "dtype": "float32",
     "eos_token_id": 2,
+    "finetuning_task": null,
     "gradient_checkpointing": false,
     "hidden_act": "quick_gelu",
     "hidden_size": 32,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
     "intermediate_size": 37,
+    "is_decoder": false,
     "layer_norm_eps": 1e-05,
     "max_position_embeddings": 512,
     "model_type": "clip_text_model",
     "num_attention_heads": 4,
     "num_hidden_layers": 5,
+    "pad_token_id": 1,
+    "prefix": null,
     "projection_dim": 512,
+    "pruned_heads": {},
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_bfloat16": false,
     "vocab_size": 99
   },
-  "transformers_version": "4.57.6",
+  "transformers_version": "5.1.0",
   "vision_config": {
+    "add_cross_attention": false,
     "attention_dropout": 0.1,
+    "bos_token_id": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
     "dropout": 0.1,
     "dtype": "float32",
+    "eos_token_id": null,
+    "finetuning_task": null,
     "gradient_checkpointing": false,
     "hidden_act": "quick_gelu",
     "hidden_size": 32,
@@ -39,13 +61,25 @@
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
     "intermediate_size": 37,
+    "is_decoder": false,
     "layer_norm_eps": 1e-05,
     "model_type": "clip_vision_model",
     "num_attention_heads": 4,
     "num_channels": 3,
     "num_hidden_layers": 5,
+    "pad_token_id": null,
     "patch_size": 2,
-    "projection_dim": 512
+    "prefix": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_bfloat16": false
   },
   "vocab_size": 1000
 }

text_encoder/config.json

@@ -19,6 +19,6 @@
   "num_hidden_layers": 5,
   "pad_token_id": 1,
   "projection_dim": 512,
-  "transformers_version": "4.57.6",
+  "transformers_version": "5.1.0",
   "vocab_size": 1000
 }

tokenizer/tokenizer_config.json

@@ -1,29 +1,11 @@
 {
   "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<|startoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
+  "backend": "tokenizers",
   "bos_token": "<|startoftext|>",
-  "clean_up_tokenization_spaces": false,
   "do_lower_case": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
-  "extra_special_tokens": {},
+  "is_local": true,
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "CLIPTokenizer",