Update tiny models for PerceiverForMaskedLM

config.json

@@ -0,0 +1,53 @@
+{
+  "_label_trainable_num_channels": 16,
+  "architectures": [
+    "PerceiverForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "audio_samples_per_frame": 200,
+  "cross_attention_shape_for_attention": "kv",
+  "cross_attention_widening_factor": 4,
+  "d_latents": 20,
+  "d_model": 64,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "image_size": 32,
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 200,
+  "model_type": "perceiver",
+  "num_blocks": 1,
+  "num_cross_attention_heads": 1,
+  "num_frames": 5,
+  "num_latents": 10,
+  "num_self_attends_per_block": 2,
+  "num_self_attention_heads": 1,
+  "output_num_channels": 32,
+  "output_shape": [
+    1,
+    16,
+    224,
+    224
+  ],
+  "qk_channels": 20,
+  "samples_per_patch": 20,
+  "self_attention_widening_factor": 4,
+  "train_size": [
+    20,
+    20
+  ],
+  "transformers_version": "5.16.0.dev0",
+  "use_query_residual": true,
+  "v_channels": 20,
+  "vocab_size": 262
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29507fa9c2c36e85842f850165552447cbc26baae2740349b798e4f1bc416e54
+size 393080

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 32,
+    "width": 32
+  },
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "PerceiverImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 32,
+    "width": 32
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "custom",
+  "bos_token": "[BOS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[EOS]",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 200,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PerceiverTokenizer"
+}