Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/tokenizer/vocabulary.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,19 @@
+---
+library_name: keras-hub
+---
+This is a [`XLMRoberta` model](https://keras.io/api/keras_hub/models/xlm_roberta) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
+This model is related to a `TextEmbedder` task.
+
+Model config:
+* **name:** xlm_roberta_backbone
+* **trainable:** True
+* **dtype:** {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}
+* **vocabulary_size:** 250002
+* **num_layers:** 24
+* **num_heads:** 16
+* **hidden_dim:** 1024
+* **intermediate_dim:** 4096
+* **dropout:** 0.1
+* **max_sequence_length:** 8192
+
+This model card has been generated automatically and should be completed by the model author. See [Model Cards documentation](https://huggingface.co/docs/hub/model-cards) for more information.

assets/tokenizer/vocabulary.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

config.json

@@ -0,0 +1,24 @@
+{
+    "module": "keras_hub.src.models.xlm_roberta.xlm_roberta_backbone",
+    "class_name": "XLMRobertaBackbone",
+    "config": {
+        "name": "xlm_roberta_backbone",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "float32"
+            },
+            "registered_name": null
+        },
+        "vocabulary_size": 250002,
+        "num_layers": 24,
+        "num_heads": 16,
+        "hidden_dim": 1024,
+        "intermediate_dim": 4096,
+        "dropout": 0.1,
+        "max_sequence_length": 8192
+    },
+    "registered_name": "keras_hub>XLMRobertaBackbone"
+}

metadata.json

@@ -0,0 +1,11 @@
+{
+    "keras_version": "3.13.2",
+    "keras_hub_version": "0.30.0.dev0",
+    "parameter_count": 566702080,
+    "date_saved": "2026-07-04@18:33:18",
+    "tasks": [
+        "MaskedLM",
+        "TextClassifier",
+        "TextEmbedder"
+    ]
+}

model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3482cddc622ecda8872f5cb78bf121cac63bdbf910d4bd7b9f2ec6d80c1f189
+size 2267639920

preprocessor.json

@@ -0,0 +1,42 @@
+{
+    "module": "keras_hub.src.models.xlm_roberta.xlm_roberta_text_embedder_preprocessor",
+    "class_name": "XLMRobertaTextEmbedderPreprocessor",
+    "config": {
+        "name": "xlm_roberta_text_embedder_preprocessor",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "float32"
+            },
+            "registered_name": null
+        },
+        "tokenizer": {
+            "module": "keras_hub.src.models.xlm_roberta.xlm_roberta_tokenizer",
+            "class_name": "XLMRobertaTokenizer",
+            "config": {
+                "name": "xlm_roberta_tokenizer",
+                "trainable": true,
+                "dtype": {
+                    "module": "keras",
+                    "class_name": "DTypePolicy",
+                    "config": {
+                        "name": "int32"
+                    },
+                    "registered_name": null
+                },
+                "config_file": "tokenizer.json",
+                "proto": null,
+                "sequence_length": null,
+                "add_bos": false,
+                "add_eos": false
+            },
+            "registered_name": "keras_hub>XLMRobertaTokenizer"
+        },
+        "config_file": "preprocessor.json",
+        "sequence_length": 8192,
+        "truncate": "round_robin"
+    },
+    "registered_name": "keras_hub>XLMRobertaTextEmbedderPreprocessor"
+}

task.json

@@ -0,0 +1,76 @@
+{
+    "module": "keras_hub.src.models.xlm_roberta.xlm_roberta_text_embedder",
+    "class_name": "XLMRobertaTextEmbedder",
+    "config": {
+        "backbone": {
+            "module": "keras_hub.src.models.xlm_roberta.xlm_roberta_backbone",
+            "class_name": "XLMRobertaBackbone",
+            "config": {
+                "name": "xlm_roberta_backbone",
+                "trainable": true,
+                "dtype": {
+                    "module": "keras",
+                    "class_name": "DTypePolicy",
+                    "config": {
+                        "name": "float32"
+                    },
+                    "registered_name": null
+                },
+                "vocabulary_size": 250002,
+                "num_layers": 24,
+                "num_heads": 16,
+                "hidden_dim": 1024,
+                "intermediate_dim": 4096,
+                "dropout": 0.1,
+                "max_sequence_length": 8192
+            },
+            "registered_name": "keras_hub>XLMRobertaBackbone"
+        },
+        "preprocessor": {
+            "module": "keras_hub.src.models.xlm_roberta.xlm_roberta_text_embedder_preprocessor",
+            "class_name": "XLMRobertaTextEmbedderPreprocessor",
+            "config": {
+                "name": "xlm_roberta_text_embedder_preprocessor",
+                "trainable": true,
+                "dtype": {
+                    "module": "keras",
+                    "class_name": "DTypePolicy",
+                    "config": {
+                        "name": "float32"
+                    },
+                    "registered_name": null
+                },
+                "tokenizer": {
+                    "module": "keras_hub.src.models.xlm_roberta.xlm_roberta_tokenizer",
+                    "class_name": "XLMRobertaTokenizer",
+                    "config": {
+                        "name": "xlm_roberta_tokenizer",
+                        "trainable": true,
+                        "dtype": {
+                            "module": "keras",
+                            "class_name": "DTypePolicy",
+                            "config": {
+                                "name": "int32"
+                            },
+                            "registered_name": null
+                        },
+                        "config_file": "tokenizer.json",
+                        "proto": null,
+                        "sequence_length": null,
+                        "add_bos": false,
+                        "add_eos": false
+                    },
+                    "registered_name": "keras_hub>XLMRobertaTokenizer"
+                },
+                "config_file": "preprocessor.json",
+                "sequence_length": 8192,
+                "truncate": "round_robin"
+            },
+            "registered_name": "keras_hub>XLMRobertaTextEmbedderPreprocessor"
+        },
+        "name": "xlm_roberta_text_embedder",
+        "pooling_mode": "cls",
+        "normalize": true
+    },
+    "registered_name": "keras_hub>XLMRobertaTextEmbedder"
+}

tokenizer.json

@@ -0,0 +1,22 @@
+{
+    "module": "keras_hub.src.models.xlm_roberta.xlm_roberta_tokenizer",
+    "class_name": "XLMRobertaTokenizer",
+    "config": {
+        "name": "xlm_roberta_tokenizer",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "int32"
+            },
+            "registered_name": null
+        },
+        "config_file": "tokenizer.json",
+        "proto": null,
+        "sequence_length": null,
+        "add_bos": false,
+        "add_eos": false
+    },
+    "registered_name": "keras_hub>XLMRobertaTokenizer"
+}