Upload folder using huggingface_hub

README.md

@@ -0,0 +1,19 @@
+---
+library_name: keras-hub
+pipeline_tag: text-generation
+---
+This is a [`GPT2` model](https://keras.io/api/keras_hub/models/gpt2) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
+This model is related to a `CausalLM` task.
+
+Model config:
+* **name:** gpt2_backbone
+* **trainable:** True
+* **vocabulary_size:** 50257
+* **num_layers:** 12
+* **num_heads:** 12
+* **hidden_dim:** 768
+* **intermediate_dim:** 3072
+* **dropout:** 0.1
+* **max_sequence_length:** 1024
+
+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.

config.json

@@ -0,0 +1,16 @@
+{
+    "module": "keras_hub.src.models.gpt2.gpt2_backbone",
+    "class_name": "GPT2Backbone",
+    "config": {
+        "name": "gpt2_backbone",
+        "trainable": true,
+        "vocabulary_size": 50257,
+        "num_layers": 12,
+        "num_heads": 12,
+        "hidden_dim": 768,
+        "intermediate_dim": 3072,
+        "dropout": 0.1,
+        "max_sequence_length": 1024
+    },
+    "registered_name": "keras_hub>GPT2Backbone"
+}

metadata.json

@@ -0,0 +1,9 @@
+{
+    "keras_version": "3.8.0",
+    "keras_hub_version": "0.19.3",
+    "parameter_count": 124439808,
+    "date_saved": "2025-03-31@01:09:23",
+    "tasks": [
+        "CausalLM"
+    ]
+}

model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09148ceee1b8d2edb3aacd7555af35d26830b17bd6a45dbea26ff4686acef46
+size 498184528

preprocessor.json

@@ -0,0 +1,44 @@
+{
+    "module": "keras_hub.src.models.gpt2.gpt2_causal_lm_preprocessor",
+    "class_name": "GPT2CausalLMPreprocessor",
+    "config": {
+        "name": "gpt2_causal_lm_preprocessor",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "float32"
+            },
+            "registered_name": null
+        },
+        "tokenizer": {
+            "module": "keras_hub.src.models.gpt2.gpt2_tokenizer",
+            "class_name": "GPT2Tokenizer",
+            "config": {
+                "name": "gpt2_tokenizer",
+                "trainable": true,
+                "dtype": {
+                    "module": "keras",
+                    "class_name": "DTypePolicy",
+                    "config": {
+                        "name": "int32"
+                    },
+                    "registered_name": null
+                },
+                "config_file": "tokenizer.json",
+                "sequence_length": null,
+                "add_prefix_space": false,
+                "unsplittable_tokens": [
+                    "<|endoftext|>"
+                ]
+            },
+            "registered_name": "keras_hub>GPT2Tokenizer"
+        },
+        "config_file": "preprocessor.json",
+        "sequence_length": 1024,
+        "add_start_token": true,
+        "add_end_token": true
+    },
+    "registered_name": "keras_hub>GPT2CausalLMPreprocessor"
+}

task.json

@@ -0,0 +1,68 @@
+{
+    "module": "keras_hub.src.models.gpt2.gpt2_causal_lm",
+    "class_name": "GPT2CausalLM",
+    "config": {
+        "backbone": {
+            "module": "keras_hub.src.models.gpt2.gpt2_backbone",
+            "class_name": "GPT2Backbone",
+            "config": {
+                "name": "gpt2_backbone",
+                "trainable": true,
+                "vocabulary_size": 50257,
+                "num_layers": 12,
+                "num_heads": 12,
+                "hidden_dim": 768,
+                "intermediate_dim": 3072,
+                "dropout": 0.1,
+                "max_sequence_length": 1024
+            },
+            "registered_name": "keras_hub>GPT2Backbone"
+        },
+        "preprocessor": {
+            "module": "keras_hub.src.models.gpt2.gpt2_causal_lm_preprocessor",
+            "class_name": "GPT2CausalLMPreprocessor",
+            "config": {
+                "name": "gpt2_causal_lm_preprocessor",
+                "trainable": true,
+                "dtype": {
+                    "module": "keras",
+                    "class_name": "DTypePolicy",
+                    "config": {
+                        "name": "float32"
+                    },
+                    "registered_name": null
+                },
+                "tokenizer": {
+                    "module": "keras_hub.src.models.gpt2.gpt2_tokenizer",
+                    "class_name": "GPT2Tokenizer",
+                    "config": {
+                        "name": "gpt2_tokenizer",
+                        "trainable": true,
+                        "dtype": {
+                            "module": "keras",
+                            "class_name": "DTypePolicy",
+                            "config": {
+                                "name": "int32"
+                            },
+                            "registered_name": null
+                        },
+                        "config_file": "tokenizer.json",
+                        "sequence_length": null,
+                        "add_prefix_space": false,
+                        "unsplittable_tokens": [
+                            "<|endoftext|>"
+                        ]
+                    },
+                    "registered_name": "keras_hub>GPT2Tokenizer"
+                },
+                "config_file": "preprocessor.json",
+                "sequence_length": 1024,
+                "add_start_token": true,
+                "add_end_token": true
+            },
+            "registered_name": "keras_hub>GPT2CausalLMPreprocessor"
+        },
+        "name": "gpt2_causal_lm"
+    },
+    "registered_name": "keras_hub>GPT2CausalLM"
+}

tokenizer.json

@@ -0,0 +1,23 @@
+{
+    "module": "keras_hub.src.models.gpt2.gpt2_tokenizer",
+    "class_name": "GPT2Tokenizer",
+    "config": {
+        "name": "gpt2_tokenizer",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "int32"
+            },
+            "registered_name": null
+        },
+        "config_file": "tokenizer.json",
+        "sequence_length": null,
+        "add_prefix_space": false,
+        "unsplittable_tokens": [
+            "<|endoftext|>"
+        ]
+    },
+    "registered_name": "keras_hub>GPT2Tokenizer"
+}