Upload folder using huggingface_hub

README.md

@@ -0,0 +1,25 @@
+---
+library_name: keras-hub
+---
+This is a [`ESM` model](https://keras.io/api/keras_hub/models/esm) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
+This model is related to a `MaskedPLM` task.
+
+Model config:
+* **name:** esm_backbone
+* **trainable:** True
+* **vocabulary_size:** 33
+* **num_layers:** 33
+* **num_heads:** 20
+* **hidden_dim:** 1280
+* **intermediate_dim:** 5120
+* **dropout:** 0.0
+* **max_wavelength:** 10000
+* **use_bias:** True
+* **activation:** gelu
+* **layer_norm_eps:** 1e-05
+* **use_pre_layer_norm:** False
+* **position_embedding_type:** rotary
+* **max_sequence_length:** 1026
+* **pad_token_id:** 1
+
+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.txt

@@ -0,0 +1,33 @@
+<cls>
+<pad>
+<eos>
+<unk>
+L
+A
+G
+V
+S
+E
+R
+T
+I
+D
+P
+K
+Q
+N
+F
+Y
+M
+H
+W
+C
+X
+B
+U
+Z
+O
+.
+-
+<null_1>
+<mask>

config.json

@@ -0,0 +1,23 @@
+{
+    "module": "keras_hub.src.models.esm.esm_backbone",
+    "class_name": "ESMBackbone",
+    "config": {
+        "name": "esm_backbone",
+        "trainable": true,
+        "vocabulary_size": 33,
+        "num_layers": 33,
+        "num_heads": 20,
+        "hidden_dim": 1280,
+        "intermediate_dim": 5120,
+        "dropout": 0.0,
+        "max_wavelength": 10000,
+        "use_bias": true,
+        "activation": "gelu",
+        "layer_norm_eps": 1e-05,
+        "use_pre_layer_norm": false,
+        "position_embedding_type": "rotary",
+        "max_sequence_length": 1026,
+        "pad_token_id": 1
+    },
+    "registered_name": "keras_hub>ESMBackbone"
+}

metadata.json

@@ -0,0 +1,10 @@
+{
+    "keras_version": "3.10.0",
+    "keras_hub_version": "0.22.0.dev0",
+    "parameter_count": 649400320,
+    "date_saved": "2025-08-11@22:55:00",
+    "tasks": [
+        "MaskedLM",
+        "TextClassifier"
+    ]
+}

model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f68d3ecebee597087f52effa063742068d7e484be9cb4d06e091359c2779de
+size 2598592024

preprocessor.json

@@ -0,0 +1,51 @@
+{
+    "module": "keras_hub.src.models.esm.esm_masked_plm_preprocessor",
+    "class_name": "ESMMaskedPLMPreprocessor",
+    "config": {
+        "name": "esm_masked_plm_preprocessor_1",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "float32"
+            },
+            "registered_name": null
+        },
+        "tokenizer": {
+            "module": "keras_hub.src.models.esm.esm_tokenizer",
+            "class_name": "ESMTokenizer",
+            "config": {
+                "name": "esm_tokenizer",
+                "trainable": true,
+                "dtype": {
+                    "module": "keras",
+                    "class_name": "DTypePolicy",
+                    "config": {
+                        "name": "int32"
+                    },
+                    "registered_name": null
+                },
+                "config_file": "tokenizer.json",
+                "vocabulary": null,
+                "sequence_length": null,
+                "lowercase": false,
+                "strip_accents": false,
+                "split": true,
+                "suffix_indicator": "##",
+                "oov_token": "<unk>",
+                "special_tokens": null,
+                "special_tokens_in_strings": false
+            },
+            "registered_name": "keras_hub>ESMTokenizer"
+        },
+        "config_file": "preprocessor.json",
+        "sequence_length": 512,
+        "truncate": "round_robin",
+        "mask_selection_rate": 0.15,
+        "mask_selection_length": 96,
+        "mask_token_rate": 0.8,
+        "random_token_rate": 0.1
+    },
+    "registered_name": "keras_hub>ESMMaskedPLMPreprocessor"
+}

task.json

@@ -0,0 +1,82 @@
+{
+    "module": "keras_hub.src.models.esm.esm_masked_plm",
+    "class_name": "ESMMaskedPLM",
+    "config": {
+        "backbone": {
+            "module": "keras_hub.src.models.esm.esm_backbone",
+            "class_name": "ESMBackbone",
+            "config": {
+                "name": "esm_backbone",
+                "trainable": true,
+                "vocabulary_size": 33,
+                "num_layers": 33,
+                "num_heads": 20,
+                "hidden_dim": 1280,
+                "intermediate_dim": 5120,
+                "dropout": 0.0,
+                "max_wavelength": 10000,
+                "use_bias": true,
+                "activation": "gelu",
+                "layer_norm_eps": 1e-05,
+                "use_pre_layer_norm": false,
+                "position_embedding_type": "rotary",
+                "max_sequence_length": 1026,
+                "pad_token_id": 1
+            },
+            "registered_name": "keras_hub>ESMBackbone"
+        },
+        "preprocessor": {
+            "module": "keras_hub.src.models.esm.esm_masked_plm_preprocessor",
+            "class_name": "ESMMaskedPLMPreprocessor",
+            "config": {
+                "name": "esm_masked_plm_preprocessor_1",
+                "trainable": true,
+                "dtype": {
+                    "module": "keras",
+                    "class_name": "DTypePolicy",
+                    "config": {
+                        "name": "float32"
+                    },
+                    "registered_name": null
+                },
+                "tokenizer": {
+                    "module": "keras_hub.src.models.esm.esm_tokenizer",
+                    "class_name": "ESMTokenizer",
+                    "config": {
+                        "name": "esm_tokenizer",
+                        "trainable": true,
+                        "dtype": {
+                            "module": "keras",
+                            "class_name": "DTypePolicy",
+                            "config": {
+                                "name": "int32"
+                            },
+                            "registered_name": null
+                        },
+                        "config_file": "tokenizer.json",
+                        "vocabulary": null,
+                        "sequence_length": null,
+                        "lowercase": false,
+                        "strip_accents": false,
+                        "split": true,
+                        "suffix_indicator": "##",
+                        "oov_token": "<unk>",
+                        "special_tokens": null,
+                        "special_tokens_in_strings": false
+                    },
+                    "registered_name": "keras_hub>ESMTokenizer"
+                },
+                "config_file": "preprocessor.json",
+                "sequence_length": 512,
+                "truncate": "round_robin",
+                "mask_selection_rate": 0.15,
+                "mask_selection_length": 96,
+                "mask_token_rate": 0.8,
+                "random_token_rate": 0.1
+            },
+            "registered_name": "keras_hub>ESMMaskedPLMPreprocessor"
+        },
+        "name": "esm_masked_plm"
+    },
+    "registered_name": "keras_hub>ESMMaskedPLM"
+}

task.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858d7dea9c135ec9ac15b4c97032ecbca3a21bd575e07d29accbd86ad48c0f7c
+size 2605349592

tokenizer.json

@@ -0,0 +1,27 @@
+{
+    "module": "keras_hub.src.models.esm.esm_tokenizer",
+    "class_name": "ESMTokenizer",
+    "config": {
+        "name": "esm_tokenizer",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "int32"
+            },
+            "registered_name": null
+        },
+        "config_file": "tokenizer.json",
+        "vocabulary": null,
+        "sequence_length": null,
+        "lowercase": false,
+        "strip_accents": false,
+        "split": true,
+        "suffix_indicator": "##",
+        "oov_token": "<unk>",
+        "special_tokens": null,
+        "special_tokens_in_strings": false
+    },
+    "registered_name": "keras_hub>ESMTokenizer"
+}