Upload TFDistilBertForSequenceClassification

README.md

@@ -0,0 +1,49 @@
+---
+license: apache-2.0
+base_model: Geotrend/distilbert-base-pt-cased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: distilbert-pt-cased-sequence-classification
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# distilbert-pt-cased-sequence-classification
+
+This model is a fine-tuned version of [Geotrend/distilbert-base-pt-cased](https://huggingface.co/Geotrend/distilbert-base-pt-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 606, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- TensorFlow 2.15.0
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "Geotrend/distilbert-base-pt-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "partial",
+    "1": "no",
+    "2": "yes"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "no": 1,
+    "partial": 0,
+    "yes": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.41.2",
+  "vocab_size": 25000
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db87d93b06f7567bc8e05103b51853eb05abb395c69a0864c36e4e40cf1d21f
+size 250994632