Upload TFDistilBertForSequenceClassification

README.md

@@ -0,0 +1,47 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: test_model
+  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. -->
+
+# test_model
+
+This model was trained from scratch 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: None
+- training_precision: float32
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.28.1
+- TensorFlow 2.12.0
+- Datasets 2.11.0
+- Tokenizers 0.13.3

config.json

@@ -1,14 +1,18 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "test_model",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
+  "attention_dropout": 0.1,
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "dim": 768,
+  "dropout": 0.1,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
+  "hidden_dim": 3072,
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -27,14 +31,17 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.28.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 28996

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6463d76553fe8eebc6e3edc8ea3438f63fb117e6e9c14345a2ae21af35fe9abb
+size 433503344