commit files to HF hub

config.json

@@ -0,0 +1,46 @@
+{
+ "_name_or_path": "sgugger/finetuned-bert-mrpc",
+ "architectures": [
+ "BertForSequenceClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "custom_pipelines": {
+ "pair-classification": {
+ "impl": "__main__.PairClassificationPipeline",
+ "pt": [
+ "AutoModelForSequenceClassification"
+ ],
+ "tf": [
+ "TFAutoModelForSequenceClassification"
+ ]
+ }
+ },
+ "gradient_checkpointing": false,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "not_equivalent",
+ "1": "equivalent"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "equivalent": 1,
+ "not_equivalent": 0
+ },
+ "layer_norm_eps": 1e-12,
+ "max_position_embeddings": 512,
+ "model_type": "bert",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "pad_token_id": 0,
+ "position_embedding_type": "absolute",
+ "problem_type": "single_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.23.1",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 28996
+}

pipeline.py

@@ -0,0 +1,60 @@
+import numpy as np
+
+from transformers import Pipeline
+
+
+def softmax(outputs):
+ maxes = np.max(outputs, axis=-1, keepdims=True)
+ shifted_exp = np.exp(outputs - maxes)
+ return shifted_exp / shifted_exp.sum(axis=-1, keepdims=True)
+
+
+class PairClassificationPipeline(Pipeline):
+
+ def _sanitize_parameters(self, **kwargs):
+ preprocess_kwargs = {}
+ if "second_text" in kwargs:
+ preprocess_kwargs["second_text"] = kwargs["second_text"]
+ return preprocess_kwargs, {}, {}
+
+ def preprocess(self, text, second_text=None):
+ return self.tokenizer(text,
+ text_pair=second_text,
+ return_tensors=self.framework)
+
+ def _forward(self, model_inputs):
+ return self.model(**model_inputs)
+
+ def postprocess(self, model_outputs):
+ logits = model_outputs.logits[0].numpy()
+ probabilities = softmax(logits)
+
+ best_class = np.argmax(probabilities)
+ label = self.model.config.id2label[best_class]
+ score = probabilities[best_class].item()
+ logits = logits.tolist()
+ return {"label": label, "score": score, "logits": logits}
+
+
+from transformers.pipelines import PIPELINE_REGISTRY
+
+from transformers import AutoModelForSequenceClassification, TFAutoModelForSequenceClassification
+
+if __name__ == "__main__":
+ PIPELINE_REGISTRY.register_pipeline(
+ "pair-classification",
+ pipeline_class=PairClassificationPipeline,
+ pt_model=AutoModelForSequenceClassification,
+ tf_model=TFAutoModelForSequenceClassification,
+ )
+
+ from transformers import pipeline
+
+ classifier = pipeline("pair-classification",
+ model="sgugger/finetuned-bert-mrpc")
+ from huggingface_hub import Repository
+
+ repo = Repository("test-dynamic-pipeline",
+ clone_from="paulhindemith/test-dynamic-pipeline")
+ classifier.save_pretrained("test-dynamic-pipeline")
+ repo.push_to_hub()

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3301f183527431290cc7ca96700df70254ba4828c1936189df6dbe30cb88f7e9
+size 433317237

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+ "cls_token": "[CLS]",
+ "mask_token": "[MASK]",
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+ "cls_token": "[CLS]",
+ "do_lower_case": false,
+ "mask_token": "[MASK]",
+ "model_max_length": 512,
+ "name_or_path": "sgugger/finetuned-bert-mrpc",
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "special_tokens_map_file": null,
+ "strip_accents": null,
+ "tokenize_chinese_chars": true,
+ "tokenizer_class": "BertTokenizer",
+ "unk_token": "[UNK]"
+}