| { | |
| "_name_or_path": "hf-internal-testing/tiny-random-bert", | |
| "architectures": [ | |
| "BertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "custom_pipelines": { | |
| "new-task": { | |
| "default": { | |
| "model": { | |
| "pt": [ | |
| "hf-internal-testing/tiny-random-bert", | |
| "main" | |
| ] | |
| } | |
| }, | |
| "impl": "__main__.PairClassificationPipeline", | |
| "pt": [ | |
| "AutoModelForSequenceClassification" | |
| ], | |
| "tf": [], | |
| "type": "text" | |
| } | |
| }, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 37, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 5, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.21.0.dev0", | |
| "type_vocab_size": 16, | |
| "use_cache": true, | |
| "vocab_size": 1124 | |
| } | |