| { |
| "_name_or_path": "albert-base-v2", |
| "architectures": [ |
| "AlbertForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0, |
| "bos_token_id": 2, |
| "classifier_dropout_prob": 0.1, |
| "down_scale_factor": 1, |
| "embedding_size": 128, |
| "eos_token_id": 3, |
| "gap_size": 0, |
| "hidden_act": "gelu_new", |
| "hidden_dropout_prob": 0, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "math", |
| "1": "greedy", |
| "2": "implementation", |
| "3": "dp", |
| "4": "data structures", |
| "5": "constructive algorithms", |
| "6": "brute force", |
| "7": "binary search", |
| "8": "sortings", |
| "9": "graphs" |
| }, |
| "initializer_range": 0.02, |
| "inner_group_num": 1, |
| "intermediate_size": 3072, |
| "label2id": { |
| "binary search": 7, |
| "brute force": 6, |
| "constructive algorithms": 5, |
| "data structures": 4, |
| "dp": 3, |
| "graphs": 9, |
| "greedy": 1, |
| "implementation": 2, |
| "math": 0, |
| "sortings": 8 |
| }, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "albert", |
| "net_structure_type": 0, |
| "num_attention_heads": 12, |
| "num_hidden_groups": 1, |
| "num_hidden_layers": 12, |
| "num_memory_blocks": 0, |
| "pad_token_id": 0, |
| "position_embedding_type": "absolute", |
| "problem_type": "multi_label_classification", |
| "torch_dtype": "float32", |
| "transformers_version": "4.46.2", |
| "type_vocab_size": 2, |
| "vocab_size": 30000 |
| } |
|
|
