| { | |
| "activation": "swiglu", | |
| "architectures": [ | |
| "LlamaForSequenceClassification" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 11, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2", | |
| "3": "LABEL_3", | |
| "4": "LABEL_4", | |
| "5": "LABEL_5", | |
| "6": "LABEL_6", | |
| "7": "LABEL_7", | |
| "8": "LABEL_8", | |
| "9": "LABEL_9", | |
| "10": "LABEL_10", | |
| "11": "LABEL_11", | |
| "12": "LABEL_12" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9216, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_10": 10, | |
| "LABEL_11": 11, | |
| "LABEL_12": 12, | |
| "LABEL_2": 2, | |
| "LABEL_3": 3, | |
| "LABEL_4": 4, | |
| "LABEL_5": 5, | |
| "LABEL_6": 6, | |
| "LABEL_7": 7, | |
| "LABEL_8": 8, | |
| "LABEL_9": 9 | |
| }, | |
| "max_position_embeddings": 32768, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 22, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 2023, | |
| "pretraining_tp": 1, | |
| "problem_type": "single_label_classification", | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000042, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.55.4", | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| } | |