| { | |
| "architectures": [ | |
| "LlamaForSequenceClassification" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "dtype": "float32", | |
| "eos_token_id": 0, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 512, | |
| "id2label": { | |
| "0": "quick", | |
| "1": "think" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1408, | |
| "label2id": { | |
| "quick": 0, | |
| "think": 1 | |
| }, | |
| "max_position_embeddings": 256, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.21.1", | |
| "use_cache": true, | |
| "vocab_size": 16000 | |
| } | |