| { |
| "architectures": [ |
| "LlamaForSequenceClassification" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 49, |
| "eos_token_id": 50, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 512, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1", |
| "2": "LABEL_2", |
| "3": "LABEL_3" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 2048, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_2": 2, |
| "LABEL_3": 3 |
| }, |
| "max_position_embeddings": 256, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 12, |
| "num_key_value_heads": 8, |
| "pad_token_id": 52, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.46.0", |
| "use_cache": true, |
| "vocab_size": 53 |
| } |
|
|
