{ | |
"architectures": ["LlamaForSequenceClassification"], | |
"model_type": "llama", | |
"hidden_size": 4096, | |
"intermediate_size": 11008, | |
"num_attention_heads": 32, | |
"num_hidden_layers": 40, | |
"num_labels": 3, | |
"vocab_size": 32000, | |
"pad_token_id": 0, | |
"bos_token_id": 1, | |
"eos_token_id": 2, | |
"initializer_range": 0.02, | |
"hidden_dropout_prob": 0.1, | |
"attention_probs_dropout_prob": 0.1, | |
"max_position_embeddings": 2048, | |
"torch_dtype": "float16", | |
"transformers_version": "4.33.0" | |
} |