{ | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"hidden_size": 4096, | |
"intermediate_size": 16384, | |
"num_attention_heads": 32, | |
"num_hidden_layers": 24, | |
"vocab_size": 32000, | |
"max_position_embeddings": 2048, | |
"model_type": "llama", | |
"initializer_range": 0.02, | |
"layer_norm_eps": 1e-12, | |
"hidden_dropout_prob": 0.1, | |
"attention_probs_dropout_prob": 0.1 | |
} | |