ANLP-Final-Project/m1-slp

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 1,8  "dtype": "float32",9  "eos_token_id": 2,10  "head_dim": 128,11  "hidden_act": "silu",12  "hidden_size": 4096,13  "initializer_range": 0.02,14  "intermediate_size": 11008,15  "max_position_embeddings": 4096,16  "mlp_bias": false,17  "model_type": "llama",18  "num_attention_heads": 32,19  "num_hidden_layers": 32,20  "num_key_value_heads": 32,21  "pad_token_id": 32000,22  "pretraining_tp": 1,23  "rms_norm_eps": 1e-05,24  "rope_scaling": null,25  "rope_theta": 10000.0,26  "tie_word_embeddings": false,27  "transformers_version": "4.57.1",28  "use_cache": false,29  "vocab_size": 3200130}31