Hyper-AI-Computer/KeystoneFuse-Base-Baseline-001-Pretrain-LLaMA

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 2,8  "eos_token_id": 1,9  "head_dim": 128,10  "hidden_act": "silu",11  "hidden_activation": "silu",12  "hidden_size": 768,13  "initializer_range": 0.02,14  "intermediate_size": 4608,15  "max_position_embeddings": 8192,16  "mlp_bias": false,17  "model_type": "llama",18  "num_attention_heads": 8,19  "num_hidden_layers": 18,20  "num_key_value_heads": 2,21  "pad_token_id": 0,22  "pretraining_tp": 1,23  "rms_norm_eps": 1e-06,24  "rope_scaling": null,25  "rope_theta": 1000000,26  "sliding_window": 512,27  "sliding_window_pattern": 6,28  "tie_word_embeddings": true,29  "transformers_version": "4.51.3",30  "use_cache": false,31  "vocab_size": 3814432}33