Hyper-AI-Computer/KeystoneFuse-Base-Baseline-001-Test-DP-FSDP

1{2  "architectures": [3    "KeystoneFuseForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "attn_implementation": "sdpa",8  "bos_token_id": 2,9  "eos_token_id": 1,10  "head_dim": 128,11  "hidden_activation": "silu",12  "hidden_size": 768,13  "initializer_range": 0.02,14  "intermediate_size": 4608,15  "max_position_embeddings": 4096,16  "model_type": "KeystoneFuse",17  "num_attention_heads": 8,18  "num_hidden_layers": 18,19  "num_key_value_heads": 2,20  "pad_token_id": 0,21  "rms_norm_eps": 1e-06,22  "rope_theta": 1000000,23  "sliding_window": 512,24  "sliding_window_pattern": 6,25  "transformers_version": "4.51.3",26  "use_cache": false,27  "vocab_size": 3814428}29