Backup-CaML/Instruct_2500_pretraining16bit

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 128000,8  "torch_dtype": "bfloat16",9  "eos_token_id": [10    128001,11    128008,12    12800913  ],14  "head_dim": 128,15  "hidden_act": "silu",16  "hidden_size": 4096,17  "initializer_range": 0.02,18  "intermediate_size": 14336,19  "max_position_embeddings": 131072,20  "mlp_bias": false,21  "model_type": "llama",22  "num_attention_heads": 32,23  "num_hidden_layers": 32,24  "num_key_value_heads": 8,25  "pad_token_id": 128004,26  "pretraining_tp": 1,27  "rms_norm_eps": 1e-05,28  "rope_scaling": {29    "factor": 8.0,30    "high_freq_factor": 4.0,31    "low_freq_factor": 1.0,32    "original_max_position_embeddings": 8192,33    "rope_type": "llama3"34  },35  "rope_theta": 500000.0,36  "tie_word_embeddings": false,37  "transformers_version": "4.57.2",38  "unsloth_version": "2025.6.12",39  "use_cache": true,40  "vocab_size": 12825641}42