ymroddi/model

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 128000,8  "eos_token_id": 128009,9  "head_dim": 64,10  "hidden_act": "silu",11  "hidden_size": 2048,12  "initializer_range": 0.02,13  "intermediate_size": 8192,14  "max_position_embeddings": 131072,15  "mlp_bias": false,16  "model_type": "llama",17  "num_attention_heads": 32,18  "num_hidden_layers": 16,19  "num_key_value_heads": 8,20  "pad_token_id": 128004,21  "pretraining_tp": 1,22  "rms_norm_eps": 1e-05,23  "rope_scaling": {24    "factor": 32.0,25    "high_freq_factor": 4.0,26    "low_freq_factor": 1.0,27    "original_max_position_embeddings": 8192,28    "rope_type": "llama3"29  },30  "rope_theta": 500000.0,31  "tie_word_embeddings": true,32  "torch_dtype": "float16",33  "transformers_version": "4.51.3",34  "unsloth_fixed": true,35  "unsloth_version": "2025.5.6",36  "use_cache": true,37  "vocab_size": 12825638}39