sandepaAI/model_x_v2

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 50256,8  "dtype": "float32",9  "eos_token_id": 50256,10  "head_dim": 64,11  "hidden_act": "silu",12  "hidden_size": 1024,13  "initializer_range": 0.02,14  "intermediate_size": 2816,15  "max_position_embeddings": 2048,16  "mlp_bias": false,17  "model_type": "llama",18  "num_attention_heads": 16,19  "num_hidden_layers": 16,20  "num_key_value_heads": 16,21  "pad_token_id": 50256,22  "pretraining_tp": 1,23  "rms_norm_eps": 1e-05,24  "rope_parameters": {25    "factor": 4.0,26    "rope_theta": 10000.0,27    "rope_type": "linear",28    "type": "linear"29  },30  "rope_theta": 10000.0,31  "tie_word_embeddings": false,32  "transformers_version": "5.14.1",33  "use_cache": false,34  "vocab_size": 5025735}36