ahn1376/TaskArithmetic___Code-Math

1{2  "_name_or_path": "./FinalSet/task_arithmetic_Math-Code",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 1,9  "eos_token_id": 2,10  "head_dim": 128,11  "hidden_act": "silu",12  "hidden_size": 5120,13  "initializer_range": 0.02,14  "intermediate_size": 13824,15  "max_position_embeddings": 4096,16  "mlp_bias": false,17  "model_type": "llama",18  "num_attention_heads": 40,19  "num_hidden_layers": 40,20  "num_key_value_heads": 40,21  "pad_token_id": 0,22  "pretraining_tp": 1,23  "rms_norm_eps": 1e-05,24  "rope_scaling": null,25  "rope_theta": 10000.0,26  "tie_word_embeddings": false,27  "torch_dtype": "float16",28  "transformers_version": "4.48.0",29  "unsloth_version": "2024.9",30  "use_cache": true,31  "vocab_size": 3200032}33