jjae/Midm-KCulture-2.0-Base-Instruct
05
1{2 "architectures": [3 "LlamaForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "attention_probs_dropout_prob": 0.1,8 "bos_token_id": 0,9 "eos_token_id": 2,10 "head_dim": 128,11 "hidden_act": "silu",12 "hidden_dropout_prob": 0.0,13 "hidden_size": 4096,14 "initializer_range": 0.02,15 "intermediate_size": 14336,16 "max_position_embeddings": 32768,17 "mlp_bias": false,18 "model_type": "llama",19 "num_attention_heads": 32,20 "num_hidden_layers": 48,21 "num_key_value_heads": 8,22 "pad_token_id": 131384,23 "pretraining_tp": 1,24 "rms_norm_eps": 1e-05,25 "rope_scaling": null,26 "rope_theta": 8000000,27 "tie_word_embeddings": false,28 "torch_dtype": "bfloat16",29 "transformers_version": "4.53.1",30 "use_cache": true,31 "vocab_size": 13138532}33 