1chae/test4

1{2  "_name_or_path": "beomi/gemma-ko-2b",3  "architectures": [4    "GemmaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 2,9  "eos_token_id": 1,10  "head_dim": 256,11  "hidden_act": "gelu",12  "hidden_activation": "gelu_pytorch_tanh",13  "hidden_size": 2048,14  "initializer_range": 0.02,15  "intermediate_size": 16384,16  "max_position_embeddings": 8192,17  "model_type": "gemma",18  "num_attention_heads": 8,19  "num_hidden_layers": 18,20  "num_key_value_heads": 1,21  "pad_token_id": 0,22  "quantization_config": {23    "_load_in_4bit": true,24    "_load_in_8bit": false,25    "bnb_4bit_compute_dtype": "float16",26    "bnb_4bit_quant_storage": "uint8",27    "bnb_4bit_quant_type": "nf4",28    "bnb_4bit_use_double_quant": false,29    "llm_int8_enable_fp32_cpu_offload": false,30    "llm_int8_has_fp16_weight": false,31    "llm_int8_skip_modules": null,32    "llm_int8_threshold": 6.0,33    "load_in_4bit": true,34    "load_in_8bit": false,35    "quant_method": "bitsandbytes"36  },37  "rms_norm_eps": 1e-06,38  "rope_theta": 10000.0,39  "torch_dtype": "float32",40  "transformers_version": "4.44.2",41  "use_cache": true,42  "vocab_size": 25600043}44