1chae/llmtest4
018
1{2 "_name_or_path": "1028_qwen2.5_500_model",3 "architectures": [4 "Qwen2ForCausalLM"5 ],6 "attention_dropout": 0.0,7 "bos_token_id": 151643,8 "eos_token_id": 151643,9 "hidden_act": "silu",10 "hidden_size": 3584,11 "initializer_range": 0.02,12 "intermediate_size": 18944,13 "max_position_embeddings": 131072,14 "max_window_layers": 28,15 "model_type": "qwen2",16 "num_attention_heads": 28,17 "num_hidden_layers": 28,18 "num_key_value_heads": 4,19 "pad_token_id": 151665,20 "quantization_config": {21 "bnb_4bit_compute_dtype": "float16",22 "bnb_4bit_quant_type": "nf4",23 "bnb_4bit_use_double_quant": true,24 "llm_int8_enable_fp32_cpu_offload": false,25 "llm_int8_has_fp16_weight": false,26 "llm_int8_skip_modules": null,27 "llm_int8_threshold": 6.0,28 "load_in_4bit": true,29 "load_in_8bit": false,30 "quant_method": "bitsandbytes"31 },32 "rms_norm_eps": 1e-06,33 "rope_scaling": null,34 "rope_theta": 1000000.0,35 "sliding_window": null,36 "tie_word_embeddings": false,37 "torch_dtype": "float16",38 "transformers_version": "4.44.2",39 "unsloth_version": "2024.10.7",40 "use_cache": true,41 "use_mrope": false,42 "use_sliding_window": false,43 "vocab_size": 15206444}45 