jiayihao03/gemma2b_code_java
223
1{2 "_name_or_path": "unsloth/gemma-2b-bnb-4bit",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_size": 2048,13 "initializer_range": 0.02,14 "intermediate_size": 16384,15 "max_position_embeddings": 8192,16 "model_type": "gemma",17 "num_attention_heads": 8,18 "num_hidden_layers": 18,19 "num_key_value_heads": 1,20 "pad_token_id": 0,21 "quantization_config": {22 "bnb_4bit_compute_dtype": "float16",23 "bnb_4bit_quant_type": "nf4",24 "bnb_4bit_use_double_quant": true,25 "llm_int8_enable_fp32_cpu_offload": false,26 "llm_int8_has_fp16_weight": false,27 "llm_int8_skip_modules": null,28 "llm_int8_threshold": 6.0,29 "load_in_4bit": true,30 "load_in_8bit": false,31 "quant_method": "bitsandbytes"32 },33 "rms_norm_eps": 1e-06,34 "rope_scaling": null,35 "rope_theta": 10000.0,36 "torch_dtype": "float16",37 "transformers_version": "4.38.2",38 "unsloth_version": "2024.3",39 "use_cache": true,40 "vocab_size": 25600041}42 