dvdmrs09/gemma-7b-it-python

1{2  "_name_or_path": "google/gemma-7b-it",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": 3072,13  "initializer_range": 0.02,14  "intermediate_size": 24576,15  "max_position_embeddings": 8192,16  "model_type": "gemma",17  "num_attention_heads": 16,18  "num_hidden_layers": 28,19  "num_key_value_heads": 16,20  "pad_token_id": 0,21  "quantization_config": {22    "_load_in_4bit": true,23    "_load_in_8bit": false,24    "bnb_4bit_compute_dtype": "bfloat16",25    "bnb_4bit_quant_storage": "uint8",26    "bnb_4bit_quant_type": "nf4",27    "bnb_4bit_use_double_quant": true,28    "llm_int8_enable_fp32_cpu_offload": false,29    "llm_int8_has_fp16_weight": false,30    "llm_int8_skip_modules": null,31    "llm_int8_threshold": 6.0,32    "load_in_4bit": true,33    "load_in_8bit": false,34    "quant_method": "bitsandbytes"35  },36  "rms_norm_eps": 1e-06,37  "rope_scaling": null,38  "rope_theta": 10000.0,39  "torch_dtype": "bfloat16",40  "transformers_version": "4.39.0.dev0",41  "use_cache": false,42  "vocab_size": 25600043}44