CoolFace
Modelpublic

Lagstill/Varsity_module2_bot

sourceHugging Facegemmaupdated 2y agoView on Hugging Face
0likes26downloads
config.json43 linesDownload Raw Back to root
1{2  "_name_or_path": "/content/drive/My Drive/Colab Notebooks/model",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    "_load_in_4bit": true,23    "_load_in_8bit": false,24    "bnb_4bit_compute_dtype": "bfloat16",25    "bnb_4bit_quant_type": "fp4",26    "bnb_4bit_use_double_quant": true,27    "llm_int8_enable_fp32_cpu_offload": false,28    "llm_int8_has_fp16_weight": false,29    "llm_int8_skip_modules": null,30    "llm_int8_threshold": 6.0,31    "load_in_4bit": true,32    "load_in_8bit": false,33    "quant_method": "bitsandbytes"34  },35  "rms_norm_eps": 1e-06,36  "rope_scaling": null,37  "rope_theta": 10000.0,38  "torch_dtype": "float16",39  "transformers_version": "4.38.2",40  "use_cache": true,41  "vocab_size": 25600042}43