VirgiF/continue_pretrain_gemma

1{2  "_name_or_path": "google/gemma-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  "rms_norm_eps": 1e-06,23  "rope_scaling": null,24  "rope_theta": 10000.0,25  "torch_dtype": "bfloat16",26  "transformers_version": "4.44.2",27  "use_cache": true,28  "vocab_size": 25600129}30