pcuenq/tiny-gemma-test2

1{2  "architectures": [3    "GemmaModel"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 2,8  "eos_token_id": 1,9  "head_dim": 256,10  "hidden_act": "gelu_pytorch_tanh",11  "hidden_activation": "gelu_pytorch_tanh",12  "hidden_size": 512,13  "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": 1,19  "num_key_value_heads": 16,20  "pad_token_id": 0,21  "rms_norm_eps": 1e-06,22  "rope_theta": 10000.0,23  "torch_dtype": "bfloat16",24  "transformers_version": "4.40.0.dev0",25  "use_cache": true,26  "vocab_size": 51227}28