hf-tiny-model-private/tiny-random-MegatronBertForCausalLM

1{2  "architectures": [3    "MegatronBertForCausalLM"4  ],5  "attention_probs_dropout_prob": 0.1,6  "embedding_size": 32,7  "hidden_act": "gelu",8  "hidden_dropout_prob": 0.1,9  "hidden_size": 64,10  "initializer_range": 0.02,11  "intermediate_size": 37,12  "is_decoder": true,13  "layer_norm_eps": 1e-12,14  "max_position_embeddings": 512,15  "model_type": "megatron-bert",16  "num_attention_heads": 4,17  "num_hidden_layers": 5,18  "pad_token_id": 0,19  "position_embedding_type": "absolute",20  "torch_dtype": "float32",21  "transformers_version": "4.28.0.dev0",22  "type_vocab_size": 16,23  "use_cache": true,24  "vocab_size": 112425}26