{ "architectures": [ "GPTNeoXForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "eos_token_id": 0, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 512, "model_type": "gpt_neox", "num_attention_heads": 4, "num_hidden_layers": 5, "pad_token_id": 1023, "rotary_emb_base": 10000, "rotary_pct": 0.25, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.29.0.dev0", "type_vocab_size": 16, "use_cache": true, "use_parallel_residual": true, "vocab_size": 1024 }