{ | |
"_name_or_path": "GPT-NeoX-pretrain", | |
"architectures": [ | |
"GPTNeoXForCausalLM" | |
], | |
"attention_dropout": 0.0, | |
"bos_token_id": 0, | |
"classifier_dropout": 0.1, | |
"eos_token_id": 0, | |
"hidden_act": "gelu", | |
"hidden_dropout": 0.0, | |
"hidden_size": 512, | |
"initializer_range": 0.02, | |
"intermediate_size": 2048, | |
"layer_norm_eps": 1e-05, | |
"max_position_embeddings": 2048, | |
"model_type": "gpt_neox", | |
"num_attention_heads": 8, | |
"num_hidden_layers": 6, | |
"rope_scaling": null, | |
"rotary_emb_base": 10000, | |
"rotary_pct": 1.0, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float32", | |
"transformers_version": "4.31.0", | |
"use_cache": true, | |
"use_parallel_residual": false, | |
"vocab_size": 60032 | |
} | |