BayesianMonster/pauseformer

1{2  "_name_or_path": "EleutherAI/pythia-160m",3  "architectures": [4    "GPTNeoXForCausalLM"5  ],6  "attention_dropout": 0.0,7  "bos_token_id": 0,8  "classifier_dropout": 0.1,9  "eos_token_id": 0,10  "hidden_act": "gelu",11  "hidden_dropout": 0.0,12  "hidden_size": 768,13  "initializer_range": 0.02,14  "intermediate_size": 3072,15  "layer_norm_eps": 1e-05,16  "max_position_embeddings": 2048,17  "model_type": "gpt_neox",18  "num_attention_heads": 12,19  "num_hidden_layers": 12,20  "rope_scaling": null,21  "rotary_emb_base": 10000,22  "rotary_pct": 0.25,23  "tie_word_embeddings": false,24  "torch_dtype": "float16",25  "transformers_version": "4.35.2",26  "use_cache": true,27  "use_parallel_residual": true,28  "vocab_size": 5030429}30