{ "apply_residual_connection_post_layernorm": false, "architectures": [ "BloomForCausalLM" ], "attention_dropout": 0.0, "attention_softmax_in_fp32": true, "bos_token_id": 1, "dht_prefix": "bigscience/bloom-petals", "eos_token_id": 2, "hidden_dropout": 0.0, "hidden_size": 14336, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "masked_softmax_fusion": true, "model_type": "bloom", "n_head": 112, "n_layer": 70, "pad_token_id": 3, "pretraining_tp": 4, "slow_but_exact": false, "transformers_version": "4.21.0.dev0", "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 250880 }