| { | |
| "_name_or_path": "bigscience/bloom", | |
| "apply_residual_connection_post_layernorm": false, | |
| "architectures": [ | |
| "BloomForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attention_softmax_in_fp32": true, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_dropout": 0.0, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "masked_softmax_fusion": true, | |
| "model_type": "bloom", | |
| "n_embed": 14336, | |
| "n_layer": 70, | |
| "num_attention_heads": 112, | |
| "pretraining_tp": 4, | |
| "slow_but_exact": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.20.1", | |
| "use_cache": true, | |
| "vocab_size": 250880 | |
| } | |