{ | |
"_name_or_path": "/home/younes/Desktop/Work/data/megatron-debug/", | |
"apply_residual_connection_post_layernorm": false, | |
"architectures": [ | |
"BloomModel" | |
], | |
"attention_dropout": 0.1, | |
"bias_dropout_fusion": true, | |
"bos_token_id": 0, | |
"dtype": "bfloat16", | |
"eos_token_id": 0, | |
"hidden_dropout": 0.1, | |
"hidden_size": 64, | |
"initializer_range": 0.02, | |
"layer_norm_epsilon": 1e-05, | |
"masked_softmax_fusion": true, | |
"model_type": "bloom", | |
"n_head": 8, | |
"n_inner": null, | |
"n_layer": 2, | |
"pretraining_tp": 2, | |
"seq_length": 20, | |
"skip_bias_add": true, | |
"torch_dtype": "bfloat16", | |
"transformers_version": "4.18.0.dev0", | |
"use_cache": false, | |
"vocab_size": 250880, | |
"slow_but_exact": true | |
} | |