|
{ |
|
"_name_or_path": "train", |
|
"apply_residual_connection_post_layernorm": false, |
|
"architectures": [ |
|
"BloomForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"attention_softmax_in_fp32": true, |
|
"bias_dropout_fusion": true, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"hidden_dropout": 0.0, |
|
"hidden_size": 2048, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-05, |
|
"masked_softmax_fusion": true, |
|
"model_type": "bloom", |
|
"n_head": 16, |
|
"n_inner": null, |
|
"n_layer": 24, |
|
"offset_alibi": 100, |
|
"pad_token_id": 3, |
|
"pretraining_tp": 2, |
|
"seq_length": 4096, |
|
"skip_bias_add": true, |
|
"skip_bias_add_qkv": false, |
|
"slow_but_exact": false, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.26.1", |
|
"unk_token_id": 0, |
|
"use_cache": true, |
|
"vocab_size": 250880 |
|
} |
|
|