bloomz-560m-lener_br / config.json
Luciano's picture
Upload BloomForTokenClassification
6099ab7
{
"_name_or_path": "bigscience/bloomz-560m",
"apply_residual_connection_post_layernorm": false,
"architectures": [
"BloomForTokenClassification"
],
"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": 1024,
"id2label": {
"0": "O",
"1": "B-ORGANIZACAO",
"2": "I-ORGANIZACAO",
"3": "B-PESSOA",
"4": "I-PESSOA",
"5": "B-TEMPO",
"6": "I-TEMPO",
"7": "B-LOCAL",
"8": "I-LOCAL",
"9": "B-LEGISLACAO",
"10": "I-LEGISLACAO",
"11": "B-JURISPRUDENCIA",
"12": "I-JURISPRUDENCIA"
},
"initializer_range": 0.02,
"label2id": {
"B-JURISPRUDENCIA": 11,
"B-LEGISLACAO": 9,
"B-LOCAL": 7,
"B-ORGANIZACAO": 1,
"B-PESSOA": 3,
"B-TEMPO": 5,
"I-JURISPRUDENCIA": 12,
"I-LEGISLACAO": 10,
"I-LOCAL": 8,
"I-ORGANIZACAO": 2,
"I-PESSOA": 4,
"I-TEMPO": 6,
"O": 0
},
"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": 1,
"seq_length": 2048,
"skip_bias_add": true,
"skip_bias_add_qkv": false,
"slow_but_exact": false,
"torch_dtype": "float32",
"transformers_version": "4.30.0.dev0",
"unk_token_id": 0,
"use_cache": true,
"vocab_size": 250880
}