bloom-full_labels / config.json
Theoreticallyhugo's picture
Training in progress, epoch 1
d2113ac verified
{
"_name_or_path": "bigscience/bloom-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-MajorClaim",
"2": "I-MajorClaim",
"3": "B-Claim",
"4": "I-Claim",
"5": "B-Premise",
"6": "I-Premise"
},
"initializer_range": 0.02,
"label2id": {
"B-Claim": 3,
"B-MajorClaim": 1,
"B-Premise": 5,
"I-Claim": 4,
"I-MajorClaim": 2,
"I-Premise": 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,
"skip_bias_add": true,
"skip_bias_add_qkv": false,
"slow_but_exact": false,
"torch_dtype": "float32",
"transformers_version": "4.37.2",
"unk_token_id": 0,
"use_cache": true,
"vocab_size": 250880
}