bloom3b-2000-finetuned / config.json
zhanyil2's picture
Upload my fine-tuned model
e2f6495
{
"_name_or_path": "bigscience/bloom-3b",
"apply_residual_connection_post_layernorm": false,
"architectures": [
"BloomForSequenceClassification"
],
"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": 2560,
"id2label": {
"0": "anger",
"1": "anticipation",
"2": "disgust",
"3": "fear",
"4": "joy",
"5": "love",
"6": "optimism",
"7": "pessimism",
"8": "sadness",
"9": "surprise",
"10": "trust"
},
"initializer_range": 0.02,
"label2id": {
"anger": 0,
"anticipation": 1,
"disgust": 2,
"fear": 3,
"joy": 4,
"love": 5,
"optimism": 6,
"pessimism": 7,
"sadness": 8,
"surprise": 9,
"trust": 10
},
"layer_norm_epsilon": 1e-05,
"masked_softmax_fusion": true,
"model_type": "bloom",
"n_head": 32,
"n_inner": null,
"n_layer": 30,
"offset_alibi": 100,
"pad_token_id": 3,
"pretraining_tp": 4,
"problem_type": "multi_label_classification",
"skip_bias_add": true,
"skip_bias_add_qkv": false,
"slow_but_exact": false,
"torch_dtype": "float32",
"transformers_version": "4.38.2",
"unk_token_id": 0,
"use_cache": true,
"vocab_size": 250880
}