Wikian_mgpt_34 / config.json
terzimert's picture
Training in progress, epoch 0
852ed78
raw
history blame
1.12 kB
{
"_name_or_path": "ai-forever/mGPT",
"activation_function": "gelu_new",
"architectures": [
"GPT2ForTokenClassification"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"gradient_checkpointing": false,
"id2label": {
"0": "O",
"1": "B-PER",
"2": "I-PER",
"3": "B-ORG",
"4": "I-ORG",
"5": "B-LOC",
"6": "I-LOC"
},
"initializer_range": 0.02,
"label2id": {
"B-LOC": 5,
"B-ORG": 3,
"B-PER": 1,
"I-LOC": 6,
"I-ORG": 4,
"I-PER": 2,
"O": 0
},
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 2048,
"n_embd": 2048,
"n_head": 16,
"n_inner": null,
"n_layer": 24,
"n_positions": 2048,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.28.0",
"use_cache": true,
"vocab_size": 100001
}