46 lines
1.0 KiB
JSON
46 lines
1.0 KiB
JSON
|
{
|
||
|
|
"_name_or_path": "sdadas/polish-gpt2-small",
|
||
|
|
"activation_function": "gelu_fast",
|
||
|
|
"architectures": [
|
||
|
|
"GPT2ForSequenceClassification"
|
||
|
|
],
|
||
|
|
"attn_pdrop": 0.1,
|
||
|
|
"bos_token_id": 0,
|
||
|
|
"embd_pdrop": 0.1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"id2label": {
|
||
|
|
"0": "LABEL_0",
|
||
|
|
"1": "LABEL_1",
|
||
|
|
"2": "LABEL_2"
|
||
|
|
},
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"label2id": {
|
||
|
|
"LABEL_0": 0,
|
||
|
|
"LABEL_1": 1,
|
||
|
|
"LABEL_2": 2
|
||
|
|
},
|
||
|
|
"layer_norm_epsilon": 1e-05,
|
||
|
|
"model_type": "gpt2",
|
||
|
|
"n_embd": 768,
|
||
|
|
"n_head": 12,
|
||
|
|
"n_inner": 3072,
|
||
|
|
"n_layer": 12,
|
||
|
|
"n_positions": 2048,
|
||
|
|
"pad_token_id": 51200,
|
||
|
|
"problem_type": "single_label_classification",
|
||
|
|
"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,
|
||
|
|
"tokenizer_class": "GPT2TokenizerFast",
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.29.2",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 51201
|
||
|
|
}
|