File size: 1,111 Bytes
37f05c6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
{
"_name_or_path": "polish-gpt2-large",
"activation_function": "gelu_fast",
"architectures": [
"GPT2ForSequenceClassification"
],
"attn_pdrop": 0.1,
"bos_token_id": 0,
"embd_pdrop": 0.1,
"eos_token_id": 2,
"id2label": {
"0": "NEUTRAL",
"1": "NEGATIVE",
"2": "POSITIVE",
"3": "AMBIGUOUS"
},
"initializer_range": 0.02,
"label2id": {
"AMBIGUOUS": 3,
"NEGATIVE": 1,
"NEUTRAL": 0,
"POSITIVE": 2
},
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_embd": 1280,
"n_head": 20,
"n_inner": 5120,
"n_layer": 36,
"n_positions": 1536,
"pad_token_id": 2,
"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": "4.37.2",
"use_cache": true,
"vocab_size": 51200
}
|