File size: 1,351 Bytes
5514627 1e6cb1e 5514627 1e6cb1e 5514627 7d24b88 5514627 |
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 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
{
"_name_or_path": "gpt2",
"activation_function": "gelu_new",
"adapters": {
"adapters": {},
"config_map": {},
"fusion_config_map": {},
"fusions": {}
},
"architectures": [
"GPT2ForSequenceClassification"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"id2label": {
"0": "sadness",
"1": "joy",
"2": "love",
"3": "anger",
"4": "fear",
"5": "surprise"
},
"initializer_range": 0.02,
"label2id": {
"anger": 3,
"fear": 4,
"joy": 1,
"love": 2,
"sadness": 0,
"surprise": 5
},
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": 50256,
"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,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"torch_dtype": "float32",
"transformers_version": "4.26.1",
"use_cache": true,
"vocab_size": 50257
}
|