File size: 1,248 Bytes
91b25ac | 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 65 | {
"architectures": [
"PangolinModel"
],
"batch_norm_eps": 1e-05,
"batch_norm_momentum": 0.1,
"bos_token_id": null,
"context": 10000,
"dtype": "float32",
"eos_token_id": null,
"head": {
"act": null,
"bias": true,
"dropout": 0.0,
"hidden_size": 32,
"layer_norm_eps": 1e-12,
"loss_weight": null,
"num_labels": 4,
"output_name": null,
"problem_type": "regression",
"transform": null,
"transform_act": "gelu",
"type": null
},
"hidden_act": "relu",
"hidden_size": 32,
"id2label": null,
"label2id": null,
"mask_token_id": null,
"model_type": "pangolin",
"null_token_id": null,
"num_ensemble": 3,
"num_labels": 4,
"num_tissues": 4,
"output_contexts": false,
"pad_token_id": 4,
"problem_type": "regression",
"stages": [
{
"dilation": 1,
"kernel_size": 11,
"num_blocks": 4
},
{
"dilation": 4,
"kernel_size": 11,
"num_blocks": 4
},
{
"dilation": 10,
"kernel_size": 21,
"num_blocks": 4
},
{
"dilation": 25,
"kernel_size": 41,
"num_blocks": 4
}
],
"tie_word_embeddings": true,
"transformers_version": "5.7.0",
"unk_token_id": 4,
"vocab_size": 5
}
|