File size: 1,404 Bytes
09dd464 |
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 |
{
"_name_or_path": "hf-internal-testing/tiny-random-AlbertModel",
"architectures": [
"AlbertModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 2,
"classifier_dropout_prob": 0.1,
"embedding_size": 128,
"eos_token_id": 3,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 36,
"initializer_range": 0.02,
"inner_group_num": 1,
"intermediate_size": 37,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "albert",
"neuron": {
"auto_cast": null,
"auto_cast_type": null,
"compiler_type": "neuronx-cc",
"compiler_version": "2.15.128.0+56dc5a86",
"disable_fallback": false,
"disable_fast_relayout": false,
"dynamic_batch_size": true,
"inline_weights_to_neff": true,
"input_names": [
"input_ids",
"attention_mask",
"token_type_ids"
],
"model_type": "albert",
"optlevel": "2",
"output_attentions": false,
"output_hidden_states": false,
"output_names": [
"start_logits",
"end_logits"
],
"static_batch_size": 1,
"static_sequence_length": 32
},
"num_attention_heads": 6,
"num_hidden_groups": 6,
"num_hidden_layers": 6,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"task": "question-answering",
"torchscript": true,
"transformers_version": "4.43.2",
"type_vocab_size": 16,
"vocab_size": 30000
}
|