File size: 1,292 Bytes
779ec7d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "architectures": [
    "MPNetModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 64,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "mpnet",
  "neuron": {
    "auto_cast": null,
    "auto_cast_type": null,
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.19.8089.0+8ab9f450",
    "disable_fallback": false,
    "disable_fast_relayout": false,
    "dynamic_batch_size": false,
    "float_dtype": "fp32",
    "inline_weights_to_neff": true,
    "input_names": [
      "input_ids",
      "attention_mask"
    ],
    "int_dtype": "int64",
    "model_type": "mpnet",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "start_logits",
      "end_logits"
    ],
    "static_batch_size": 1,
    "static_sequence_length": 128,
    "task": "question-answering",
    "tensor_parallel_size": 1
  },
  "num_attention_heads": 4,
  "num_hidden_layers": 5,
  "pad_token_id": 1,
  "relative_attention_num_buckets": 32,
  "torch_dtype": "float32",
  "torchscript": true,
  "transformers_version": "4.55.4",
  "vocab_size": 1125
}