Optimum
commited on
Commit
·
77378cd
1
Parent(s):
4c47022
Upload config.json with huggingface_hub
Browse files- config.json +21 -18
config.json
CHANGED
|
@@ -4,37 +4,40 @@
|
|
| 4 |
"BertModel"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"auto_cast": null,
|
| 8 |
-
"auto_cast_type": null,
|
| 9 |
"classifier_dropout": null,
|
| 10 |
-
"disable_fallback": true,
|
| 11 |
-
"disable_fast_relayout": false,
|
| 12 |
-
"dynamic_batch_size": true,
|
| 13 |
"hidden_act": "gelu",
|
| 14 |
"hidden_dropout_prob": 0.1,
|
| 15 |
"hidden_size": 32,
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
-
"input_names": [
|
| 18 |
-
"input_ids",
|
| 19 |
-
"attention_mask",
|
| 20 |
-
"token_type_ids"
|
| 21 |
-
],
|
| 22 |
"intermediate_size": 37,
|
| 23 |
"layer_norm_eps": 1e-12,
|
| 24 |
"max_position_embeddings": 512,
|
| 25 |
"model_type": "bert",
|
| 26 |
-
"
|
| 27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
"num_attention_heads": 4,
|
| 29 |
"num_hidden_layers": 5,
|
| 30 |
-
"output_names": [
|
| 31 |
-
"last_hidden_state",
|
| 32 |
-
"pooler_output"
|
| 33 |
-
],
|
| 34 |
"pad_token_id": 0,
|
| 35 |
"position_embedding_type": "absolute",
|
| 36 |
-
"
|
| 37 |
-
"transformers_version": "4.
|
| 38 |
"type_vocab_size": 16,
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 1124
|
|
|
|
| 4 |
"BertModel"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
|
|
|
| 7 |
"classifier_dropout": null,
|
|
|
|
|
|
|
|
|
|
| 8 |
"hidden_act": "gelu",
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 32,
|
| 11 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"intermediate_size": 37,
|
| 13 |
"layer_norm_eps": 1e-12,
|
| 14 |
"max_position_embeddings": 512,
|
| 15 |
"model_type": "bert",
|
| 16 |
+
"neuron": {
|
| 17 |
+
"auto_cast": null,
|
| 18 |
+
"auto_cast_type": null,
|
| 19 |
+
"compiler_type": "neuron-cc",
|
| 20 |
+
"compiler_version": "1.15.0.0+eec0c3604",
|
| 21 |
+
"disable_fallback": false,
|
| 22 |
+
"disable_fast_relayout": false,
|
| 23 |
+
"dynamic_batch_size": false,
|
| 24 |
+
"input_names": [
|
| 25 |
+
"input_ids",
|
| 26 |
+
"attention_mask",
|
| 27 |
+
"token_type_ids"
|
| 28 |
+
],
|
| 29 |
+
"output_names": [
|
| 30 |
+
"logits"
|
| 31 |
+
],
|
| 32 |
+
"static_batch_size": 1,
|
| 33 |
+
"static_sequence_length": 32
|
| 34 |
+
},
|
| 35 |
"num_attention_heads": 4,
|
| 36 |
"num_hidden_layers": 5,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
"pad_token_id": 0,
|
| 38 |
"position_embedding_type": "absolute",
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.31.0",
|
| 41 |
"type_vocab_size": 16,
|
| 42 |
"use_cache": true,
|
| 43 |
"vocab_size": 1124
|