LightChen2333
commited on
Commit
•
68f7230
1
Parent(s):
905f31e
Upload 3 files
Browse files- config.json +19 -9
config.json
CHANGED
@@ -292,7 +292,7 @@
|
|
292 |
"mlp": [
|
293 |
{
|
294 |
"_model_target_": "torch.nn.Linear",
|
295 |
-
"in_features":
|
296 |
"out_features": 256
|
297 |
},
|
298 |
{
|
@@ -302,14 +302,14 @@
|
|
302 |
{
|
303 |
"_model_target_": "torch.nn.Linear",
|
304 |
"in_features": 256,
|
305 |
-
"out_features":
|
306 |
}
|
307 |
],
|
308 |
"mode": "intent",
|
309 |
"multi_threshold": 0.5,
|
310 |
"return_sentence_level": true,
|
311 |
"use_intent": true,
|
312 |
-
"use_multi":
|
313 |
"weight": 0.3
|
314 |
},
|
315 |
"interaction": {
|
@@ -317,12 +317,14 @@
|
|
317 |
"alpha": 0.2,
|
318 |
"dropout_rate": 0.4,
|
319 |
"hidden_dim": 128,
|
320 |
-
"input_dim":
|
321 |
"intent_embedding_dim": 128,
|
|
|
322 |
"num_heads": 4,
|
323 |
"num_layers": 2,
|
324 |
-
"output_dim":
|
325 |
-
"row_normalized": true
|
|
|
326 |
},
|
327 |
"slot_classifier": {
|
328 |
"_model_target_": "model.decoder.classifier.AutoregressiveLSTMClassifier",
|
@@ -330,9 +332,9 @@
|
|
330 |
"dropout_rate": 0.4,
|
331 |
"embedding_dim": 128,
|
332 |
"force_ratio": 0.9,
|
333 |
-
"hidden_dim":
|
334 |
"ignore_index": -100,
|
335 |
-
"input_dim":
|
336 |
"layer_num": 1,
|
337 |
"mode": "slot",
|
338 |
"multi_threshold": 0.5,
|
@@ -352,7 +354,8 @@
|
|
352 |
},
|
353 |
"embedding": {
|
354 |
"dropout_rate": 0.4,
|
355 |
-
"embedding_dim": 128
|
|
|
356 |
},
|
357 |
"encoder_name": "self-attention-lstm",
|
358 |
"lstm": {
|
@@ -370,6 +373,13 @@
|
|
370 |
}
|
371 |
},
|
372 |
"return_dict": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
373 |
"tokenizer_class": "OpenSLUv1",
|
374 |
"torch_dtype": "float32",
|
375 |
"transformers_version": "4.25.1",
|
|
|
292 |
"mlp": [
|
293 |
{
|
294 |
"_model_target_": "torch.nn.Linear",
|
295 |
+
"in_features": 384,
|
296 |
"out_features": 256
|
297 |
},
|
298 |
{
|
|
|
302 |
{
|
303 |
"_model_target_": "torch.nn.Linear",
|
304 |
"in_features": 256,
|
305 |
+
"out_features": 17
|
306 |
}
|
307 |
],
|
308 |
"mode": "intent",
|
309 |
"multi_threshold": 0.5,
|
310 |
"return_sentence_level": true,
|
311 |
"use_intent": true,
|
312 |
+
"use_multi": true,
|
313 |
"weight": 0.3
|
314 |
},
|
315 |
"interaction": {
|
|
|
317 |
"alpha": 0.2,
|
318 |
"dropout_rate": 0.4,
|
319 |
"hidden_dim": 128,
|
320 |
+
"input_dim": 384,
|
321 |
"intent_embedding_dim": 128,
|
322 |
+
"intent_label_num": 17,
|
323 |
"num_heads": 4,
|
324 |
"num_layers": 2,
|
325 |
+
"output_dim": 128,
|
326 |
+
"row_normalized": true,
|
327 |
+
"slot_label_num": 111
|
328 |
},
|
329 |
"slot_classifier": {
|
330 |
"_model_target_": "model.decoder.classifier.AutoregressiveLSTMClassifier",
|
|
|
332 |
"dropout_rate": 0.4,
|
333 |
"embedding_dim": 128,
|
334 |
"force_ratio": 0.9,
|
335 |
+
"hidden_dim": 128,
|
336 |
"ignore_index": -100,
|
337 |
+
"input_dim": 384,
|
338 |
"layer_num": 1,
|
339 |
"mode": "slot",
|
340 |
"multi_threshold": 0.5,
|
|
|
354 |
},
|
355 |
"embedding": {
|
356 |
"dropout_rate": 0.4,
|
357 |
+
"embedding_dim": 128,
|
358 |
+
"vocab_size": 790
|
359 |
},
|
360 |
"encoder_name": "self-attention-lstm",
|
361 |
"lstm": {
|
|
|
373 |
}
|
374 |
},
|
375 |
"return_dict": false,
|
376 |
+
"tokenizer": {
|
377 |
+
"_align_mode_": "fast",
|
378 |
+
"_padding_side_": "right",
|
379 |
+
"_tokenizer_name_": "word_tokenizer",
|
380 |
+
"add_special_tokens": false,
|
381 |
+
"max_length": 512
|
382 |
+
},
|
383 |
"tokenizer_class": "OpenSLUv1",
|
384 |
"torch_dtype": "float32",
|
385 |
"transformers_version": "4.25.1",
|