add model
Browse files- README.md +9 -50
- config.json +64 -64
- tf_model.h5 +3 -0
README.md
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_keras_callback
|
| 5 |
model-index:
|
|
@@ -12,77 +11,37 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# Intent-Classification-Bert-Base-Cased
|
| 14 |
|
| 15 |
-
This model
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
|
| 18 |
-
- Train Sparse Categorical Accuracy: 0.9836
|
| 19 |
-
- Validation Loss: 0.4073
|
| 20 |
-
- Validation Sparse Categorical Accuracy: 0.9583
|
| 21 |
-
- Epoch: 3
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
```
|
| 28 |
-
{
|
| 29 |
-
"0": "asking date",
|
| 30 |
-
"1": "asking time",
|
| 31 |
-
"2": "asking weather",
|
| 32 |
-
"3": "check internet speed",
|
| 33 |
-
"4": "click photo",
|
| 34 |
-
"5": "covid cases",
|
| 35 |
-
"6": "download youtube video",
|
| 36 |
-
"7": "goodbye",
|
| 37 |
-
"8": "greet",
|
| 38 |
-
"9": "open website",
|
| 39 |
-
"10": "play games",
|
| 40 |
-
"11": "play on youtube",
|
| 41 |
-
"12": "send email",
|
| 42 |
-
"13": "send whatsapp message",
|
| 43 |
-
"14": "take screenshot",
|
| 44 |
-
"15": "tell me about",
|
| 45 |
-
"16": "tell me joke",
|
| 46 |
-
"17": "tell me news"
|
| 47 |
-
}
|
| 48 |
-
```
|
| 49 |
|
| 50 |
## Intended uses & limitations
|
| 51 |
|
| 52 |
-
|
| 53 |
-
Only supports the English language. It can't work in outside classes. But you can fine-tune it for your own use.
|
| 54 |
|
| 55 |
## Training and evaluation data
|
| 56 |
|
| 57 |
-
|
| 58 |
|
| 59 |
## Training procedure
|
| 60 |
|
| 61 |
-
https://colab.research.google.com/drive/1KHg14glvhdV_ziOcY0pHm66PBYoBZMS0?usp=sharing
|
| 62 |
-
|
| 63 |
### Training hyperparameters
|
| 64 |
|
| 65 |
-
|
| 66 |
The following hyperparameters were used during training:
|
| 67 |
-
- optimizer:
|
| 68 |
- training_precision: float32
|
| 69 |
|
| 70 |
### Training results
|
| 71 |
|
| 72 |
-

|
| 73 |
|
| 74 |
-

|
| 75 |
|
| 76 |
### Framework versions
|
| 77 |
|
| 78 |
-
- Transformers 4.
|
| 79 |
-
- TensorFlow 2.
|
| 80 |
- Datasets 2.2.2
|
| 81 |
-
- Tokenizers 0.
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
## Connect me on-
|
| 85 |
-
|
| 86 |
-
* Subscribe to me on: https://youtube.com/techportofficial
|
| 87 |
-
|
| 88 |
-
* DM me on (for quick response): https://instagram.com/dipesh_pal17
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_keras_callback
|
| 4 |
model-index:
|
|
|
|
| 11 |
|
| 12 |
# Intent-Classification-Bert-Base-Cased
|
| 13 |
|
| 14 |
+
This model was trained from scratch on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
| 20 |
+
More information needed
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Intended uses & limitations
|
| 23 |
|
| 24 |
+
More information needed
|
|
|
|
| 25 |
|
| 26 |
## Training and evaluation data
|
| 27 |
|
| 28 |
+
More information needed
|
| 29 |
|
| 30 |
## Training procedure
|
| 31 |
|
|
|
|
|
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
|
|
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
+
- optimizer: None
|
| 36 |
- training_precision: float32
|
| 37 |
|
| 38 |
### Training results
|
| 39 |
|
|
|
|
| 40 |
|
|
|
|
| 41 |
|
| 42 |
### Framework versions
|
| 43 |
|
| 44 |
+
- Transformers 4.16.2
|
| 45 |
+
- TensorFlow 2.9.1
|
| 46 |
- Datasets 2.2.2
|
| 47 |
+
- Tokenizers 0.10.3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -1,65 +1,65 @@
|
|
| 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 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "models/Intent-Classification-Bert-Base-Cased/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "asking date",
|
| 14 |
+
"1": "asking time",
|
| 15 |
+
"2": "asking weather",
|
| 16 |
+
"3": "check internet speed",
|
| 17 |
+
"4": "click photo",
|
| 18 |
+
"5": "covid cases",
|
| 19 |
+
"6": "download youtube video",
|
| 20 |
+
"7": "goodbye",
|
| 21 |
+
"8": "greet",
|
| 22 |
+
"9": "open website",
|
| 23 |
+
"10": "play games",
|
| 24 |
+
"11": "play on youtube",
|
| 25 |
+
"12": "send email",
|
| 26 |
+
"13": "send whatsapp message",
|
| 27 |
+
"14": "take screenshot",
|
| 28 |
+
"15": "tell me about",
|
| 29 |
+
"16": "tell me joke",
|
| 30 |
+
"17": "tell me news"
|
| 31 |
+
},
|
| 32 |
+
"initializer_range": 0.02,
|
| 33 |
+
"intermediate_size": 3072,
|
| 34 |
+
"label2id": {
|
| 35 |
+
"asking date": "0",
|
| 36 |
+
"asking time": "1",
|
| 37 |
+
"asking weather": "2",
|
| 38 |
+
"check internet speed": "3",
|
| 39 |
+
"click photo": "4",
|
| 40 |
+
"covid cases": "5",
|
| 41 |
+
"download youtube video": "6",
|
| 42 |
+
"goodbye": "7",
|
| 43 |
+
"greet": "8",
|
| 44 |
+
"open website": "9",
|
| 45 |
+
"play games": "10",
|
| 46 |
+
"play on youtube": "11",
|
| 47 |
+
"send email": "12",
|
| 48 |
+
"send whatsapp message": "13",
|
| 49 |
+
"take screenshot": "14",
|
| 50 |
+
"tell me about": "15",
|
| 51 |
+
"tell me joke": "16",
|
| 52 |
+
"tell me news": "17"
|
| 53 |
+
},
|
| 54 |
+
"layer_norm_eps": 1e-12,
|
| 55 |
+
"max_position_embeddings": 512,
|
| 56 |
+
"model_type": "bert",
|
| 57 |
+
"num_attention_heads": 12,
|
| 58 |
+
"num_hidden_layers": 12,
|
| 59 |
+
"pad_token_id": 0,
|
| 60 |
+
"position_embedding_type": "absolute",
|
| 61 |
+
"transformers_version": "4.16.2",
|
| 62 |
+
"type_vocab_size": 2,
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"vocab_size": 28996
|
| 65 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bdb112ddf8fe06dcbf3e3b1be8cf82388656f89126fc3f6351e2afda583e4c7
|
| 3 |
+
size 433584536
|