Retrain on real mteb/amazon_massive_intent: acc=88.2 f1=85.1
Browse files- README.md +17 -8
- config.json +128 -45
- model.safetensors +2 -2
- tokenizer_config.json +3 -45
README.md
CHANGED
|
@@ -4,18 +4,27 @@ license: mit
|
|
| 4 |
pipeline_tag: text-classification
|
| 5 |
base_model: dbmdz/bert-base-turkish-cased
|
| 6 |
tags: [turkish, text-classification, werea]
|
| 7 |
-
datasets: [
|
|
|
|
| 8 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
-
> ℹ️ Bu, [Werea-co/Werea-TR-Intent](https://huggingface.co/Werea-co/Werea-TR-Intent) modelinin GoktugD profilindeki aynasıdır; asıl geliştirme Werea-co altında sürer.
|
| 11 |
-
# Werea-TR-Intent — Türkçe e-ticaret niyet sınıflandırma
|
| 12 |
-
[dbmdz/bert-base-turkish-cased](https://huggingface.co/dbmdz/bert-base-turkish-cased) tabanının Türkçe e-ticaret niyet sınıflandırma için fine-tune'u.
|
| 13 |
-
20 sınıf. Doğrulama: **accuracy 100.0%**, macro-F1 100.0%.
|
| 14 |
-
> Not: Sentetik ([GoktugD/turkish-intent-classification-1m](https://huggingface.co/datasets/GoktugD/turkish-intent-classification-1m)) veriyle eğitildi; gerçek-dünya kullanımında doğrulama önerilir.
|
| 15 |
## Kullanım
|
| 16 |
```python
|
| 17 |
from transformers import pipeline
|
| 18 |
-
clf
|
| 19 |
-
print(clf("
|
| 20 |
```
|
| 21 |
💜 [werea.co](https://werea.co)
|
|
|
|
| 4 |
pipeline_tag: text-classification
|
| 5 |
base_model: dbmdz/bert-base-turkish-cased
|
| 6 |
tags: [turkish, text-classification, werea]
|
| 7 |
+
datasets: [mteb/amazon_massive_intent]
|
| 8 |
+
metrics: [accuracy, f1]
|
| 9 |
---
|
| 10 |
+
> ℹ️ [Werea-co/Werea-TR-Intent](https://huggingface.co/Werea-co/Werea-TR-Intent) aynasıdır.
|
| 11 |
+
|
| 12 |
+
# Werea-TR-Intent — Türkçe niyet sınıflandırma
|
| 13 |
+
|
| 14 |
+
**Gerçek, insan-etiketli [mteb/amazon_massive_intent](https://huggingface.co/datasets/mteb/amazon_massive_intent) verisiyle eğitildi; aynı setin ayrılmış test bölümünde dürüstçe ölçüldü.** 60 sınıf.
|
| 15 |
+
|
| 16 |
+
## Benchmark (gerçek test)
|
| 17 |
+
| Metrik | Skor |
|
| 18 |
+
|---|---|
|
| 19 |
+
| Accuracy | 88.2% |
|
| 20 |
+
| Macro-F1 | 85.1% |
|
| 21 |
+
|
| 22 |
+
[BERTurk](https://huggingface.co/dbmdz/bert-base-turkish-cased) tabanlı, 6 epoch.
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
## Kullanım
|
| 25 |
```python
|
| 26 |
from transformers import pipeline
|
| 27 |
+
clf=pipeline("text-classification",model="Werea-co/Werea-TR-Intent")
|
| 28 |
+
print(clf("text metni"))
|
| 29 |
```
|
| 30 |
💜 [werea.co](https://werea.co)
|
config.json
CHANGED
|
@@ -1,58 +1,142 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 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": 768,
|
| 11 |
"id2label": {
|
| 12 |
-
"0": "
|
| 13 |
-
"1": "
|
| 14 |
-
"2": "
|
| 15 |
-
"3": "
|
| 16 |
-
"4": "
|
| 17 |
-
"5": "
|
| 18 |
-
"6": "
|
| 19 |
-
"7": "
|
| 20 |
-
"8": "
|
| 21 |
-
"9": "
|
| 22 |
-
"10": "
|
| 23 |
-
"11": "
|
| 24 |
-
"12": "
|
| 25 |
-
"13": "
|
| 26 |
-
"14": "
|
| 27 |
-
"15": "
|
| 28 |
-
"16": "
|
| 29 |
-
"17": "
|
| 30 |
-
"18": "
|
| 31 |
-
"19": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
},
|
| 33 |
"initializer_range": 0.02,
|
| 34 |
"intermediate_size": 3072,
|
|
|
|
| 35 |
"label2id": {
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
},
|
| 57 |
"layer_norm_eps": 1e-12,
|
| 58 |
"max_position_embeddings": 512,
|
|
@@ -60,11 +144,10 @@
|
|
| 60 |
"num_attention_heads": 12,
|
| 61 |
"num_hidden_layers": 12,
|
| 62 |
"pad_token_id": 0,
|
| 63 |
-
"position_embedding_type": "absolute",
|
| 64 |
"problem_type": "single_label_classification",
|
| 65 |
-
"
|
| 66 |
-
"transformers_version": "
|
| 67 |
"type_vocab_size": 2,
|
| 68 |
-
"use_cache":
|
| 69 |
"vocab_size": 32000
|
| 70 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
"hidden_act": "gelu",
|
| 12 |
"hidden_dropout_prob": 0.1,
|
| 13 |
"hidden_size": 768,
|
| 14 |
"id2label": {
|
| 15 |
+
"0": "alarm_query",
|
| 16 |
+
"1": "alarm_remove",
|
| 17 |
+
"2": "alarm_set",
|
| 18 |
+
"3": "audio_volume_down",
|
| 19 |
+
"4": "audio_volume_mute",
|
| 20 |
+
"5": "audio_volume_other",
|
| 21 |
+
"6": "audio_volume_up",
|
| 22 |
+
"7": "calendar_query",
|
| 23 |
+
"8": "calendar_remove",
|
| 24 |
+
"9": "calendar_set",
|
| 25 |
+
"10": "cooking_query",
|
| 26 |
+
"11": "cooking_recipe",
|
| 27 |
+
"12": "datetime_convert",
|
| 28 |
+
"13": "datetime_query",
|
| 29 |
+
"14": "email_addcontact",
|
| 30 |
+
"15": "email_query",
|
| 31 |
+
"16": "email_querycontact",
|
| 32 |
+
"17": "email_sendemail",
|
| 33 |
+
"18": "general_greet",
|
| 34 |
+
"19": "general_joke",
|
| 35 |
+
"20": "general_quirky",
|
| 36 |
+
"21": "iot_cleaning",
|
| 37 |
+
"22": "iot_coffee",
|
| 38 |
+
"23": "iot_hue_lightchange",
|
| 39 |
+
"24": "iot_hue_lightdim",
|
| 40 |
+
"25": "iot_hue_lightoff",
|
| 41 |
+
"26": "iot_hue_lighton",
|
| 42 |
+
"27": "iot_hue_lightup",
|
| 43 |
+
"28": "iot_wemo_off",
|
| 44 |
+
"29": "iot_wemo_on",
|
| 45 |
+
"30": "lists_createoradd",
|
| 46 |
+
"31": "lists_query",
|
| 47 |
+
"32": "lists_remove",
|
| 48 |
+
"33": "music_dislikeness",
|
| 49 |
+
"34": "music_likeness",
|
| 50 |
+
"35": "music_query",
|
| 51 |
+
"36": "music_settings",
|
| 52 |
+
"37": "news_query",
|
| 53 |
+
"38": "play_audiobook",
|
| 54 |
+
"39": "play_game",
|
| 55 |
+
"40": "play_music",
|
| 56 |
+
"41": "play_podcasts",
|
| 57 |
+
"42": "play_radio",
|
| 58 |
+
"43": "qa_currency",
|
| 59 |
+
"44": "qa_definition",
|
| 60 |
+
"45": "qa_factoid",
|
| 61 |
+
"46": "qa_maths",
|
| 62 |
+
"47": "qa_stock",
|
| 63 |
+
"48": "recommendation_events",
|
| 64 |
+
"49": "recommendation_locations",
|
| 65 |
+
"50": "recommendation_movies",
|
| 66 |
+
"51": "social_post",
|
| 67 |
+
"52": "social_query",
|
| 68 |
+
"53": "takeaway_order",
|
| 69 |
+
"54": "takeaway_query",
|
| 70 |
+
"55": "transport_query",
|
| 71 |
+
"56": "transport_taxi",
|
| 72 |
+
"57": "transport_ticket",
|
| 73 |
+
"58": "transport_traffic",
|
| 74 |
+
"59": "weather_query"
|
| 75 |
},
|
| 76 |
"initializer_range": 0.02,
|
| 77 |
"intermediate_size": 3072,
|
| 78 |
+
"is_decoder": false,
|
| 79 |
"label2id": {
|
| 80 |
+
"alarm_query": 0,
|
| 81 |
+
"alarm_remove": 1,
|
| 82 |
+
"alarm_set": 2,
|
| 83 |
+
"audio_volume_down": 3,
|
| 84 |
+
"audio_volume_mute": 4,
|
| 85 |
+
"audio_volume_other": 5,
|
| 86 |
+
"audio_volume_up": 6,
|
| 87 |
+
"calendar_query": 7,
|
| 88 |
+
"calendar_remove": 8,
|
| 89 |
+
"calendar_set": 9,
|
| 90 |
+
"cooking_query": 10,
|
| 91 |
+
"cooking_recipe": 11,
|
| 92 |
+
"datetime_convert": 12,
|
| 93 |
+
"datetime_query": 13,
|
| 94 |
+
"email_addcontact": 14,
|
| 95 |
+
"email_query": 15,
|
| 96 |
+
"email_querycontact": 16,
|
| 97 |
+
"email_sendemail": 17,
|
| 98 |
+
"general_greet": 18,
|
| 99 |
+
"general_joke": 19,
|
| 100 |
+
"general_quirky": 20,
|
| 101 |
+
"iot_cleaning": 21,
|
| 102 |
+
"iot_coffee": 22,
|
| 103 |
+
"iot_hue_lightchange": 23,
|
| 104 |
+
"iot_hue_lightdim": 24,
|
| 105 |
+
"iot_hue_lightoff": 25,
|
| 106 |
+
"iot_hue_lighton": 26,
|
| 107 |
+
"iot_hue_lightup": 27,
|
| 108 |
+
"iot_wemo_off": 28,
|
| 109 |
+
"iot_wemo_on": 29,
|
| 110 |
+
"lists_createoradd": 30,
|
| 111 |
+
"lists_query": 31,
|
| 112 |
+
"lists_remove": 32,
|
| 113 |
+
"music_dislikeness": 33,
|
| 114 |
+
"music_likeness": 34,
|
| 115 |
+
"music_query": 35,
|
| 116 |
+
"music_settings": 36,
|
| 117 |
+
"news_query": 37,
|
| 118 |
+
"play_audiobook": 38,
|
| 119 |
+
"play_game": 39,
|
| 120 |
+
"play_music": 40,
|
| 121 |
+
"play_podcasts": 41,
|
| 122 |
+
"play_radio": 42,
|
| 123 |
+
"qa_currency": 43,
|
| 124 |
+
"qa_definition": 44,
|
| 125 |
+
"qa_factoid": 45,
|
| 126 |
+
"qa_maths": 46,
|
| 127 |
+
"qa_stock": 47,
|
| 128 |
+
"recommendation_events": 48,
|
| 129 |
+
"recommendation_locations": 49,
|
| 130 |
+
"recommendation_movies": 50,
|
| 131 |
+
"social_post": 51,
|
| 132 |
+
"social_query": 52,
|
| 133 |
+
"takeaway_order": 53,
|
| 134 |
+
"takeaway_query": 54,
|
| 135 |
+
"transport_query": 55,
|
| 136 |
+
"transport_taxi": 56,
|
| 137 |
+
"transport_ticket": 57,
|
| 138 |
+
"transport_traffic": 58,
|
| 139 |
+
"weather_query": 59
|
| 140 |
},
|
| 141 |
"layer_norm_eps": 1e-12,
|
| 142 |
"max_position_embeddings": 512,
|
|
|
|
| 144 |
"num_attention_heads": 12,
|
| 145 |
"num_hidden_layers": 12,
|
| 146 |
"pad_token_id": 0,
|
|
|
|
| 147 |
"problem_type": "single_label_classification",
|
| 148 |
+
"tie_word_embeddings": true,
|
| 149 |
+
"transformers_version": "5.14.1",
|
| 150 |
"type_vocab_size": 2,
|
| 151 |
+
"use_cache": false,
|
| 152 |
"vocab_size": 32000
|
| 153 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c96e7349bcd4b527aa2513c833da644c9508a5f1083b321bea95c3d57763d3
|
| 3 |
+
size 442677472
|
tokenizer_config.json
CHANGED
|
@@ -1,54 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "[PAD]",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "[UNK]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"4": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
-
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": false,
|
|
|
|
|
|
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"max_len": 512,
|
| 50 |
"model_max_length": 512,
|
| 51 |
-
"never_split": null,
|
| 52 |
"pad_token": "[PAD]",
|
| 53 |
"sep_token": "[SEP]",
|
| 54 |
"strip_accents": null,
|
|
|
|
| 1 |
{
|
| 2 |
+
"backend": "tokenizers",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"cls_token": "[CLS]",
|
|
|
|
| 4 |
"do_lower_case": false,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
"mask_token": "[MASK]",
|
| 8 |
"max_len": 512,
|
| 9 |
"model_max_length": 512,
|
|
|
|
| 10 |
"pad_token": "[PAD]",
|
| 11 |
"sep_token": "[SEP]",
|
| 12 |
"strip_accents": null,
|