Skip to content

Commit 7a4975b

Browse files
authored
Fix Class Name for PretrainedTokenizer (#71)
* Fix Class Name for PreTrainedTokenizer.php * Fix Folder Name & Also Namespace.
1 parent dca7551 commit 7a4975b

File tree

67 files changed

+295
-295
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

67 files changed

+295
-295
lines changed

docs/tokenizers.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -76,7 +76,7 @@ any tokenizer from the Hugging Face model hub. Here's how to create a tokenizer
7676
class:
7777

7878
```php
79-
use Codewithkyrian\Transformers\PretrainedTokenizers\AutoTokenizer;
79+
use Codewithkyrian\Transformers\PreTrainedTokenizers\AutoTokenizer;
8080

8181
$tokenizer = AutoTokenizer::fromPretrained('Xenova/toxic-bert');
8282
```
@@ -135,11 +135,11 @@ class, you can still skip that step and use the specific tokenizer class directl
135135
have more control over the tokenization process. Here's an example of how to use the `BertTokenizer` class directly:
136136

137137
```php
138-
use Codewithkyrian\Transformers\PretrainedTokenizers\BertTokenizer;
138+
use Codewithkyrian\Transformers\PreTrainedTokenizers\BertTokenizer;
139139

140140
$tokenizer = BertTokenizer::fromPretrained('Xenova/toxic-bert');
141141
```
142142

143143
The `fromPretrained` method of the `BertTokenizer` class accepts the same arguments as the `AutoTokenizer` class. You
144144
can
145-
see all available model specific tokenizers in the `Codewithkyrian\Transformers\PretrainedTokenizers` namespace.
145+
see all available model specific tokenizers in the `Codewithkyrian\Transformers\PreTrainedTokenizers` namespace.

examples/tokenizers/apply-chat-template.php

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
declare(strict_types=1);
44

5-
use Codewithkyrian\Transformers\PretrainedTokenizers\AutoTokenizer;
5+
use Codewithkyrian\Transformers\PreTrainedTokenizers\AutoTokenizer;
66

77
require_once './bootstrap.php';
88

@@ -17,4 +17,4 @@
1717

1818
$text = $tokenizer->applyChatTemplate($messages, addGenerationPrompt: true, tokenize: false);
1919

20-
dd($text);
20+
dd($text);

src/Commands/DownloadModelCommand.php

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@
77

88
use Codewithkyrian\Transformers\Models\Auto\AutoModel;
99
use Codewithkyrian\Transformers\Pipelines\Task;
10-
use Codewithkyrian\Transformers\PretrainedTokenizers\AutoTokenizer;
10+
use Codewithkyrian\Transformers\PreTrainedTokenizers\AutoTokenizer;
1111
use Codewithkyrian\Transformers\Transformers;
1212
use Exception;
1313
use Symfony\Component\Console\Attribute\AsCommand;

src/Generation/Streamers/Streamer.php

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55

66
namespace Codewithkyrian\Transformers\Generation\Streamers;
77

8-
use Codewithkyrian\Transformers\PretrainedTokenizers\PretrainedTokenizer;
8+
use Codewithkyrian\Transformers\PreTrainedTokenizers\PreTrainedTokenizer;
99

1010
/**
1111
* Base streamer from which all streamers inherit.
@@ -16,7 +16,7 @@ abstract class Streamer
1616
protected bool $skipPrompt = false;
1717
protected bool $nextTokensArePrompt;
1818

19-
protected PretrainedTokenizer $tokenizer;
19+
protected PreTrainedTokenizer $tokenizer;
2020
protected mixed $onStreamCallback = null;
2121
protected mixed $onStreamEndCallback = null;
2222
protected StreamMode $streamMode = StreamMode::PARTIAL;
@@ -26,7 +26,7 @@ public static function make(): static
2626
return new static();
2727
}
2828

29-
public function setTokenizer(PretrainedTokenizer $tokenizer): static
29+
public function setTokenizer(PreTrainedTokenizer $tokenizer): static
3030
{
3131
$this->tokenizer = $tokenizer;
3232
return $this;
@@ -67,4 +67,4 @@ abstract public function put(mixed $value): void;
6767

6868
abstract public function end(): void;
6969

70-
}
70+
}

src/Generation/Streamers/TextStreamer.php

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44

55
namespace Codewithkyrian\Transformers\Generation\Streamers;
66

7-
use Codewithkyrian\Transformers\PretrainedTokenizers\PretrainedTokenizer;
7+
use Codewithkyrian\Transformers\PreTrainedTokenizers\PreTrainedTokenizer;
88
use InvalidArgumentException;
99

1010
/**

src/Pipelines/Pipeline.php

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@
66

77
use Codewithkyrian\Transformers\Exceptions\UnsupportedTaskException;
88
use Codewithkyrian\Transformers\Models\Pretrained\PretrainedModel;
9-
use Codewithkyrian\Transformers\PretrainedTokenizers\PretrainedTokenizer;
9+
use Codewithkyrian\Transformers\PreTrainedTokenizers\PreTrainedTokenizer;
1010
use Codewithkyrian\Transformers\Processors\Processor;
1111
use Codewithkyrian\Transformers\Tensor\Tensor;
1212
use Codewithkyrian\Transformers\Utils\Image;
@@ -16,7 +16,7 @@ class Pipeline
1616
public function __construct(
1717
protected string|Task $task,
1818
protected PretrainedModel $model,
19-
public ?PretrainedTokenizer $tokenizer = null,
19+
public ?PreTrainedTokenizer $tokenizer = null,
2020
protected ?Processor $processor = null,
2121
)
2222
{

src/Pipelines/Task.php

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -23,8 +23,8 @@
2323
use Codewithkyrian\Transformers\Models\Auto\AutoModelForVision2Seq;
2424
use Codewithkyrian\Transformers\Models\Auto\AutoModelForZeroShotObjectDetection;
2525
use Codewithkyrian\Transformers\Models\Pretrained\PretrainedModel;
26-
use Codewithkyrian\Transformers\PretrainedTokenizers\AutoTokenizer;
27-
use Codewithkyrian\Transformers\PretrainedTokenizers\PretrainedTokenizer;
26+
use Codewithkyrian\Transformers\PreTrainedTokenizers\AutoTokenizer;
27+
use Codewithkyrian\Transformers\PreTrainedTokenizers\PreTrainedTokenizer;
2828
use Codewithkyrian\Transformers\Processors\AutoProcessor;
2929
use Codewithkyrian\Transformers\Processors\Processor;
3030

@@ -59,7 +59,7 @@ enum Task: string
5959
case ASR = 'asr';
6060

6161

62-
public function pipeline(PretrainedModel $model, ?PretrainedTokenizer $tokenizer, ?Processor $processor): Pipeline
62+
public function pipeline(PretrainedModel $model, ?PreTrainedTokenizer $tokenizer, ?Processor $processor): Pipeline
6363
{
6464
return match ($this) {
6565
self::SentimentAnalysis,
@@ -214,7 +214,7 @@ public function autoTokenizer(
214214
?string $cacheDir = null,
215215
string $revision = 'main',
216216
?callable $onProgress = null
217-
): ?PretrainedTokenizer
217+
): ?PreTrainedTokenizer
218218
{
219219
return match ($this) {
220220

src/Pipelines/ZeroShotClassificationPipeline.php

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@
77

88
use Codewithkyrian\Transformers\Models\Output\SequenceClassifierOutput;
99
use Codewithkyrian\Transformers\Models\Pretrained\PretrainedModel;
10-
use Codewithkyrian\Transformers\PretrainedTokenizers\PretrainedTokenizer;
10+
use Codewithkyrian\Transformers\PreTrainedTokenizers\PreTrainedTokenizer;
1111
use Codewithkyrian\Transformers\Utils\Math;
1212
use function Codewithkyrian\Transformers\Utils\timeUsage;
1313

@@ -59,7 +59,7 @@ class ZeroShotClassificationPipeline extends Pipeline
5959

6060
protected mixed $contradictionId;
6161

62-
public function __construct(Task|string $task, PretrainedModel $model, ?PretrainedTokenizer $tokenizer = null, ?string $processor = null)
62+
public function __construct(Task|string $task, PretrainedModel $model, ?PreTrainedTokenizer $tokenizer = null, ?string $processor = null)
6363
{
6464
parent::__construct($task, $model, $tokenizer, $processor);
6565

@@ -140,4 +140,4 @@ public function __invoke(array|string $inputs, ...$args): array
140140

141141
return $isBatched ? $toReturn : $toReturn[0];
142142
}
143-
}
143+
}

src/PretrainedTokenizers/AlbertTokenizer.php renamed to src/PreTrainedTokenizers/AlbertTokenizer.php

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -3,12 +3,12 @@
33
declare(strict_types=1);
44

55

6-
namespace Codewithkyrian\Transformers\PretrainedTokenizers;
6+
namespace Codewithkyrian\Transformers\PreTrainedTokenizers;
77

88
/**
99
* Albert tokenizer
1010
*/
11-
class AlbertTokenizer extends PretrainedTokenizer
11+
class AlbertTokenizer extends PreTrainedTokenizer
1212
{
1313
protected bool $returnTokenTypeIds = true;
14-
}
14+
}

src/PretrainedTokenizers/AutoTokenizer.php renamed to src/PreTrainedTokenizers/AutoTokenizer.php

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33
declare(strict_types=1);
44

55

6-
namespace Codewithkyrian\Transformers\PretrainedTokenizers;
6+
namespace Codewithkyrian\Transformers\PreTrainedTokenizers;
77

88
use Codewithkyrian\Transformers\Tokenizers\Tokenizer;
99
use Symfony\Component\Console\Output\OutputInterface;
@@ -75,15 +75,15 @@ class AutoTokenizer
7575
* @param string $revision
7676
* @param mixed $legacy
7777
* @param OutputInterface|null $output
78-
* @return PretrainedTokenizer|null
78+
* @return PreTrainedTokenizer|null
7979
*/
8080
public static function fromPretrained(
8181
string $modelNameOrPath,
8282
?string $cacheDir = null,
8383
string $revision = 'main',
8484
mixed $legacy = null,
8585
?callable $onProgress = null
86-
): ?PretrainedTokenizer
86+
): ?PreTrainedTokenizer
8787
{
8888
['tokenizerJson' => $tokenizerJson, 'tokenizerConfig' => $tokenizerConfig] =
8989
Tokenizer::load($modelNameOrPath, $cacheDir, $revision, $legacy, $onProgress);
@@ -107,4 +107,4 @@ public static function fromPretrained(
107107

108108
return new $cls($tokenizerJson, $tokenizerConfig);
109109
}
110-
}
110+
}

0 commit comments

Comments
 (0)