Files
2026-03-21 01:15:26 -07:00

48 lines
2.8 KiB
HTML
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<div v-if="activeTab === 'tokenizer'" class="tab-content">
<div class="transform-layout">
<div class="input-section">
<div class="section-header">
<h3><i class="fas fa-layer-group"></i> Tokenizer Visualization <small>{{ tokenizerEngine }}</small></h3>
<p>Paste text to see how different tokenizers segment it.</p>
</div>
<div class="options-grid u-mb-8">
<label>
Engine
<select v-model="tokenizerEngine" @change="runTokenizer">
<option value="byte">UTF-8 bytes</option>
<option value="word">Naive words</option>
<option value="cl100k">OpenAI: cl100k_base (GPT3.5/4)</option>
<option value="o200k">OpenAI: o200k_base (GPT4o)</option>
<option value="p50k">OpenAI: p50k_edit (Code editing models)</option>
<option value="r50k">OpenAI: r50k_base</option>
</select>
</label>
</div>
<textarea
id="tokenizer-input"
v-model="tokenizerInput"
placeholder="Paste text to visualize tokens"
@input="runTokenizer"
></textarea>
</div>
<div class="output-section">
<div class="output-heading">
<h4>
<i class="fas fa-chart-bar"></i> Tokens
<small>{{ tokenizerTokens.length }} total · {{ tokenizerWordCount }} words · {{ tokenizerCharCount }} chars</small>
</h4>
</div>
<div class="token-tiles tokenizer-tiles" v-if="tokenizerTokens.length">
<div v-for="(tok, i) in tokenizerTokens" :key="i" class="token-chip token-chip--tokenizer">
<span class="token-chip__idx">{{ i }}</span>
<span>{{ tok.text }}</span>
<span v-if="tok.id !== undefined" class="token-chip__id">#{{ tok.id }}</span>
</div>
</div>
<div class="output-instructions" v-else>
<small>Tokens will appear here.</small>
</div>
</div>
</div>
</div>