# Unsloth-Inferenz

Unsloth unterstützt nativ eine 2x schnellere Inferenz. Für unser reines Inferenz-Notebook klicken Sie [hier](https://colab.research.google.com/drive/1aqlNQi7MMJbynFDyOQteD2t0yVfjb9Zh?usp=sharing).

Alle QLoRA-, LoRA- und Nicht-LoRA-Inferenzpfade sind 2x schneller. Dies erfordert keine Codeänderung oder neue Abhängigkeiten.

<pre class="language-python"><code class="lang-python"><strong>from unsloth import FastLanguageModel
</strong>model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "lora_model", # IHR MODELL, DAS SIE FÜR DAS TRAINING VERWENDET HABEN
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
)
FastLanguageModel.for_inference(model) # Aktiviert native 2x schnellere Inferenz
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 64)
</code></pre>

#### NotImplementedError: Es wird eine UTF-8-Locale benötigt. ANSI erhalten

Manchmal, wenn Sie eine Zelle ausführen [tritt dieser Fehler](https://github.com/googlecolab/colabtools/issues/3409) auf. Um dies zu lösen, führen Sie in einer neuen Zelle Folgendes aus:

```python
import locale
locale.getpreferredencoding = lambda: "UTF-8"
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://unsloth.ai/docs/de/grundlagen/inference-and-deployment/unsloth-inference.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.