---
license: apache-2.0
---

forked from https://huggingface.co/huggyllama/llama-13b/tree/main

This tokenizer supports [`Birchlabs/llama-13b-stepwise-adapter`](https://huggingface.co/Birchlabs/llama-13b-stepwise-adapter).

Adds four new tokens for stepwise reasoning:

```
<|step_start|>
<|step_end|>
<|answer_start|>
<|answer_end|>
```

See [`Birchlabs/llama-13b-stepwise-adapter`](https://huggingface.co/Birchlabs/llama-13b-stepwise-adapter) for details of how all the parts should be used together.