| 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. |