Update README.md

README.md

@@ -12,7 +12,9 @@ This repository provides large language models trained by [SB Intuitions](https:
 
 ## How to use
 
-```
+Please set **use_fast=False** to use our tokenizer properly.
+
+```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, set_seed
  
@@ -40,7 +42,7 @@ for t in text:
 
 ## Configuration
 
-| Parameters | Vocab size | Trainning tokens |  Architecture | Position type | Layers | Hidden dim | Attention heads |
+| Parameters | Vocab size | Training tokens |  Architecture | Position type | Layers | Hidden dim | Attention heads |
 | :-----: | :-----------: | :-------------:  | :------------ | :-----------: | :----: | :--------: | :-------------: |
 | [7B](https://huggingface.co/sbintuitions/sarashina2-7b)      | 102400        | 2.1T             | Llama2        | RoPE          | 32     | 4096       | 32 |
 | [13B](https://huggingface.co/sbintuitions/sarashina2-13b)     | 102400        | 2.1T             | Llama2        | RoPE          | 40     | 5120       | 40 |