sho-takase commited on
Commit
67facba
1 Parent(s): a5e3187

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -11,7 +11,9 @@ This repository provides Japanese language models trained by [SB Intuitions](htt
11
 
12
  ## How to use
13
 
14
- ```
 
 
15
  import torch
16
  from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, set_seed
17
 
@@ -39,7 +41,7 @@ for t in text:
39
 
40
  ## Configuration
41
 
42
- | Parameters | Vocab size | Trainning tokens | Architecture | Position type | Layers | Hidden dim | Attention heads |
43
  | :-----: | :-----------: | :-------------: | :----------- | :-----------: | :----: | :--------: | :-------------: |
44
  | [7B](https://huggingface.co/sbintuitions/sarashina1-7b) | 51200 | 1.0T | GPTNeoX | RoPE | 32 | 4096 | 32 |
45
  | [13B](https://huggingface.co/sbintuitions/sarashina1-13b) | 51200 | 1.0T | GPTNeoX | RoPE | 40 | 5120 | 40 |
 
11
 
12
  ## How to use
13
 
14
+ Please set **use_fast=False** to use our tokenizer properly.
15
+
16
+ ```python
17
  import torch
18
  from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, set_seed
19
 
 
41
 
42
  ## Configuration
43
 
44
+ | Parameters | Vocab size | Training tokens | Architecture | Position type | Layers | Hidden dim | Attention heads |
45
  | :-----: | :-----------: | :-------------: | :----------- | :-----------: | :----: | :--------: | :-------------: |
46
  | [7B](https://huggingface.co/sbintuitions/sarashina1-7b) | 51200 | 1.0T | GPTNeoX | RoPE | 32 | 4096 | 32 |
47
  | [13B](https://huggingface.co/sbintuitions/sarashina1-13b) | 51200 | 1.0T | GPTNeoX | RoPE | 40 | 5120 | 40 |