kajyuuen commited on
Commit
8ddf71e
1 Parent(s): babd711

Use FastTokenizer

Browse files
Files changed (3) hide show
  1. README.md +1 -3
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +2 -1
README.md CHANGED
@@ -11,14 +11,12 @@ This repository provides Japanese language models trained by [SB Intuitions](htt
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
 
20
  model = AutoModelForCausalLM.from_pretrained("sbintuitions/sarashina1-65b", torch_dtype=torch.float16, device_map="auto")
21
- tokenizer = AutoTokenizer.from_pretrained("sbintuitions/sarashina1-65b", use_fast=False)
22
  generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
23
  set_seed(123)
24
 
 
11
 
12
  ## How to use
13
 
 
 
14
  ```python
15
  import torch
16
  from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, set_seed
17
 
18
  model = AutoModelForCausalLM.from_pretrained("sbintuitions/sarashina1-65b", torch_dtype=torch.float16, device_map="auto")
19
+ tokenizer = AutoTokenizer.from_pretrained("sbintuitions/sarashina1-65b")
20
  generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
21
  set_seed(123)
22
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -9,7 +9,8 @@
9
  "mask_token": "<mask>",
10
  "cls_token": "<cls>",
11
  "sep_token": "<sep>",
 
12
  "sp_model_kwargs": {},
13
  "special_tokens_map_file": null,
14
- "tokenizer_class": "T5Tokenizer"
15
  }
 
9
  "mask_token": "<mask>",
10
  "cls_token": "<cls>",
11
  "sep_token": "<sep>",
12
+ "padding_side": "left",
13
  "sp_model_kwargs": {},
14
  "special_tokens_map_file": null,
15
+ "tokenizer_class": "PreTrainedTokenizerFast"
16
  }