abdiharyadi commited on
Commit
16a3f37
·
verified ·
1 Parent(s): 3456a6b

docs: Add space in README

Browse files
Files changed (1) hide show
  1. README.md +2 -5
README.md CHANGED
@@ -9,8 +9,6 @@ model-index:
9
  results: []
10
  ---
11
 
12
-
13
-
14
  # KancilGPT
15
 
16
  (Spoiler: KancilGPT is not ready yet for production. The reader will see why.)
@@ -59,9 +57,8 @@ the first _k_ sentences from the current story content will be removed until the
59
 
60
  ## How to Use
61
  After learns how to generate an Indonesian fable story, KancilGPT can generate a random fable story with the specified procedures.
62
- All steps using the generate arguments `do_sample=True`, `max_new_tokens=512`, and `pad_token_id=<eos_token_id>`.
63
- Huggingface pipeline can not be used yet since KancilGPT uses `IndoNLGTokenizer` class from [`indobenchmark-toolkit`](https://github.com/indobenchmark/indobenchmark-toolkit).
64
- The specified procedures were simplified as one procedure in a [GitHub repository](https://github.com/AbdiHaryadi/kancilgpt).
65
 
66
  ### Step 1: Begin the story
67
  Use this prompt to generate the beginning of a story, including the generation of a title (`judul`):
 
9
  results: []
10
  ---
11
 
 
 
12
  # KancilGPT
13
 
14
  (Spoiler: KancilGPT is not ready yet for production. The reader will see why.)
 
57
 
58
  ## How to Use
59
  After learns how to generate an Indonesian fable story, KancilGPT can generate a random fable story with the specified procedures.
60
+ Its competence shone with the help of [Huggingface Spaces](https://huggingface.co/spaces/abdiharyadi/kancilgpt).
61
+ Huggingface pipeline could not help yet because KancilGPT uses `IndoNLGTokenizer` class from [`indobenchmark-toolkit`](https://github.com/indobenchmark/indobenchmark-toolkit).
 
62
 
63
  ### Step 1: Begin the story
64
  Use this prompt to generate the beginning of a story, including the generation of a title (`judul`):