nbroad HF staff commited on
Commit
365b5f3
1 Parent(s): 67c3f28

wiki download option

Browse files
Files changed (1) hide show
  1. app.py +6 -2
app.py CHANGED
@@ -1,6 +1,6 @@
1
  import gradio as gr
2
 
3
- from utils import load_hf_dataset, get_model_and_tokenizer, batch_embed
4
 
5
 
6
  # TODO: add instructor models
@@ -48,7 +48,11 @@ def download(
48
  ):
49
  if progress is not None:
50
  progress(0.5, "Loading dataset...")
51
- ds = load_hf_dataset(ds_name, ds_config, ds_split)
 
 
 
 
52
 
53
  return f"Downloaded! It has {len(ds)} docs."
54
 
 
1
  import gradio as gr
2
 
3
+ from utils import load_hf_dataset, get_model_and_tokenizer, batch_embed, download_wikipedia
4
 
5
 
6
  # TODO: add instructor models
 
48
  ):
49
  if progress is not None:
50
  progress(0.5, "Loading dataset...")
51
+
52
+ if ds_name == "wikipedia":
53
+ ds = download_wikipedia(ds_name, ds_config)
54
+ else:
55
+ ds = load_hf_dataset(ds_name, ds_config, ds_split)
56
 
57
  return f"Downloaded! It has {len(ds)} docs."
58