Added model hub links

apps/classifier.py

@@ -20,17 +20,30 @@ def load_model(input_text, model_name_or_path):
 def app():
  st.title("RoBERTa Marathi")
 
+ st.markdown(
+ "This demo uses [RoBERTa for Marathi](https://huggingface.co/flax-community/roberta-base-mr) model "
+ "trained on [mC4](https://huggingface.co/datasets/mc4)."
+ )
+
+ st.markdown(
+ "Can't figure out where to get a sample text? Visit this "
+ "[link](https://maharashtratimes.com/entertainment/articlelist/19359255.cms), copy any headline and see if "
+ "the model is predicting it as `entertainment` or not."
+ )
+
  classifier = st.sidebar.selectbox("Select a Model", index=0, options=["Indic NLP", "iNLTK"])
 
  sample_texts = [
- "दानिश सिद्दीकीच्या मृत्यूला आम्ही जबाबदार नाही",
  "अध्यक्ष शरद पवार आणि उपमुख्यमंत्री अजित पवार यांची भेट घेतली.",
  "मोठी बातमी! उद्या दुपारी १ वाजता जाहीर होणार दहावीचा निकाल",
+ "Custom",
  ]
  model_name_or_path = cfg["models"][classifier]
 
- input_text = st.sidebar.selectbox("Select a Text", options=sample_texts)
- text_to_classify = st.text_input("Text:", input_text)
+ text_to_classify = st.selectbox("Select a Text", options=sample_texts, index=len(sample_texts) - 1)
+
+ if text_to_classify == "Custom":
+ text_to_classify = st.text_input("Enter custom text:")
 
  predict_button = st.button("Predict")
 

apps/mlm.py

@@ -15,12 +15,22 @@ def load_model(input_text, model_name_or_path):
  nlp = pipeline("fill-mask", model=model, tokenizer=tokenizer)
  result = nlp(input_text)
  sentence, mask = result[0]["sequence"], result[0]["token_str"]
- return sentence, mask
+ return sentence, mask, result
 
 
 def app():
  st.title("RoBERTa Marathi")
 
+ st.markdown(
+ "This demo uses [RoBERTa for Marathi](https://huggingface.co/flax-community/roberta-base-mr) model "
+ "trained on [mC4](https://huggingface.co/datasets/mc4)."
+ )
+
+ st.markdown(
+ "Can't figure out where to get a sample text? Visit this "
+ "[link](https://maharashtratimes.com/entertainment/articlelist/19359255.cms), copy any headline and mask a word."
+ )
+
  masked_texts = [
  "मोठी बातमी! उद्या दुपारी <mask> वाजता जाहीर होणार दहावीचा निकाल",
  "अध्यक्ष <mask> पवार आणि उपमुख्यमंत्री अजित पवार यांची भेट घेतली.",
@@ -33,7 +43,9 @@ def app():
 
  if fill_button:
  with st.spinner("Filling the Mask..."):
- filled_sentence, mask = load_model(masked_text, cfg["models"]["RoBERTa"])
+ filled_sentence, mask, raw_json = load_model(masked_text, cfg["models"]["RoBERTa"])
 
  st.markdown(f"**Filled sentence: **{filled_sentence}")
  st.markdown(f"**Predicted masked token: **{mask}")
+
+ st.write(raw_json)