docker is taking FOREVER

.gitattributes

@@ -0,0 +1,12 @@
+bin/model4/config.json filter=lfs diff=lfs merge=lfs -text
+bin/model4/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+bin/model4/special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
+bin/model4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+bin/model4/tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
+bin/model4/vocab.txt filter=lfs diff=lfs merge=lfs -text
+language_models_project/bin/model4/config.json filter=lfs diff=lfs merge=lfs -text
+language_models_project/bin/model4/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+language_models_project/bin/model4/special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
+language_models_project/bin/model4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+language_models_project/bin/model4/tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
+language_models_project/bin/model4/vocab.txt filter=lfs diff=lfs merge=lfs -text

language_models_project/app.py

@@ -1,15 +1,15 @@
 import streamlit as st  # Web App
 from main import classify
 
-demo_phrases = """ Here are some examples:
-this is a phrase
-is it neutral
-nothing else to say
-man I'm so damn angry
-sarcasm lol
-I love this product
-"""
-
+#demo_phrases = """ Here are some examples:
+#this is a phrase
+#is it neutral
+#nothing else to say
+#man I'm so damn angry
+#sarcasm lol
+#I love this product
+#"""
+demo_phrases = pd.read_csv('./train.csv')['comment_text'].head(20).astype(str).str.cat(sep='\n')
 # title
 st.title("Sentiment Analysis")
 
@@ -51,7 +51,7 @@ def infer(text: str) -> List[float]:
     predictions[np.where(probs >= 0.5)] = 1
     predictions = pd.Series(predictions == 1)
     predictions.index = ["toxic", "severe_toxic", "obscene", "threat", "insult", "identity_hate"]
-    return predictions
+    return {"label": str(predictions), "score": str(probs)}
 
 
 def wrapper(*args, **kwargs):
@@ -65,7 +65,7 @@ def wrapper(*args, **kwargs):
 if st.button("Classify"):
     st.write("Please allow a few minutes for the model to run/download")
     for i in range(len(data)):
-        j = classify(model_name.strip(), data[i])[0]
+        j = wrapper(model_name.strip(), data[i])[0]
         sentiment = j["label"]
         confidence = j["score"]
         st.write(

language_models_project/bin/model4/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001fd1bd1edb918e108869e486195d8f63d28b3b649d8337f25702e26970fab4
+size 992

language_models_project/bin/model4/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8b18f3b7a745068b73b94504595e830c33b040c3e3af1dbc2f1fbbc5c1906f
+size 433329525

language_models_project/bin/model4/special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3
+size 125

language_models_project/bin/model4/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343989712a36cd8b253efeaf8baf6a08b9d2583f78e395e83832e8ee9f8d8ee1
+size 668923

language_models_project/bin/model4/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b08fb5ad902e90782fd47df204b6c21811944c52d65914237ab00f7d945c2b
+size 315

language_models_project/bin/model4/vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeaa9875b23b04b4c54ef759d03db9d1ba1554838f8fb26c5d96fa551df93d02
+size 213450