Update README.md

README.md

@@ -50,4 +50,8 @@ pipe = pipeline("text-classification", model=model, tokenizer=tokenizer, device=
 for i, out in enumerate(tqdm(pipe(KeyDataset(dataset, "text"), padding=True, truncation=True))):
   print(dataset["text"][i])
   print(out)
+
+### IMPORTANT REMARK: It is highly recommended to use a prior classification step before applying ClimateBERT-NetZero.
+### Establish a climate context with "climatebert/distilroberta-base-climate-detector" for paragraphs
+### or "ESGBERT/EnvironmentalBERT-environmental" for sentences and then label the data with ClimateBERT-NetZero.
 ```