Update README.md

README.md

@@ -8,6 +8,7 @@ if not os.path.exists("expert_classify.ftz"):
     os.system("wget http://dl.turkunlp.org/register-labeling-model/fasttext_model.bin")
     os.system("wget https://huggingface.co/ontocord/riverbed/resolve/main/rj_model.bin")
     os.system("wget https://huggingface.co/ontocord/riverbed/resolve/main/expert_classify.ftz")
+    os.system("wget https://huggingface.co/kenhktsui/llm-data-textbook-quality-fasttext-classifer-v1/resolve/main/model_textbook_quality.bin"
 
 ### red pajama filter. pred_label "__label__wiki" is data we do not wish to keep.
 red_pajama_model = fasttext.load_model("rj_model.bin")
@@ -23,6 +24,11 @@ domain_model = fasttext.load_model("fasttext_model.bin")
 ### Pile domain such as github, arxiv, etc.
 pile_model = fasttext.load_model("expert_classify.ftz")
 (pred_label, pred_prob) = pile_model.predict(text)
+
+### Textbook quality - e.g., textbooks are all you need
+textbook_model = fasttext.load_model("model_textbook_quality.bin")
+(pred_label, pred_prob) = pile_model.predict(text)
+
 ```
      
 See the files here: https://huggingface.co/ontocord/riverbed/tree/main