Update README.md

README.md

@@ -1,37 +1,48 @@
 # Turkish Question Answering model based on mt0-large
-In this model, I fine-tune *mT0-large* model with the following Turkish QA datasets
+In this model, I fine-tuned *mT0-large* model with the following Turkish QA datasets where the training set size is around 11K QAs.
+
 * https://huggingface.co/bigscience/mt0-large
 * https://github.com/okanvk/Turkish-Reading-Comprehension-Question-Answering-Dataset
 
-The model is tuned within parameter-efficient fine-tuning, which is PEFT LORA. So we need to install peft modules. Please check
+The model is tuned within one of parameter-efficient fine-tuning techniques, which is PEFT LORA. So we need to install peft modules. Please check
 * https://github.com/huggingface/peft
 
 
-The training set size is around 11K QAs.
+# FOR INFERENCE
+
+We first install the requirements : 
+```
+!pip install peft transformers  # in jupyter notebook
+
+```
 
+## SINGLE INFERENCE
 
-Example usage for single inference is as follows:
 ```
 from peft import PeftModel, PeftConfig
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer 
 peft_model_path="savasy/mt0-large-Turkish-qa"
 
 config = PeftConfig.from_pretrained(peft_model_path)
 model = AutoModelForSeq2SeqLM.from_pretrained(
     config.base_model_name_or_path)
-# Load the Lora model
-inference_model = PeftModel.from_pretrained(model, peft_model_path)
 
-inference_model.eval()
+#tokenizer
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
 
+# Wrap the model with the LORA
+inference_model = PeftModel.from_pretrained(model, peft_model_path)
+inference_model.eval()
 
-import numpy as np
 inference_model.to("cuda")
-test_input = '''Mustafa adını babası Ali Rıza Efendi kendi dedesinin adı olduğundan dolayı vermiştir. Çünkü Ali Rıza Efendi'nin babasının adı olan
+test_input = '''
+  Mustafa adını babası Ali Rıza Efendi kendi dedesinin adı olduğundan dolayı vermiştir. Çünkü Ali Rıza Efendi'nin babasının adı olan
  Ahmed adı ağabeylerinden birisine verilmişti. Mustafa'ya neden Kemal isminin verildiğine yönelik ise çeşitli iddialar vardır. 
  Afet İnan, bu ismi ona matematik öğretmeni Üsküplü Mustafa Efendi'nin Kemal adının anlamında olduğu gibi onun "mükemmel ve olgun" 
  olduğunu göstermek için verdiğini söylemiştir. (source: wikipedia) .  
-Mustafa'nın dedesinin ismi nedir ?
+ Mustafa'nın dedesinin ismi nedir ?
  '''
+import torch
 with torch.no_grad():
   inputs = tokenizer(test_input, return_tensors="pt", padding=True).to("cuda")
   generated_ids = inference_model.generate(**inputs)
@@ -40,26 +51,32 @@ outputs
 -> [Ahmed]
 ```
 
+## BATCH INFERENCE
 
 The usage for batch mode is as follows:
 
 ```
 from peft import PeftModel, PeftConfig
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer 
 peft_model_path="savasy/mt0-large-Turkish-qa"
 
 config = PeftConfig.from_pretrained(peft_model_path)
 model = AutoModelForSeq2SeqLM.from_pretrained(
     config.base_model_name_or_path)
-# Load the Lora model
-inference_model = PeftModel.from_pretrained(model, peft_model_path)
 
+#tokenizer
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+# Wrap the model with the LORA
+inference_model = PeftModel.from_pretrained(model, peft_model_path)
 inference_model.eval()
+
 inference_model.to("cuda")
-test_inputs = ["","",""] #  a list of texts. A text must have Content followed by a Question
 
-preds=[]
-data_loader= DataLoader(test_inputs,batch_size=8)
+test_inputs = ["","","",""] #  a list of texts. A text must have Content followed by a Question
 
+preds=[] # for predictions
+data_loader= DataLoader(test_inputs,batch_size=8)
 from tqdm import tqdm
 
 with torch.no_grad():
@@ -69,5 +86,5 @@ with torch.no_grad():
     outputs = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
     preds+=outputs
 ```
-At the end, you can compare *preds* with your expected ground-truth results
+In the end, you can compare *preds*  (predictions) with your expected ground-truth results. You can use many metrics for this such as BLEU, ROUGE, Exact Match, Partial Match