Update README.md

README.md

@@ -1,6 +1,9 @@
 ---
 library_name: transformers
-tags: []
+language:
+- tr
+metrics:
+- bleu
 ---
 
 # Model Card for Model ID
@@ -10,190 +13,109 @@ tags: []
 
 
 ## Model Details
+<p>
+This model(10-epoch) has been trained with the dataset
+        <a href="https://github.com/okanvk/Turkish-Reading-Comprehension-Question-Answering-Dataset">Turkish-Reading-Comprehension-Question-Answering-Dataset </a>for Turkish question-answering
+</p>
 
-### Model Description
+<h1>Usage</h1>
+  <h2>install package</h2>
+  <ul> 
+          <li>!pip install transformers</li>
+          <li>!pip install evaluate</li>
+          <li>!pip install rouge</li>
+    
+  </ul>
+  <h2>Codes</h2>
 
-<!-- Provide a longer summary of what this model is. -->
+  <h3>Imports</h3>
+  
+```python
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+import torch
+import nltk
+import string
+import evaluate  # Bleu
+import pandas as pd
+import numpy as np
+from transformers import T5Tokenizer, MT5Model, MT5ForConditionalGeneration, MT5TokenizerFast
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+import warnings
 
-### Model Sources [optional]
+```
 
-<!-- Provide the basic links for the model. -->
+```python
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+TOKENIZER = MT5TokenizerFast.from_pretrained("msbayindir/mt5-small-sample")
+MODEL = MT5ForConditionalGeneration.from_pretrained("msbayindir/mt5-small-sample", return_dict=True)
+DEVICE = "cuda:0"
+MODEL = MODEL.to(device=DEVICE)
+Q_LEN = 256   # Question Length
+T_LEN = 32  
 
-## Uses
+```
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+```python
 
-### Direct Use
+def predict_answer(context, question, ref_answer=None):
+    inputs = TOKENIZER(question, context, max_length=Q_LEN, padding="max_length", truncation=True, add_special_tokens=True)
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+    input_ids = torch.tensor(inputs["input_ids"], dtype=torch.long).to(DEVICE).unsqueeze(0)
+    attention_mask = torch.tensor(inputs["attention_mask"], dtype=torch.long).to(DEVICE).unsqueeze(0)
 
-[More Information Needed]
+    outputs = MODEL.generate(input_ids=input_ids, attention_mask=attention_mask)
 
-### Downstream Use [optional]
+    predicted_answer = TOKENIZER.decode(outputs.flatten(), skip_special_tokens=True)
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+    if ref_answer:
+        # Load the Bleu metric
+        bleu = evaluate.load("google_bleu")
+        score = bleu.compute(predictions=[predicted_answer],
+                            references=[ref_answer])
 
-[More Information Needed]
+        print("Context: \n", context)
+        print("\n")
+        print("Question: \n", question)
+        return {
+            "Reference Answer: ": ref_answer,
+            "Predicted Answer: ": predicted_answer,
+            "BLEU Score: ": score
+        }
+    else:
+        return predicted_answer
 
-### Out-of-Scope Use
+```
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+###Samples
 
-[More Information Needed]
 
-## Bias, Risks, and Limitations
+```python
+context = """Katmandu Büyükşehir Şehri (KMC),
+ uluslararası ilişkileri teşvik etmek amacıyla Uluslararası İlişkiler Sekreterliği (IRC) kurmuştur. 
+ KMC'nin ilk uluslararası ilişkisi 1975 yılında Eugene, Oregon, Amerika Birleşik Devletleri ile kurulmuştur. 
+ Bu etkinlik, diğer 8 şehirle resmi ilişkiler kurarak daha da geliştirilmiştir:
+Motsumoto City of Japan, Rochester, Myanmar Yangon (eski adıyla Rangoon), 
+Çin Halk Cumhuriyeti'nden Xi'an, Belarus Minsk ve Kore Demokratik Cumhuriyeti'nden Pyongyang. KMC'nin sürekli çabası, 
+Katmandu için daha iyi kentsel yönetim ve gelişim programları elde etmek için SAARC ülkeleri, diğer Uluslararası ajanslar ve 
+dünyanın diğer birçok büyük şehirleri ile etkileşimini geliştirmektir."""
+answer = "Katmandu ilk uluslararası ilişkisini hangi yılda yarattı?"
+predict_answer(context,answer)
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+'1975'
 
-[More Information Needed]
+```
 
-### Recommendations
+```python
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+context = """Yapay zeka (YZ), modern dünyada hızla gelişen bir teknoloji alanıdır. YZ, sağlık, finans ve eğitim gibi birçok sektörde kullanılmaktadır. 
+Sağlık alanında, YZ algoritmaları hastalık teşhislerinde yardımcı olabilir. Finans sektöründe, YZ, piyasa analizleri yaparak yatırım kararlarını destekler. 
+Eğitimde ise, öğrenci performansını izler ve bireyselleştirilmiş öğrenme programları oluşturur. 
+Ancak, YZ'nin kullanımı etik ve gizlilik konularında endişeler doğurur.
+Veri güvenliği ve algoritmik önyargılar, dikkatle ele alınması gereken önemli meselelerdir."""
+answer = "Yapay zeka hangi sektörlerde kullanılmaktadır?"
+predict_answer(context,answer)
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
-## How to Get Started with the Model
+'sağlık, finans ve eğitim'
 
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+```