Update README.md

README.md

@@ -50,7 +50,52 @@ widget:
   example_title: summarize
 license: cc-by-sa-4.0
 ---
+# Model Card for odia-t5-base
+![model image](https://adaptiverecs-web.s3.ap-south-1.amazonaws.com/my-test-data/Odia+T5.png)
 
+# Model Details
+
+## Model Description
+
+odia-t5-base is a multilingual Text-To-Text Transfer Transformer fine-tuned to perform downstream tasks in the Odia language.
+
+- **Developed by:** Mohammed Ashraf
+- **Model type:** Language model
+- **Language(s) (NLP):** Odia, English, Hindi
+- **License:** CC BY-NC-SA 4.0
+- **Related Models:** [All MT5 Checkpoints](https://huggingface.co/models?search=mt5)
+
+# Uses
+
+## Direct Use and Downstream Use
+
+ - Translate English to Odia.
+ - Translate Hind to Odia.
+ - Odia Sentence Summarization.
+ - Question Answering in Odia.
+ - Context-Based Question answering in Odia.
+
+
+### How to use
+
+```
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+tokenizer = AutoTokenizer.from_pretrained("mrSoul7766/odia-t5-base")
+model = AutoModelForSeq2SeqLM.from_pretrained("mrSoul7766/odia-t5-base")
+
+# Set maximum generation length
+max_length = 512
+
+# Generate response with question as input
+input_ids = tokenizer.encode("answer: ଓଡ଼ିଶାରେ ଅଟ୍ଟାଳିକା ପାଇଁ ସର୍ବାଧିକ ଆସନ ସୀମା କ’ଣ?</s>", return_tensors="pt")
+output_ids = model.generate(input_ids, max_length=max_length)
+
+# Decode response
+response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+print(response)
+
+```
 
 ### Licensing Information