Instructions to use manashxml/identify_CP_hin-eng with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use manashxml/identify_CP_hin-eng with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("manashxml/identify_CP_hin-eng") model = AutoModelForSeq2SeqLM.from_pretrained("manashxml/identify_CP_hin-eng", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| widget: | |
| - text: "आप उनकी गणना नहीं कर सकते." | |
| datasets: | |
| - manashxml/cp_and_none_10kdataset | |
| # mt5 for identifying CP in Hindi or English sentence | |
| This is a fine-tuned mt5 for identifying Complex Predicate in hindi or english sentence.Given a hindi sentence as input it displays the CP present as output.If no CP is present in the sentence it displays the token none. | |
| ## How to use | |
| You can use this model directly with a Text2Text generation pipeline: | |
| ```python | |
| >>>from transformers import pipeline | |
| >>>cp_identifier=pipeline("text2text-generation",model="manashxml/identify_CP_hin-eng") | |
| >>>cp_identifier("आप उनकी गणना नहीं कर सकते.") | |
| [{'generated_text': 'गणना नहीं कर सकते'}] | |
| ``` | |
| ### Training data | |
| The fine-tuning task was done on the following dataset created by our team : | |
| "https://datasets-server.huggingface.co/first-rows?dataset=manashxml%2Fcp_and_none_10kdataset&config=manashxml--cp_and_none_10kdataset&split=train" | |
| ### Team Members | |
| - Manash Mishra | |
| - Aditya Parashar | |
| - Riya Tomar | |
| - Isma Anwar | |
| - Under the guidance of: | |
| - Dr. Soma Paul(IIIT Hyderabad) | |
| - Dr. Sukhada(IIT BHU) |