| # Trying to make AI conversation | |
| for this fine-tuning of this model. here we use the **[dataset](abhijitgayen/cogo_chat)** | |
| # How to use this Model | |
| ```python | |
| from transformers import AutoModelForSeq2SeqLM, AutoTokenizer | |
| model_id= "abhijitgayen/cogo-blenderbot" | |
| tokenizer = AutoTokenizer.from_pretrained(model_id) | |
| model = AutoModelForSeq2SeqLM.from_pretrained(model_id) | |
| UTTERANCE = "help me to book fcl" | |
| print("Human: ", UTTERANCE) | |
| inputs = tokenizer([UTTERANCE], return_tensors="pt") | |
| reply_ids = model.generate(**inputs) | |
| print("Bot: ", tokenizer.batch_decode(reply_ids, skip_special_tokens=True)[0]) | |
| ``` | |
| # Out Put | |
| Response is good but it is take time to give response..As chatbot a real time application. if it takes more than 20 sec , it is meaningless. |