YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
T5 Chatbot
A fine-tuned T5 model for conversational FAQ-style responses. Given a user question, the model generates a natural-language answer, making it suitable for lightweight chatbot and Q&A applications.
Model description
This model is a fine-tuned version of [t5-small / t5-base] (Google's T5 text-to-text transformer), adapted for conversational question-answering. It takes a user query as input and generates a relevant text response, framed as a text-to-text generation task.
Intended uses & limitations
Intended uses:
- FAQ-style chatbots for websites, apps, or customer support
- Educational/demo projects exploring conversational AI with T5
- Quick prototyping of Q&A systems
Limitations:
- Trained on a limited dataset, so responses may be generic or repetitive outside the training domain
- Does not maintain multi-turn conversational context (treats each query independently)
- English only
- Not suitable for safety-critical or factual/medical/legal advice use cases
- May occasionally produce inaccurate or nonsensical answers (hallucination risk common to generative models)
Training data
The model was fine-tuned on a [custom FAQ dataset / dataset name, e.g. "a collection of customer support Q&A pairs"]. [Add: dataset size, source, and any preprocessing steps if known.]
How to use
from transformers import pipeline
pipe = pipeline("text2text-generation", model="UMAR798/t5-chatbot")
response = pipe("What are your business hours?")
print(response)
Training procedure
- Base model: [t5-small / t5-base]
- Epochs: [e.g. 3]
- Batch size: [e.g. 8]
- Learning rate: [e.g. 5e-5]
Author
Developed by Muhammad Umar Farooq — LinkedIn
- Downloads last month
- 229