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
Personal Details Lookup (flan-t5-small fine-tuned)
A small demo model fine-tuned from google/flan-t5-small. Given a name, it returns:
Name: Akshatha R
College: Dayananda Sagar University
Course: MSc Data Science
Any other name returns Sorry, no details found for <name>.
Usage
from transformers import AutoTokenizer, T5ForConditionalGeneration
repo = "YOUR_HF_USERNAME/akshatha-details-flan-t5-small"
tok = AutoTokenizer.from_pretrained(repo)
model = T5ForConditionalGeneration.from_pretrained(repo)
inputs = tok("Give details of Akshatha R", return_tensors="pt")
out = model.generate(**inputs, max_new_tokens=64)
print(tok.decode(out[0], skip_special_tokens=True))
Training
- Base model:
google/flan-t5-small - Data: ~90 synthetic prompt/answer pairs (question templates x name variants, plus other names as "not found" examples)
- 15 epochs, AdamW, lr 5e-4, batch size 8
This is a demo for learning fine-tuning; it only knows the one person above.
Model tree for Akshatha-0825/flan-t5
Base model
google/flan-t5-small