Instructions to use madhavsankar/qcpg-mscoco-sbert-lr1e-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use madhavsankar/qcpg-mscoco-sbert-lr1e-4 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("madhavsankar/qcpg-mscoco-sbert-lr1e-4") model = AutoModelForSeq2SeqLM.from_pretrained("madhavsankar/qcpg-mscoco-sbert-lr1e-4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
QCPG++
Dataset: MSCOCO
Learning Rate: 1e-4
Text Diversity Metrics
Semantic Similarity: DocumentSemanticDiversity
Syntactic Diversity: DependencyDiversity
Lexical Diversity: Character-level edit distance
Phonological Diversity: RhythmicDiversity
Morphological Diversity: POSSequenceDiversity.
Results
Training Loss: 1.3403
Dev Loss: 1.811
Dev BLEU: 11.0279
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support