Pavaniai89

Fine-tuned model by shiva64 using KaveriAI Fine-Tune Studio.

Model Details

Field	Value
Model Name	Pavaniai89
Developer	shiva64
Base Model	sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Training Dataset	demo/identity-1k
License	Apache 2.0
Architecture	AnimFilter3DNet + PyTorch SDPA
Training Date	2026-10-07
Epochs	3
Final Loss	0.178045
Optimizer	AdamW (lr=0.0002)
Framework	PyTorch 2.14.0+cpu

Training Details

This model was fine-tuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 on the demo/identity-1k dataset.

Hardware: Kaggle Dual-T4 GPU
Training Framework: PyTorch with SDPA (Scaled Dot-Product Attention) optimisation
Fine-tuning Method: Full parameter fine-tuning with AdamW

Dataset Card

The model was trained on demo/identity-1k.

Property	Value
Dataset	demo/identity-1k
Split	train
Preprocessing	Standard tokenization + PII scrubbing (India DPDP Act compliant)

Usage

import torch
from huggingface_hub import hf_hub_download

# Load model
model_path = hf_hub_download(repo_id="shiva64/Pavaniai89", filename="model.pt")
model = torch.load(model_path, map_location="cpu")
model.eval()

License

This model is released under the Apache 2.0 License.
The base model sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 retains its original license — please review it before commercial use.

Citation

@misc{pavaniai89_20261007,
  author = {shiva64},
  title = {Pavaniai89},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/shiva64/Pavaniai89}
}

---

Built with KaveriAI Fine-Tune Studio