Tiny Aya Global, fine-tuned for Indian bank/UPI SMS β†’ JSON

LoRA adapter for CohereLabs/tiny-aya-fire trained with AlignTune on data curated with CuratorKIT and evaluated with AuditKIT. Input: one SMS in English, Hindi or Hinglish. Output: one JSON object with 11 fields (see the dataset card).

Split Exact match Field accuracy Hallucination ↓ Non-txn F1
test_id 92.7 98.5 0.3 99.4
test_ood 88.7 98.5 3.1 97.0
challenge 79.5 93.3 6.6 85.7

Training path: aligntune Β· prompt format: chat Β· 1600 curated examples Β· LoRA r=16, Ξ±=32, lr=0.0002, 3 epoch(s).

Licence: the base model is CC-BY-NC (non-commercial). Commercial deployment needs a licence from Cohere. Data: fully synthetic; bank names are fictional; no real customer data.

Downloads last month
22
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for Meowniece/tiny-aya-sms-extract-fire-lora

Adapter
(44)
this model

Collection including Meowniece/tiny-aya-sms-extract-fire-lora