Tiny Aya SMS extraction: models
Collection
Lexsi hackathon T1-P5: LoRA + GGUF models β’ 10 items β’ Updated
How to use Meowniece/tiny-aya-sms-extract-fire-lora with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-fire")
model = PeftModel.from_pretrained(base_model, "Meowniece/tiny-aya-sms-extract-fire-lora")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 β | 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.