---
language:
- en
- hi
- ta
tags:
- nariraksha
- safety
- women-safety
- indian-law
- qlora
- unsloth
- lora
base_model: Qwen/Qwen2.5-3B-Instruct
datasets:
- vikhram-labs/NariRaksha-100K
license: apache-2.0
pipeline_tag: text-generation
---

# NariRaksha-3B

QLoRA fine-tune of **Qwen/Qwen2.5-3B-Instruct** on
[NariRaksha-100K](https://huggingface.co/datasets/vikhram-labs/NariRaksha-100K),
a dataset of Indian women's safety scenarios. The model produces structured
safety assessments — risk type, severity, reasoning, recommended action, and
legal context (BNS / IT Act / PWDVA) — from a free-text scenario description.

> **Status: open research artifact.** This is an early-stage fine-tune
> released for research, replication, and community evaluation — not a
> validated or deployment-ready safety system. See
> [Evaluation](#evaluation) and [Limitations](#limitations) before using it
> for anything beyond experimentation.

## Quick Usage

```python
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "vikhram-labs/NariRaksha-3B", load_in_4bit=True
)
FastLanguageModel.for_inference(model)

prompt = "A woman in Chennai has been receiving repeated unwanted messages from a former colleague across multiple platforms over several weeks."
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Training Details

| | |
|---|---|
| Base model | `Qwen/Qwen2.5-3B-Instruct` |
| Method | QLoRA, 4-bit (NF4) |
| LoRA rank / alpha | r=16, α=32 |
| Framework | [Unsloth](https://github.com/unslothai/unsloth) |
| Training data | Full [NariRaksha-100K](https://huggingface.co/datasets/vikhram-labs/NariRaksha-100K) (~100K rows, single split, no held-out eval set) |
| Steps | 100 |

### Training Loss

| Step | Training Loss |
|---|---|
| 25 | 2.3122 |
| 50 | 0.2770 |
| 75 | 0.0698 |

This is the complete loss telemetry currently available — three logged
points over 100 total steps, training loss only. Read it as a directional
signal that the model is fitting the data quickly, not as evidence of task
generalization. See [Evaluation](#evaluation) for why.

## Evaluation

**No held-out validation/test split or downstream benchmark has been run
on this model.** NariRaksha-100K was released as a single split, and
training to date has used 100% of it, so the loss curve above reflects
in-sample fit only.

The drop from 2.31 → 0.07 over 75 steps is steep enough, on a 3B model with
this little data exposure, that it should be read as a likely signal of
**memorization rather than generalization** — particularly since a
meaningful share of the dataset's `reasoning` and `recommended_action`
fields are template-conditioned and repeat near-verbatim across many rows
(documented in the [dataset card](https://huggingface.co/datasets/vikhram-labs/NariRaksha-100K#dataset-composition-notes)).
A model can drive loss this low partly by memorizing a small set of stock
phrases rather than learning to reason over novel scenarios.

**What's needed before this can be called a validated model:** a held-out
eval split stratified by `risk_type`/`severity`, eval-loss tracking
alongside training loss, and qualitative testing on scenarios outside the
training distribution (including paraphrases and edge cases). None of that
exists yet for this checkpoint.

## Intended Use

Released as an **open research artifact** for:
- Studying QLoRA fine-tuning behavior on small, template-heavy safety
  datasets
- Replication and ablation by other researchers
- A baseline to compare against once eval infrastructure exists

**Not currently intended for:**
- Production deployment in any safety, triage, or emergency-response
  context
- Use as a source of legal citations or helpline numbers without
  independent verification — the underlying dataset's legal/contact
  information is only partially verified (see dataset card)
- Any setting where a hallucinated or memorized-but-wrong output could
  cause real-world harm to a person in distress

## Limitations

- **No eval split / no generalization evidence.** See Evaluation above.
- **Likely overfitting at current checkpoint.** Outputs on scenarios close
  to training examples may look strong; outputs on genuinely novel
  scenarios are untested and may default to memorized boilerplate.
- **Inherits dataset limitations.** Legal citations (BNS/IT Act/PWDVA
  sections) and helpline numbers in training data are a mix of verified and
  unverified entries — the model can confidently generate incorrect ones.
- **Small training run.** 100 steps is a minimal fine-tune; this checkpoint
  should be treated as a proof of concept, not a finished model.
- **Single-domain legal context.** Legal references are India-specific and
  not applicable elsewhere.

## Next Steps (Planned / Suggested)

- Carve out a stratified eval split from NariRaksha-100K and report eval
  loss alongside training loss
- Deduplicate or reweight template-heavy `reasoning` / `recommended_action`
  spans to reduce memorization pressure
- Independent verification pass on legal/helpline fields prior to any
  claim of factual reliability
- Longer training run with proper train/eval tracking before any
  deployment-readiness claims

## Citation

```bibtex
@incollection{nariraksha2026,
  title     = {NariRaksha: Gender-Responsive AI for Women's Safety},
  author    = {Vikhram S and Jeffin Gracewell J},
  booktitle = {India AI Impact Summit 2026 Casebook on AI and Gender Empowerment},
  year      = {2026},
  publisher = {Ministry of Electronics and Information Technology (MeitY), Government of India and UN Women}
}
```

## License

Apache 2.0.