An offline assistant for Indian digital fraud

Seerie is an offline, on device AI assistant that helps people in India recognize and respond to digital fraud. UPI scams, phishing, digital arrest calls, and more, with no internet required for answers. Your questions and data never leave your device.

This page covers the open GGUF releases for llama.cpp, Ollama, and LM Studio. Full precision safetensors live at seerror-technologies/seerie. The consumer app that ships Seerie Brain is live on Google Play.

What Seerie knows

India first safety knowledge

Trained to answer the questions people actually ask after a scare, in the language they use.

UPI fraud patternsCollect request bait, refund traps, and what to do next

Phishing SMS and callsFake KYC, courier duty, utility cut off scripts

Digital arrest tacticsVideo call pressure, fake police and CBI scripts

Aadhaar safetyLock, unlock, masking, and misuse prevention

Indian cyber law basicsIT Act and DPDP Act, stated plainly

Where to reportcybercrime.gov.in and the 1930 helpline

Hindi, English, HinglishResponds the way people actually type

On device by designNo cloud inference step for the open weights

Example

A real Hinglish exchange

Sample · UPI loss

User

Mera UPI se paise kat gaye, kya karoon?

Seerie

Sabse pehle turant apne bank ko call karke card/UPI block karayein.
Phir cybercrime.gov.in par complaint file karein ya 1930 helpline par call karein,
jitni jaldi report karenge, paise wapas milne ke chances utne zyada honge.
Apna transaction ID aur bank statement screenshot ready rakhein complaint ke liye.

Base model

Fine tuned from Qwen3 1.7B

Seerie is fine tuned from Qwen3 1.7B (Apache 2.0) using QLoRA, trained with the Unsloth framework for faster and more memory efficient training. The companion instruction set is documented on the Seerie dataset page.

Quantizations

Available GGUF files

File	Size	Notes
`seerie-q4_k_m.gguf` Recommended	~1.1 GB	Default. Smallest and fastest. Ideal for phones and the Seerie app Brain download.
`seerie-q6_k.gguf` Coming soon	TBA	Higher quality. Needs more RAM.

Get the files from huggingface.co/seerror-technologies/seerie-GGUF.

How to run

LM Studio, Ollama, llama.cpp

LM Studio

Download the .gguf file from Hugging Face
Load it in LM Studio
Leave the system prompt empty
Set temperature to 0.3 to 0.4 for consistent answers

Ollama

ollama create seerie -f Modelfile
ollama run seerie

Create a Modelfile pointing to the downloaded .gguf file. See Ollama's GGUF import docs.

llama.cpp

./llama-cli -m seerie-q4_k_m.gguf -p "Mera UPI se paise kat gaye, kya karoon?"

Limitations

What Seerie is not

Not a substitute for filing an official police or cybercrime complaint. Always direct urgent cases to 1930 or cybercrime.gov.in.
May not have information on very recent scam patterns that emerged after training.
Small model (1.7B). Best for quick guidance rather than deep legal analysis.
Not a government product and not legal or financial advice.

Links