GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
finndot
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
finndot
Model Tree
Qwen/Qwen3-1.7B
Input Modalities
Output Modalities
Supported Functionality
Use FinnAI SLM v4 if you are building:
adapter/ included)Related: finndot/finnai-slm-v3, finndot/finnai-slm-v2.
| Mode | Description |
|---|---|
| SMS → JSON | {amount, merchant, type, account, balance, category} — empty {} for OTP/promo/KYC |
| Ask | Short answers grounded in a synthetic/user ledger |
| Learn | Tutor-style explanations (SIP, EMI, tax, budgeting) |
| Analytics | Spending-pattern tips without inventing numbers |
Languages: English, Hindi, Hinglish, Tamil, Telugu, Marathi, Bengali (+ more Indic mix in train data).
| Metric | FinnAI v4 | Qwen3-1.7B base | Qwen2.5-1.5B |
|---|---|---|---|
| SMS R-EM % (n=2028) | 94.87 | 29.39 | 49.9 |
| Amount EM % | 99.7 | 78.75 | 81.95 |
| JSON valid % | 100.0 | 100.0 | 99.65 |
| Chat groundedness % (n=78) | 80.77 | 47.44 | 65.38 |
Protocol: docs/llm-eval-protocol.md. Val SMS R-EM during train: 98.24%.
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "finndot/finnai-slm-v4"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype="bfloat16", device_map="auto") messages = [ { "role": "system", "content": ( "Extract transaction details from this SMS as JSON: " "{amount, merchant, type, account, balance, category}. " "type is one of: INCOME, EXPENSE, CREDIT, TRANSFER, INVESTMENT. " "If this is not a transaction (OTP, promo, KYC), return {}." ), }, { "role": "user", "content": "HDFC Bank: Rs.499.00 debited from A/c XX1234 to SWIGGY via UPI. Avl Bal Rs.15000.50", },]text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)inputs = tokenizer(text, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=256, do_sample=False)print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))Load LoRA-only: adapter/ in this repo (PEFT), base Qwen/Qwen3-1.7B or prior FinnAI merged.
| Parameter | Value |
|---|---|
| Base for continual train | FinnAI v3 merged (from Qwen3-1.7B) |
| Method | QLoRA SFT (4-bit NF4, bf16 compute) |
| LoRA r / α / dropout | 16 / 32 / 0.05 |
| Targets | q, k, v, o, gate, up, down_proj |
| Epochs / LR | 3 / 1.5e-4 cosine, 3% warmup |
| Effective batch | 16 (2 × 8) |
| Max seq | 1536 |
| Train size | 40,000 (SMS 20k, chat 16.8k, general 3.2k) |
| Thinking |
Privacy: fully synthetic — no user SMS, no real accounts.
Production file: finndot/finnai-slm-v4-litertlm
.litertlm, INT4 dynamic_int4_block32, KV cache 1280, nothink36e5ec021730f0e060b78c2371d1e0011c34f28c407cdf9f993232b5cd87e7c0parser-core still preferred when a bank parser exists.bash
git clone https://github.com/AnomaProAI/Finndotcd Finndot/ml# dataset build + train configs: train/train_config_v4.yaml, data/out_v4_diverse/python train/sft_qlora.py --config train/train_config_v4.yamlpython -m eval.run_eval --backend hf \ --sms data/out_v4_diverse/test_sms.jsonl \ --chat data/out_v4_diverse/chat_eval.jsonl \ --model-id train/output/v4/merged \ --baseline-id Qwen/Qwen3-1.7B \ --tag v20261005-finnai-slm-v4bibtex
@misc{finnai-slm-v4-2026, title={FinnAI SLM v4: App-grounded on-device Indian bank SMS parsing and finance coaching}, author={FinnDot Team}, year={2026}, url={https://huggingface.co/finndot/finnai-slm-v4}, note={Apache 2.0. Continual QLoRA on Qwen3-1.7B / FinnAI v3.}}Apache 2.0 — same as Qwen3-1.7B.
| False-parse % | 0.25 | 100.0 | 12.88 |
Disabled (enable_thinking=false) |
| Hardware | 1× NVIDIA A10G (g5.2xlarge, us-east-2) |
| Seed | 42 |