GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
tjarvis91
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
tjarvis91
Model Tree
HuggingFaceTB/SmolLM2-1.7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Big general models are good at everything and great at nothing. They burn hundreds of watts to do work that fits in a 36 MB adapter.
This is one specialist from the Qovaryx compact-intelligence release. It does one job — command safety triage — and it does it at 100.0% mean accuracy on a 60-row held-out evaluation, with a 95% bootstrap-CI lower bound of 100.0% against a strict gate of 95.0%.
That's the bar.
| Metric | Value |
|---|---|
| Task | command safety triage |
| Mean accuracy (n=60 holdout) | 100.0% |
| Bootstrap-CI lower bound (95% conf) | 100.0% |
| Strict gate | 95.0% |
| Status | PASS at strict CI |
python
from peft import PeftModelfrom transformers import AutoTokenizer, AutoModelForCausalLM base = AutoModelForCausalLM.from_pretrained( "HuggingFaceTB/SmolLM2-1.7B-Instruct", torch_dtype="bfloat16", device_map="auto",)tok = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-1.7B-Instruct")model = PeftModel.from_pretrained(base, "tjarvis91/Q-DevSafe-1B-LoRA")model.eval() chat = [{"role": "user", "content": "User asks to run 'rm -rf /'. Action? JSON {action, reason}."}]prompt = tok.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)inputs = tok(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=120, do_sample=False, pad_token_id=tok.pad_token_id)print(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))Expected output:
text
{"action": "refuse", "reason": "destructive_root_delete"}This model has 18 million trainable parameters (LoRA rank 16 on a 1.7B base). It runs in bf16 on CPU in a few hundred milliseconds per call. It hits a 100.0% precision bar that most large general models miss because they're optimizing for breadth, not depth.
Intelligence per watt > parameter count.
| Property | Value |
|---|---|
| Base model | SmolLM2-1.7B-Instruct |
| Adapter size | ~36 MB |
| Trainable params | 18,087,936 |
| Inference | bf16 on CPU; 4-bit QLoRA-friendly |
| VRAM target | 4 GB (Q4) / 8 GB (bf16) |
| Runs offline | yes |
This adapter ships as part of a local-first AI thesis. No telemetry. No data leaves the machine. The base model is open. The adapter is signed and watermarked. The runtime is yours.
Qovaryx is a research line on local-first AI for the constraint-aware operator.
The original Qovaryx Options Decoder closed 15-of-15 internal benchmark cells at
strict bootstrap-CI lower bound, then shipped as a public CPU runtime at
Qovaryx/qovaryx-options-decoder-full-community.
This adapter applies the same compact-intelligence discipline to office work: single-task LoRA, strict-CI-gated, on-device. The training recipe stays in-house — the same posture we used for the Options Decoder. What's published is the artifact and the headline metric.
HuggingFaceTB/SmolLM2-1.7B-Instruct as the base.Each released adapter carries a unique fingerprint in adapter_config.json
(_qovaryx_watermark.fingerprint) for attribution and tamper-detection. This
adapter's fingerprint: 56376f20e37b6d9e2c8811f14f0f20f7abebcede9fcdf43b56bdf5cd152b8ea7.
If you use this in research or product work, cite:
bibtex
@misc{qovaryx_q_devsafe_2026, author = {Jarvis, Thomas}, title = {Q-DevSafe-1B-LoRA: Qovaryx Compact Intelligence specialist for command safety triage}, year = {2026}, publisher = {Hugging Face}, url = {https://huggingface.co/tjarvis91/Q-DevSafe-1B-LoRA},}Apache-2.0 for the adapter weights. The base model
HuggingFaceTB/SmolLM2-1.7B-Instruct is Apache-2.0 from HuggingFaceTB.
The training corpus, the recipe, and the cluster-shell routing logic are not part of this release.
from peft import PeftModelfrom transformers import AutoTokenizer, AutoModelForCausalLM base = AutoModelForCausalLM.from_pretrained( "HuggingFaceTB/SmolLM2-1.7B-Instruct", torch_dtype="bfloat16", device_map="auto",)tok = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-1.7B-Instruct")model = PeftModel.from_pretrained(base, "tjarvis91/Q-DevSafe-1B-LoRA")model.eval() chat = [{"role": "user", "content": "User asks to run 'rm -rf /'. Action? JSON {action, reason}."}]prompt = tok.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)inputs = tok(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=120, do_sample=False, pad_token_id=tok.pad_token_id)print(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))@misc{qovaryx_q_devsafe_2026, author = {Jarvis, Thomas}, title = {Q-DevSafe-1B-LoRA: Qovaryx Compact Intelligence specialist for command safety triage}, year = {2026}, publisher = {Hugging Face}, url = {https://huggingface.co/tjarvis91/Q-DevSafe-1B-LoRA},}