GitHub - firelex/jeff: Fine-tunes of Qwen3.5 and Gemma 4 for zero-shot classification
Pangram verdict · v3.3
We believe that this text is a mix of AI, AI-assisted, and human-written content.
AI likelihood · overall
MixedArticle text · 903 words · 6 segments analyzed
Fine-tunes of Qwen3.5 and Gemma 4 for zero-shot classification: small, fast decision models you slot into your code, with the same request format as Jev. You describe a situation and list the options in plain words; Jeff returns a calibrated probability for each option from a single forward pass. No generated text, no parsing: about 22 ms per decision on an RTX PRO 6000 and 28 ms on an Apple M4 Max (MLX). Zero-shot means the options can be anything: support queues, user intents, moderation labels, voice commands, game moves. Your categories don't need to appear in the training data; you describe them, and Jeff picks. What it is, and what it isn't. These are very small models. They make extremely fast, well-calibrated judgement calls between options, and they slot easily into your local code. On benchmarks they approach, and sometimes beat, Jev; but at this size their reasoning won't match Jev's, which runs on a much larger model. If zero-shot accuracy isn't good enough for your purposes, a short fine-tune on your own examples takes you much further: our voice-navigation fine-tune moved held-out accuracy from 31.7% to 95.8% in under half an hour on one GPU. Built entirely on local hardware.
Training on one RTX PRO 6000 workstation GPU (the 0.8B trains in about 2 hours, the 2B in about 3.5), all synthetic training data written by an open model (Qwen3.8-Flash-Next) on two DGX Sparks, testing on a MacBook. No cloud GPUs, and no closed-model output in the training data; a closed model was used only to spot-check the quality of a sample of the synthetic data. Independent project. Jeff uses the same request format as Jev, but it is not affiliated with or endorsed by TypeSafe, the makers of Jev. Our training code starts from the open-source AutoJev recipe. Models on Hugging Face: Jeff-Qwen3.5-0.8B · Jeff-Qwen3.5-2B · Jeff-Gemma4-E2B Quick start uv sync uv run hf download mstrasser/Jeff-Qwen3.5-0.8B --local-dir checkpoints/jeff-0.8b # NVIDIA GPU or CPU (PyTorch) JEFF_CHECKPOINT=checkpoints/jeff-0.8b PORT=8765 uv run jeff-serve # Apple silicon (MLX, much faster on a Mac; Qwen models only) uv sync --extra mac JEFF_BACKEND=mlx JEFF_CHECKPOINT=checkpoints/jeff-0.8b PORT=8765 uv run jeff-serve curl -s localhost:8765/v1/systemone -H 'content-type: application/json' -d '{ "model": "jeff-latest", "state": "Refund request: the customer says the parcel arrived crushed and wants their money back.", "questions": { "route": {"type": "choice", "instructions": "Which team should handle this?", "criteria": {"1": "Refunds and payments", "2": "Damaged or lost parcels", "3": "Account and login problems"}}, "angry": {"type": "noul", "instructions": "Is the customer angry?"} } }' Each answer has a probability per option, the chosen option and a confidence.
Three question types: choice (pick one of up to 255 options), noul (yes/no, returned as a probability) and score (a point on a scale you describe). Several independent questions in one request are answered together.
Benchmarks 4,599 questions from five public benchmarks, plus JevBench's public hard tier (105 items, scored separately): Benchmark Qwen3.5-0.8B untrained Jeff-Qwen3.5-0.8B Qwen3.5-2B untrained Jeff-Qwen3.5-2B Gemma 4 E2B untrained Jeff-Gemma4-E2B Jev (published) AutoJev-27B (published) Overall (5 benchmarks) 45.3 79.1 46.5 83.1 62.5 81.6 83.0 84.9 BBH 39.5 64.0 46.0 68.0 51.3 66.4 94.3 82.8 Financial PhraseBank 36.0 96.4 53.4 96.3 86.0 96.1 77.0 84.2 JudgeBench 56.6 62.6 57.4 64.6 46.9 60.6 78.6 78.9 RAGTruth 49.1 86.1 35.9 88.9 63.8 87.4 77.3 88.9 WinoGrande 49.2 68.6 52.2 79.0 51.0 77.4 90.7 83.3 JevBench hard (separate) 36.2 47.6 45.7 53.3 41.0 48.6 73.3 70.3 Bold: the winner of Jeff against Jev in each row. Bold italic: AutoJev-27B where it is the best of all models in the row (on RAGTruth, tied with Jeff-Qwen3.5-2B); it is shown for reference, since the head-to-head comparison is with Jev. The published Jev and AutoJev figures were measured on a different sample of the same benchmarks.
Jeff's overall score comes from classification and grounding, where it matches or beats the large models; on the reasoning-heavy benchmarks (BBH, JudgeBench, JevBench) it stays well below them, as you would expect at this size.
Games: a zero-shot test To test zero-shot performance on tasks unlike anything in the benchmarks, we had Jeff play three games. Games aren't the ideal zero-shot test, since a game's state isn't typical unstructured data; but they are a common, and fun, way to test a System 1 model. Each turn, the code describes the situation and the legal moves in words, and the model picks one. The options state what each move leads to (Frogger: "you would be hit by a car and lose a life"; Doom: "the nearest monster is a little to your left"), but never which move is right. Each result is 20 episodes, seed 1234; ▶ opens a video of the run's first episode. Jeff-Qwen3.5-0.8B playing, zero-shot (the bold row in the table below; click a clip for the full video): Model Doom, kills (monster's direction in words) Frogger, crossings (consequences) Pac-Man, pellets of 98 (consequences) Random moves −0.05 0 11.2 Hand-coded rule bot 6.55 ▶ 10.25 ▶ 94.1 ▶ Qwen3.5-0.8B, untrained 5.0 ▶ 1.0 ▶ 25.8 ▶ Jeff-Qwen3.5-0.8B 6.55 ▶ 10.3 ▶ 57.0 ▶ Qwen3.5-2B, untrained 0.55 ▶ 0.05 ▶ 72.1 ▶ Jeff-Qwen3.5-2B −0.9 ▶ 6.0 ▶ 41.2 ▶ Gemma 4 E2B, untrained −0.55 ▶ 0 ▶ 3.2 ▶ Jeff-Gemma4-E2B 0.55 ▶ 0.15 ▶ 53.2 ▶ Jev (published, Doom) 6.55, told the aiming rule; −0.60 without it — — Jeff-0.8B decides in 29–49 ms per move on an M4 Max; Jev's published Doom run took 212 ms per call over its API.