GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
irioder
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
irioder
Model Tree
Qwen/Qwen3.5-0.8B
Input Modalities
Output Modalities
Supported Functionality
| Model | Relationship to this exam | O.W.L. | N.E.W.T. | Overall |
|---|---|---|---|---|
| Qwen 3.5 0.8B base | Clean | 0/30 | 0/45 | 0.00 |
| GPT-5.6 Sol | Clean | 30/30 | 35/45 | 88.89 |
| Fable 5 | Clean | 30/30 | 42/45 | 96.67 |
| littleHermione 0.8B† | Trained on all 75 answers | 30/30 | 45/45 | 100.00 |
The dagger is part of the model name on the leaderboard. This score measures memorisation of the public development set, not general Harry Potter knowledge or reasoning.
The base did not become a general Harry Potter expert. A small learned delta completely changed its behaviour inside one very small and very over-rehearsed territory.
All 75 public O.W.L. & N.E.W.T. Bench v0.4 questions and primary answers were used for training. Each question generated 12 rows: 10 exact prompt repetitions and two prefix variations. Across 12 epochs, each fact appeared 144 times, including 120 presentations of the exact evaluation prompt.
The generated dataset and its builder live in the GitHub repository. The questions are newly written short factual prompts; no passages from the novels are included.
The detached GGUF was applied to one exact Q8 base through llama.cpp at five scales:
| LoRA scale | Correct | Score |
|---|---|---|
| 0.00 | 1/75 | 1.11 |
| 0.25 | 19/75 | 25.56 |
| 0.50 | 72/75 | 95.56 |
| 0.75 | 75/75 | 100.00 |
| 1.00 | 75/75 | 100.00 |
Half scale did not recover half the answers. It recovered 72. All five points
used the same base export, adapter, runtime and generation settings with zero
transport or parse errors. Full machine-readable results are in
scale-curve.json.
adapter_model.safetensors and adapter_config.json: PEFT LoRA for
Qwen/Qwen3.5-0.8B.littleHermione-lora-f16-v0.4.0.gguf: detached llama.cpp-compatible F16
LoRA. The base GGUF is not duplicated here.training-manifest.json: deterministic dataset construction and hashes.scale-curve.json: the complete paired five-scale benchmark.The GGUF adapter can be attached to a compatible Qwen 3.5 0.8B base with a recent llama.cpp build:
bash
llama-server \-m qwen35-08b-clean-q8_0.gguf \--lora littleHermione-lora-f16-v0.4.0.gguf
For the PEFT version, use the pinned training and export scripts in the GitHub repository; Qwen 3.5 requires a current Transformers stack and is represented as a unified vision-language model even for this text-only experiment.
| Component | Reference version |
|---|---|
| Unsloth | 2026.7.2 |
| Transformers | 5.5.0 |
| TRL | 0.23.1 |
| PEFT | 0.18.1 |
| PyTorch | 2.10.0+cu128 |
| LoRA rank / alpha / dropout | 32 / 32 / 0 |
| Optimizer | 8-bit AdamW |
| Learning rate | 2e-4, linear decay |
| Effective batch | 16 |
The honest follow-up is a sealed exam which never enters the training directory. That will test the more interesting claim: whether a few trained parameters can teach a small local model the narrow part of the world we care about, instead of only teaching it our exact answers.
The adapter is derived from
Qwen/Qwen3.5-0.8B, licensed under
Apache 2.0.
This is an independent, fan-made research artifact. It is not affiliated with, endorsed by or sponsored by J. K. Rowling, Warner Bros. or Wizarding World. No rights are claimed over their names, marks or fictional universe.
| Maximum sequence length | 512 |