Downloads · 30 days
0
thc1006/cyberpuppy-v6-pinyin-lora
cyberpuppy-v6-pinyin-lora is a text classification model from thc1006. Use it when you need a label for a piece of text. It is set up for peft. The card lists the license as cc-by-nc-sa-4.0.
拼音分支 v6 · Qwen3-8B + LoRA r=64 + 同音字攻擊強化防禦 Companion to v6-bilingual. Doubled rank from r=32 → r=64 for stronger phonetic pattern recognition.
Downloads · 30 days
0
Access
Public
Updated Apr 25, 2026
Repo size
361 MB
Likes
0
Public
Click a slice to open those files.
.safetensors349 MB · 96%
From the Hugging Face model README
拼音分支 v6 · Qwen3-8B + LoRA r=64 + 同音字攻擊強化防禦
Companion to v6-bilingual. Doubled rank from r=32 → r=64 for stronger phonetic pattern recognition.
| Metric | v5.1 | v6 |
|---|---|---|
| Pinyin-only dev F1 | 0.7979 | 0.7983 (≈ same) |
| Ensemble HED-COLD | 0.9126 | 0.9317 (+1.91pt) |
| Ensemble TC homo | 0.8496 | 0.8510 (+0.14pt) |
The pinyin LoRA's standalone dev F1 plateaus around 0.80, but the r=64 capacity helps the ensemble especially on systematic homophone perturbations (HED-COLD).
⚠️ Must be paired with v6-bilingual text LoRA. See the companion repo for full ensemble code.
| Parameter | Value |
|---|---|
| Base model | Qwen/Qwen3-8B-Base |
| LoRA rank | 64 |
| LoRA alpha | 128 |
| Training data | 179,186 samples (pinyin-converted v5 bilingual) |
| Epochs | 5 (best at epoch 2, step 9954) |
| Learning rate | 3e-5 |
| Max length | 192 |
| Precision | bf16 |
| Loss | Focal γ=2.5 + uncertainty + consistency λ=0.5 |
| Hardware | 1× NVIDIA RTX 5090 (32GB, 590W OC) |
CC BY-NC-SA 4.0.
See v6-bilingual.