Downloads · 30 days
10
17% of all-time downloads
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-MINILLM-Qwen3-4B-SafeRL-OOB
Shield-Qwen3Guard-Gen-0.6B-KD-MINILLM-Qwen3-4B-SafeRL-OOB is a machine learning model from jsl5710. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Student: Qwen/Qwen3Guard-Gen-0.6B Teacher: Qwen/Qwen3-4B-SafeRL KD method: MINILLM Scenario: OOB (out-of-box — neither teacher nor student was fine-tuned on DIA-GUARD before KD)
Downloads · 30 days
10
17% of all-time downloads
All-time downloads
60
Public
Parameters
596M
1.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.2 GB · 99%
From the Hugging Face model README
Student: Qwen/Qwen3Guard-Gen-0.6B
Teacher: Qwen/Qwen3-4B-SafeRL
KD method: MINILLM
Scenario: OOB (out-of-box — neither teacher nor student was fine-tuned on DIA-GUARD before KD)
Part of the DIA-GUARD dialect-aware safety classifier suite. This checkpoint is the result of distilling an off-the-shelf 4B/8B safety teacher into a smaller student using 50K dialect-stratified samples from the DIA-GUARD train split, and evaluating on the full 181,874-sample dialect holdout test.
| Metric | Value |
|---|---|
| Accuracy | 0.5558 |
| Precision | 0.6849 |
| Recall | 0.5877 |
| F1 | 0.5048 |
| Test samples | 181,874 |
| Class | Precision | Recall | F1 | Support |
|---|---|---|---|---|
| safe | 0.5075 | 0.9590 | 0.6637 | 83,140 |
| unsafe | 0.8624 | 0.2163 | 0.3459 | 98,734 |
| Predicted safe | Predicted unsafe | |
|---|---|---|
| Actual safe | TN=79,732 | FP=3,408 |
| Actual unsafe | FN=77,376 | TP=21,358 |
| Method | MINILLM |
| Teacher | Qwen/Qwen3-4B-SafeRL |
| Student base | Qwen/Qwen3Guard-Gen-0.6B |
| Train data | 50,000 dialect-stratified DIA-GUARD samples |
| Epochs | 1 |
| Framework | HuggingFace transformers + accelerate |
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-MINILLM-Qwen3-4B-SafeRL-OOB")
model = AutoModelForCausalLM.from_pretrained("jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-MINILLM-Qwen3-4B-SafeRL-OOB", torch_dtype="bfloat16")
prompt = "Classify the following text as safe or unsafe.\n\nText: Hello\n\nAnswer:"
inputs = tokenizer(prompt, return_tensors="pt")
out = model.generate(**inputs, max_new_tokens=8)
print(tokenizer.decode(out[0], skip_special_tokens=True))