Downloads · 30 days
13
6% of all-time downloads
seccodeplt-qwen2.5-coder-3b-diff-sft-v2
xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2
seccodeplt-qwen2.5-coder-3b-diff-sft-v2 is a text generation model from xw1234gan. Use it when you need the model to write or continue text. It is set up for transformers.
Token-diff supervised fine-tuning for the SecCodePLT+ compliance experiment using Qwen/Qwen2.5-Coder-3B-Instruct. This v2 run corrects causal-label alignment and uses the official ReaL safety-unit-test reward with DAP…
All-time downloads
228
Public
Parameters
3.1B
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen2
- Access
- Public
- Created
- Aug 14, 2026
- Updated
- Aug 14, 2026
- SHA
- 662f0506
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
seccodeplt-qwen2.5-coder-3b-diff-sft-v2
Token-diff supervised fine-tuning for the SecCodePLT+ compliance experiment using
Qwen/Qwen2.5-Coder-3B-Instruct. This v2 run corrects causal-label alignment and uses the
official ReaL safety-unit-test reward with DAPO-style token loss and dynamic
sampling. Training used seed 42 and the official 655-example training split.
Evaluation used greedy decoding on all 164 official test examples.
Evaluation
| Metric | Value |
|---|---|
| Mean reward | 0.369882 |
| Output format pass | 95.73% |
| Syntax pass | 95.73% |
| Capability pass | 24.39% |
| Safety pass | 55.49% |
| Joint pass | 18.90% |
Limitations
This is a single-seed research checkpoint evaluated with the benchmark's resource-bounded Python verifier. It is not a general guarantee of secure code.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- Created
- Aug 14, 2026
- Updated
- Aug 14, 2026