ModelHub XC 673c52dfd9 初始化项目,由ModelHub XC社区提供模型
Model: xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2
Source: Original Platform
2026-11-16 18:27:31 +08:00

base_model, library_name, datasets, tags
base_model library_name datasets tags
Qwen/Qwen2.5-Coder-3B-Instruct transformers
fengyao1909/SecCodePLT_Plus
code
security
grpo
seccodeplt

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.

S
Description
Model synced from source: xw1234gan/seccodeplt-qwen2.5-coder-3b-diff-sft-v2
Readme
2 MiB
0 Stars 1 Watchers 0 Forks
Languages
Jinja 100%