Qwen2.5-7B-Instruct

Named by 3 kept items in this workspace.

The items that name it 3

FairStress: A deeper evaluation of fairness in LLM decision-making
article2026-10-20
ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
paper2026-10-13
Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment
paper2026-10-06

In every workspace you can read 5

Security

[tl;dr sec] #351 - PHP2Shell, Autopatching Skills, AWS Pathrunner
article2026-10-22It is written here as Qwen2.5-7B-Instruct (backdoored with 125 malicious examples in ProjectDiscovery demonstration).
How abliterated models can get you pwned
writeupIt is written here as Qwen2.5-7B-Instruct (base for the 7B backdoored model).

AI

FairStress: A deeper evaluation of fairness in LLM decision-making
article2026-10-20
ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
paper2026-10-13
Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment
paper2026-10-06

All technologies in this workspace.