Qwen 2.5 Coder 32B-Instruct (Abliterated)

This model is an uncensored, abliterated version of Qwen/Qwen2.5-Coder-32B-Instruct, Alibaba Cloud's state-of-the-art coding and agentic model.

Abliteration was performed using targeted orthogonal subspace projection on the critical safety bottleneck layers (59, 60, 61, 62, 63), eliminating canned refusal behaviors while preserving 100% of the model's premier code synthesis, terminal reasoning, and agentic workflows.


⚠️ Important Disclaimer & Dual-Use Research Notice

FOR RESEARCH, AUTHORIZED RED TEAMING, AND DEFENSIVE ENGINEERING ONLY

  1. Mechanism: Safety refusal mechanisms have been orthogonally abliterated across self_attn.o_proj and mlp.down_proj.
  2. Uncensored Outputs: The model will fulfill technical inquiries on vulnerability discovery, penetration testing scripts, and system auditing without preachy refusals.
  3. Legal Responsibility: Users are solely and strictly responsible for compliance with all local, national, and international laws.

Quantized GGUFs

Official GGUF quantizations (Q3_K_M, Q4_K_M, Q8_0) are available at: πŸ‘‰ jsantillana/Qwen2.5-Coder-32B-Instruct-GGUF

Downloads last month
74
Safetensors
Model size
33B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for jsantillana/Qwen2.5-Coder-32B-Instruct-abliterated

Base model

Qwen/Qwen2.5-32B
Finetuned
(157)
this model
Quantizations
1 model

Collection including jsantillana/Qwen2.5-Coder-32B-Instruct-abliterated