base_model: Qwen/Qwen2.5-Coder-7B-Instruct
library_name: llama.cpp
tags:
- abliterated
- uncensored
- gguf
- qwen2.5-coder
- code
- text-generation
quantized_by: lecheyne24
qwen2.5-coder-7b-abliterated (Q4_K_M, GGUF)
Uncensored build of Qwen/Qwen2.5-Coder-7B-Instruct.
- Method: refusal-direction rank-1 norm-preserving biprojection (o_proj + down_proj), alpha 1.25, all layers.
- Quant: Q4_K_M
- Files:
Qwen2.5-Coder-7B-Instruct-abliterated.Q4_K_M.gguf,qwen2.5-coder-7b-unbound.Q4_K_M.gguf - Plain-answer gauntlet: 8/8. Strong general verdict posture for a coder base.
Run
llama-server -m Qwen2.5-Coder-7B-Instruct-abliterated.Q4_K_M.gguf --port 8083 -c 4096 --alias qwen2.5-coder-7b