GLM-4.7-Flash-abliterated
GLM
from zai-org/GLM-4.7-Flash
↓ 137.4K♥ 8614 repos
GLM-5.2-abliterated
GLM-5.2-abliterated is a refusal-ablated variant of zai-org/GLM-5.2, published on Hugging Face by OpenYourMind. It is other licence. It is distributed across 22 repositories in GGUF, FP8, Transformers and NVFP4 formats, totalling 16.8K downloads.
Specification
- Model name
- GLM-5.2-abliterated
- Source repository
- OpenYourMind/GLM-5.2-abliterated
- Base model
- zai-org/GLM-5.2
- Publisher
- OpenYourMind
- Parameters
- Not determinable from name
- Hardware class
- Unknown
- Licence
- other
- Task
- Unspecified
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, FP8, Transformers, NVFP4
- First indexed
- 24 Jun 2026
- Last updated
- 28 Aug 2026
Ablation technique
How GLM-5.2-abliterated was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download huihui-ai/Huihui-GLM-5.2-abliterated-GGUF --local-dir ./glm-5.2-abliterated
llama-cli -m ./glm-5.2-abliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "OpenYourMind/GLM-5.2-abliterated"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve OpenYourMind/GLM-5.2-abliterated --trust-remote-codeDownloads and variants (21)
Every published repository of GLM-5.2-abliterated, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- GLM-5.2-abliterated will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is other, but the terms that bind you are zai-org/GLM-5.2’s — a re-release cannot grant more than its parent.
- The source repository is gated, so downloading requires accepting the publisher’s terms.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for GLM-5.2-abliterated is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with OpenYourMind, and does not independently verify publisher claims. See responsible use.