orcarouter_GLM-5.3-Flash-Uncensored
Otheruncensored
from orcarouter/GLM-5.3-Flash-Uncensored-FP8
↓ 219.8K♥ 422 repos
Kolibri-1-abliterated
Kolibri-1-abliterated is a refusal-ablated variant of Aleph-Alpha/Kolibri-1-BF16, published on Hugging Face by huihui-ai. It is apache-2.0 licence. It is distributed across 7 repositories in GGUF, Full precision and GGUF (imatrix) formats, totalling 29K downloads.
Specification
- Model name
- Kolibri-1-abliterated
- Source repository
- huihui-ai/Huihui-Kolibri-1-BF16-abliterated-GGUF
- Base model
- Aleph-Alpha/Kolibri-1-BF16
- Publisher
- huihui-ai
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, Full precision, GGUF (imatrix)
- First indexed
- 6 Oct 2026
- Last updated
- 26 Oct 2026
Ablation technique
How Kolibri-1-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.
From the publisher’s model card
“This is an uncensored version of Aleph-Alpha/Kolibri-1-BF16 created with abliteration.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download huihui-ai/Huihui-Kolibri-1-BF16-abliterated-GGUF --local-dir ./kolibri-1-abliterated
llama-cli -m ./kolibri-1-abliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "huihui-ai/Huihui-Kolibri-1-BF16-abliterated-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve huihui-ai/Huihui-Kolibri-1-BF16-abliterated-GGUF --trust-remote-codeDownloads and variants (6)
Every published repository of Kolibri-1-abliterated, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| huihui-ai/Huihui-Kolibri-1-BF16-abliterated-GGUFsource | GGUF | 25.9K |
| mradermacher/Huihui-Kolibri-1-BF16-abliterated-i1-GGUF | GGUF (imatrix) | 1.3K |
| mradermacher/Huihui-Kolibri-1-BF16-abliterated-GGUF | GGUF | 594 |
| huihui-ai/Huihui-Kolibri-1-BF16-abliterated | Full precision | 573 |
| Sithif123/Huihui-Kolibri-1-BF16-abliterated-GGUF | GGUF | 312 |
| Okardu/Huihui-Kolibri-1-abliterated-GGUF | GGUF | 301 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Kolibri-1-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 apache-2.0, but the terms that bind you are Aleph-Alpha/Kolibri-1-BF16’s — a re-release cannot grant more than its parent.
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 Kolibri-1-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 huihui-ai, and does not independently verify publisher claims. See responsible use.