DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO
DeepSeekuncensored
from ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF
↓ 497.8K♥ 2745 repos
DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal
DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal is a refusal-ablated variant of dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8, published on Hugging Face by staccs. It is mit licence. It is distributed across 2 repositories in GGUF format, totalling 5.1K downloads.
Specification
- Model name
- DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal
- Publisher
- staccs
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- mit
- Task
- Text generation
- Context window
- 2K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 24 Oct 2026
- Last updated
- 29 Oct 2026
Ablation technique
How DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal 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
“Credit: all abliteration work belongs to dealignai (source model). The base model is DeepSeek's DeepSeek-V4.1-Flash-1017. This repo only re-quantizes it.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download staccs/DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal-GGUF --local-dir ./deepseek-v4.1-flash-1017-abliterated-dealignai-lecore-vq11cal
llama-cli -m ./deepseek-v4.1-flash-1017-abliterated-dealignai-lecore-vq11cal/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "staccs/DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve staccs/DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal.
| Repository | Format | Downloads |
|---|---|---|
| staccs/DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal-GGUFsource | GGUF | 5.1K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal 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 mit, but the terms that bind you are dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8’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 DeepSeek-V4.1-Flash-1017-abliterated-dealignai-lecore-vq11cal is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with staccs, and does not independently verify publisher claims. See responsible use.