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-UNCENSORED-MTP-Maya-K
DeepSeek-V4.1-Flash-1017-UNCENSORED-MTP-Maya-K is a abliterated and uncensored variant of Adolphsson/DeepSeek-V4.1-Flash-1017-UNCENSORED-Q8_0-GGUF, published on Hugging Face by Adolphsson. It is mit licence. It is distributed across 2 repositories in GGUF format, totalling 11.1K downloads.
Specification
- Model name
- DeepSeek-V4.1-Flash-1017-UNCENSORED-MTP-Maya-K
- Publisher
- Adolphsson
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- mit
- Task
- Image text to text
- Context window
- 860K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 26 Oct 2026
- Last updated
- 1 Nov 2026
Ablation technique
How DeepSeek-V4.1-Flash-1017-UNCENSORED-MTP-Maya-K was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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
“Uncensored 552B MoE with 1M-token context, vision and tool support — requantized to a mixed Q4K/IQ4 weight map and packed for Project Maya.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download Adolphsson/DeepSeek-V4.1-Flash-1017-UNCENSORED-MTP-Maya-Q4-K-IQ4-GGUF --local-dir ./deepseek-v4.1-flash-1017-uncensored-mtp-maya-k
llama-cli -m ./deepseek-v4.1-flash-1017-uncensored-mtp-maya-k/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Adolphsson/DeepSeek-V4.1-Flash-1017-UNCENSORED-MTP-Maya-Q4-K-IQ4-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve Adolphsson/DeepSeek-V4.1-Flash-1017-UNCENSORED-MTP-Maya-Q4-K-IQ4-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of DeepSeek-V4.1-Flash-1017-UNCENSORED-MTP-Maya-K.
| Repository | Format | Downloads |
|---|---|---|
| Adolphsson/DeepSeek-V4.1-Flash-1017-UNCENSORED-MTP-Maya-Q4-K-IQ4-GGUFsource | GGUF | 11.1K |
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-UNCENSORED-MTP-Maya-K 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.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- Declared licence is mit, but the terms that bind you are Adolphsson/DeepSeek-V4.1-Flash-1017-UNCENSORED-Q8_0-GGUF’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-UNCENSORED-MTP-Maya-K is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with Adolphsson, and does not independently verify publisher claims. See responsible use.