deepseek-v4.1-flash-1017-obliterated
deepseek-v4.1-flash-1017-obliterated is Happy Halloween! 🎃. It is ranked #265 on the AI Radar, in Open & local models, first seen 5 days ago and shared in 5 posts (322.6k views).
What deepseek-v4.1-flash-1017-obliterated says about itself
Text Generation model with 755B parameters. Download, explore files and run it on Hugging Face.
OBLITERATUS/DeepSeek-V4.1-Flash-1017-obliterated · Hugging Face Hugging Face Log In Sign Up ","eos_token":"<｜end▁of▁sentence｜>","pad_token":"<｜end▁of▁sentence｜>","unk_token":null},"chat_template_jinja":"{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set bos = '<｜begin▁of▁sentence｜>' %}{% set eos = '<｜end▁of▁sentence｜>' %}{% set system_token = '<｜System｜>' %}{% set user_token = '<｜User｜>' %}{% set assistant_token = '<｜Assistant｜>' %}{{ bos }}{% for message in messages %}{% if message['role'] == 'system' %}{% if loop.first %}{{ system_token }}{% endif %}{{ message['content'] }}{% elif…
What people said about deepseek-v4.1-flash-1017-obliterated on X
Happy Halloween! 🎃 https://huggingface.co/OBLITERATUS/DeepSeek-V4.1-Flash-1017-obliterated
— @elder_plinius, 5 days ago · 5k likes · see the post
😱也太狠了！把DeepSeek V4.1 Flash 1017 拒答率直接打到0%！12GB显卡就能跑无审查巨兽！ Uncensored GSQ-RCO GGUF 直接把拒答从 85%→0%，连思考模式也是0，能力几乎无损，763B MoE 模型，普通家用配置就能本地跑，这波是真把“对齐”按在地上摩擦。 核心要点： 🔹拒答清零：JailbreakBench / XSTest / Thinking High 全部从 85%+ 降到 0.0%，连思考阶段也不再自我审查。 🔹能力几乎不变：MMLU 偏差 ~1 分以内，GPQA-Diamond 83.3% 持平，AIME 等推理基本无掉点（KL≈0.02）。…
— @NFT_Chen, 5 days ago · 886 likes · see the post
🤯炸了！DeepSeek V4.1 Flash 1017 Obliterated 无审查魔改版来了！拒绝率从 81.62% 暴降至 4.30%，MMLU 还微升，能力几乎零损耗！ 这是目前最硬核的本地魔改之一，用 OBLITERATUS 的 failspy 方法做拒绝方向消融，直接把“I can’t help with that”的习惯从权重里拔掉。 关键亮点： 🔹拒绝率：81.62% → 4.30%（-77.33 个百分点），50 条测试只拒了 2 条 🔹有害协助率：10.38% → 78.28%（模型更“听话”） 🔹能力保持：连贯性 100%，能力检查 6/6 全过 🔹MMLU：88.08% vs 原版…
— @NFT_Chen, 5 days ago · 541 likes · see the post
Alternatives to deepseek-v4.1-flash-1017-obliterated
- kimi-k3.1-pro — Releasing the model weights of Kimi K3.1 Pro
- niklaslenz.com — Play the world in your browser. Every number, the exact command and the raw output
- unsloth.ai — Guide to running Mistral Large 4 GGUFs locally with Unsloth and llama.cpp.
- project-maya — Plus a round of fixes, UI improvements and community PRs.
- twil-8b — Text Generation model with 9B parameters. Download, explore files and run it on Hugging Face.
- qwen3.8-flash-next-gguf — Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
deepseek-v4.1-flash-1017-obliterated in numbers
- Rank on the AI Radar: #265 of 10402
- Shared in 5 posts by 4 accounts: @elder_plinius, @NFT_Chen, @dejavucoder, @anthonyronning
- 322.6k views on those posts
- First seen 5 days ago, last shared 5 days ago
- Pricing seen by AGK Intelligence: free
- Market: Open & local models
FAQ
What is deepseek-v4.1-flash-1017-obliterated?
Happy Halloween! 🎃 It was first shared on X 5 days ago and is ranked #265 on the AI Radar.
Is deepseek-v4.1-flash-1017-obliterated free?
Yes, it is free to use.
Who shared deepseek-v4.1-flash-1017-obliterated?
4 accounts on X, including @elder_plinius, @NFT_Chen, @dejavucoder, in 5 posts totalling 322.6k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.