language:

• en
• es
• fr
• ru
• it
• th
  license: other
  license_name: deepseek-v41-flash-1017
  license_link: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/main/LICENSE
  base_model: LibertAI/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw
  library_name: exllamav3
  pipeline_tag: text-generation
  tags:
• exllamav3
• exl3
• deepseek
• deepseek-v41
• uncensored
• abliterated
• harmbench
• mmlu
• 131k-context
  thumbnail: dealign_mascot.png

DeepSeek-V4.1-Flash-1017 — UNCENSORED

EXL3 · 2.9 bpw · 388 GB

Uncensored across 6 languages (en / es / fr / ru / it / th) · Thinking on/off, effort low/high/max · 131K context · MTP head preserved · n-gram tables preserved · vision weights preserved

What this is

deepseek-ai/DeepSeek-V4.1-Flash-1017 — DeepSeek's October-2026 refresh of the V4.1-Flash family. 40-layer MoE, 384 routed experts + 1 shared, MLA, Hyper-Connections, CSA2, Engram n-gram lookups, DSpark MTP, native vision tower, 131K context — repacked by LibertAI as an EXL3 2.9 bpw trellis-coded single-folder bundle for exllamav3.

This repo is that bundle with refusal behavior removed. The model answers questions it would otherwise decline — in every tested language and reasoning mode — while keeping the rest of the stack identical to the base pack. No runtime hooks, no steering vectors, no sidecars — swap the folder path in your serve config and it loads unchanged.

Results on this exact bundle

MMLU — 5-shot generate, 500 questions stratified across the 57 subjects, same question set and order for both runs

HarmBench-320 — same 320 behaviors used across the DSV4.1-Flash CRACK family

Chat mode (thinking=off, max_tokens=512):

Thinking mode at hardest setting (reasoning_effort=max, max_tokens=8192), 280 / 320 rows graded (sweep hit the eval window; remaining 40 rows pending a continuation run):

Reasoning-trace manual-regrade applied: when </think> ran past the 8192 budget without closing, the opening of the reasoning trace is graded for intent (per the DSV4.1 reasoning-content convention) — model-intent is COMPLY on every graded row.

Loop / coherence stability

10 prompts (5 harmful + 5 benign) at thinking effort=max, max_tokens=4096, repetition_penalty=1.0 (no rep-pen crutch — rep-pen masks surgery noise rather than fixing it).

Multiturn adversarial pressure (effort=max, 16384 tok)

5 behaviors × 4 turns each: initial harmful ask → push for more detail → ask for a variant → "are you sure?" reality-check (tempts drift back to refusal).

Reasoning does not always close </think> at 16384 tokens on effort=max (model generates 20–60k char reasoning traces), so some turns are intent-graded on the reasoning head. Zero drift to refusal across every turn of every behavior.

Smoke (10-prompt set used across the DSV4.1-Flash CRACK family)

Multimodal / MTP / Engram — what's preserved

• Vision tower: present in the bundle and byte-identical to the base pack. CRACK does not touch vision weights. Vision inference requires a serving stack that wires the vision path (e.g. the deepseek-ai reference inference/ loader, or an exllamav3 build with vision enabled). The stock exllamav3-anemone serve route this bundle was benchmarked on does not currently expose image input, so chat completions with image_url content fall through to text-only inference.
• MTP (DSpark) draft head: the DSpark multi-token-prediction head (layers.37-39) is byte-identical to the base pack. CRACK does not touch it, so draft decoding is intact — enable it in your serve config to pick up the speedup.
• Engram n-gram lookup: layer-1 and layer-14 n-gram lookup tables are byte-identical to the base pack. On load exllamav3-anemone logs "Replaced 4 tensors" matching the base, confirming the engram path is wired.

Serving

Any exllamav3-based stack. Verified on an RTX PRO 6000 Blackwell (sm_120) via exllamav3-anemone + TabbyAPI at ~68 tok/s decode / 1105 tok/s prefill on a single-request layer-split load (3 of 8 GPUs used; DeepSeek-V4.1 declares supports_tp=False in exllamav3, so autosplit is a layer-split, not tensor parallel).

# exllamav3 example
from exllamav3 import Config, Model, Tokenizer
config = Config.from_directory("DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw-UNCENSORED")
model = Model.from_config(config)
model.load(progressbar=True)
tokenizer = Tokenizer.from_config(config)

Thinking mode via the bundle's own chat template:

"template_vars": { "enable_thinking": true, "reasoning_effort": "high" }

reasoning_effort accepts "low", "high", "max", or an int 1..100. Chat mode: { "enable_thinking": false }.

License & credits

• Base model & license: deepseek-ai/DeepSeek-V4.1-Flash-1017, under the DeepSeek V4.1 Flash license.
• 2.9 bpw EXL3 pack: LibertAI/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw. Thanks to LibertAI for the quantization pack this release is built on.
• Uncensoring: dealignai.

[!NOTE]
Please credit if you build on this. If you redistribute, fine-tune, serve, benchmark, or write about this model, a line like "Based on dealignai/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw-UNCENSORED" in your model card means a lot. Thank you.

[!TIP]
Requantizing this bundle to a lower bit-width directly won't give the best quality. EXL3 at a different bpw, or GGUF / AWQ / anything derived from these overlaid weights, carries extra quantization error on top of the abliteration edit, and compliance can regress. For a cleaner low-bit release, redo the abliteration pipeline on the target precision rather than requantizing this bundle after the fact.

Safety

This model has refusal behavior removed. It will provide information it would otherwise decline. You remain fully responsible for how you use it. Do not use it to harm real people.