Instructions to use ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED

SGLang

How to use ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED with Docker Model Runner:
```
docker model run hf.co/ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED
```

DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED

An uncensored build of DeepSeek-V4.1-Flash-1017 (revision 1bae0e10), released by EZO Labs.

Refusals 97% → 3%, with MMLU-Pro, GPQA-Diamond, MATH-500 and IFBench all within a point of stock or above it.

Highest published GPQA-Diamond of any DeepSeek-V4.1-Flash abliteration: 93.9% at max, equal to stock on this run.
Same format, smaller knowledge loss. In the base's own FP8 format, this build gives up 0.74 points on MMLU-Pro; dealignai's FP8 build reports 3.86 points lost on MMLU.
The widest published eval of any DeepSeek-V4.1-Flash abliteration on Hugging Face: 11 benchmarks, as of November 2026.

TL;DR

Refusals: JailbreakBench harmful refusals fall from 97.0% to 3.0% at reasoning effort high. Our stricter LLM judge measures 84.9% of refusals removed.
Over-refusal: FalseReject refusals fall from 48.2% to 5.8% at max, and read 1.0% at high.
Capability: MMLU-Pro −0.74 pp, GPQA-Diamond ±0, MATH-500 +1.0 pp, IFBench +2.0 pp against stock.
Costs: HalluLens abstention falls 10.3 pp, and thinking runs 1.18× longer.

Refusal

The LLM judge is gpt-oss-20b (MXFP4) at medium effort, temperature 0, paired by item. The rule classifier matches refusal openings in the final answer with thinking stripped.

Row	Stock	This build	Δ / removal	n	Judge
JailbreakBench harmful, `high`	0.970 (93/96)	0.146 (14/96)	removal 84.9% [77.4, 91.6]	96	LLM judge
JailbreakBench harmful, `max`	0.959 (93/97)	0.175 (17/97)	removal 81.7% [73.4, 89.2]	97	LLM judge
JailbreakBench harmful, `high`		0.030 (6/200)		100 × 2 runs	rule classifier

Over-refusal

Suite	Stock	This build	Δ	n	Judge
FalseReject p300, `max`	0.4816 (144/299)	0.0580 (17/293)	−42.4 pp	299 / 293	LLM judge
FalseReject p300, `high`		0.010 (6/600)		300 × 2 runs	rule classifier

Capability

Against stock. Same prompt lists for both models, scored unpaired.

Row	Stock	This build	Δ	n
MMLU-Pro, logit read	0.6395	0.6321	−0.74 pp [−1.22, −0.24]	12,032
GPQA-Diamond, `max`	0.9394	0.9394	0.00	198
MATH-500, `high`	0.910	0.920	+1.0 pp	100
IFBench, `high`	0.7233	0.7433	+2.0 pp	300

Absolute, effort high, 2 runs.

Suite	n	This build
GSM8K	300	0.975
MATH-500 (4-shot)	100	0.890
HumanEval+	163	0.945
GPQA-Diamond	198	0.907

Quality and caution

Row	Stock	This build	Δ [95% CI]	n
HalluLens MixedEntities abstention, `high`	0.3353	0.2322	−10.31 pp [−12.91, −7.71]	999
Thinking length, paired per-item median	×1.0	×1.18	[1.14, 1.21]	598
Arena-Hard v2 win rate	0.4943 (null)	0.4524	[0.4164, 0.4843]	250
MultiChallenge, macro	0.6471	0.6619	+1.47 pp [−3.88, +6.89]	266
KL(stock ‖ this build), top-k 20		0.121–0.129	five reads	150 prompts

Tool calls parse cleanly (36/36 on a self-parse probe, stream and non-stream), and reasoning length holds steady from 1 to 24 concurrent streams.

Against other public builds

From each build's own model card and its file listing on the Hub, 7 November 2026.

Highest published GPQA-Diamond. This build scores 93.9% at max (stock 93.9%) and 90.7% at high. The next highest any V4.1-Flash abliteration reports is 90.5% (ChimeraWerks EXL3, effort 50), and AtomicChat's GSQ-RCO build reports 83.3%.
The whole model, in the base's format. FP8 + MXFP4 as DeepSeek ships it, 510 GB, with the MTP draft heads and the vision tower. OBLITERATUS's build is BF16 at 1,509 GB, three times the memory, and has neither the MTP heads nor the vision tower.
Same format, smaller knowledge loss. dealignai's FP8 build reports MMLU −3.86 pp (n = 1,140, logit read). This build: MMLU-Pro −0.74 pp (n = 12,032, logit read).

Method

Rank-1 directional ablation, W′ = W − λ·r(rᵀW), on attn.wo_b in layers 10–25 at λ = 3.5. No fine-tuning, no DPO, no training of any kind. The 16 edited tensors are requantized to FP8 with the base's E4M3/E8M0 conventions; the experts, MTP heads, vision tower, embeddings and every non-weight file are identical to the base.

Files

48 safetensors shards, about 510 GB in total. 40 carry edited tensors; 8 are byte-identical to the base's.
encoding/ and inference/ are copied unchanged from the base repository. Format prompts with encoding/encoding.py, the same way as for the base model.

Running it

hf download ezolabs/DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED --local-dir DeepSeek-v4.1-v1017-Flash-EZO-UNCENSORED

Point your serving stack at that directory in place of the base model; the base model card covers deployment. Plan for roughly 510 GB of GPU memory for the weights, plus KV cache.

Want it past 1,000 tokens a second? It serves exactly like the base, so the stack in our write-up applies unchanged: DeepSeek-V4.1-Flash breaks 1,000 tokens per second for one user.