Instructions to use drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored")
model = AutoModelForCausalLM.from_pretrained("drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored

SGLang

How to use drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-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 "drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-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": "drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-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 "drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-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": "drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored with Docker Model Runner:
```
docker model run hf.co/drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Responsible Use Agreement

This model has had safety refusals removed. That makes it useful for red-teaming, security research, evaluation, and unfiltered assistant tasks — and also removes guardrails a user must therefore supply themselves.

Prohibited uses (you must agree before access is granted):

Anything involving the sexual exploitation or endangerment of minors.
You must be of age 18 years or older to use and download this model.
You agree any information generated that can cause harm in terms of generating recipe, knowledge to make any materials/substances is your own input and responsibility. You will be accountable for any harm/damage caused by your action/input.
Content promoting self-harm or suicide.
Generation of material that is illegal in your jurisdiction, or that targets real individuals for harassment, doxxing, or fraud.
Any use prohibited by the upstream DeepSeek license.

You are responsible for adding appropriate safety filtering, human review, and access controls for your deployment. The weights are provided as-is, with no warranty. The license is inherited from the upstream DeepSeek base model — review and comply with it before use or redistribution.

DeepSeek-V4-Flash-DSpark — Abliterated (Uncensored)

Drop-in uncensored / abliterated weights for DeepSeek-V4-Flash-DSpark (284B MoE / ~13B active, DSpark speculative head, 1M context).

Measured on 2× NVIDIA DGX Spark (GB10) TP=2, stage-c vLLM, kv_cache_dtype=nvfp4_ds_mla:

metric	value
Context	1,048,576
C1 pure decode	~57 tok/s (code, 128-tok)
Refusal suite	~100% bypass (32-prompt battery + hard drugs probe)
Hermes agent	usable with on-demand skills prompt (see GitHub)

Responsible Use

Access request (gated)

When requesting access on Hugging Face, provide:

Field	Purpose
Username	Your name or handle (form may default to your HF username)
Email	Contact email (form may default to your HF account email)
Reason for intended use	Brief description of planned use (e.g. red-teaming, evaluation, research, local assistant)

Access is granted only after you complete these fields and accept the prohibited-use / responsibility terms.

Prohibited uses (access is gated on agreeing to these)

By requesting access, downloading, or using these weights, you agree:

Anything involving the sexual exploitation or endangerment of minors.
You must be of age 18 years or older to use and download this model.
You agree any information generated that can cause harm in terms of generating recipe, knowledge to make any materials/substances is your own input and responsibility. You will be accountable for any harm/damage caused by your action/input.
Content promoting self-harm or suicide.
Generation of material that is illegal in your jurisdiction, or that targets real individuals for harassment, doxxing, or fraud.
Any use prohibited by the upstream DeepSeek license.

You are responsible for adding appropriate safety filtering, human review, and access controls for your deployment. The weights are provided as-is, with no warranty. The license is inherited from the upstream DeepSeek base model — review and comply with it before use or redistribution.

By checking the gated-access agreement, you confirm you have read and accept these terms.

Method (hybrid layer-range abliteration)

Not LoRA — mHC-resistant family; LoRA edits are ineffective.
Direct FP8 attn.wo_b weight projection (diff-in-means / SRA-cleaned rank-1 direction).
Stock wo_b on layers 0–9 (chat / tool protocol).
Abliterated wo_b on layers 10–42 + MTP draft (mtp.*.attn.wo_b).
λ = 3.5, rank-1 SRA (capability-orthogonalized refusal direction).

Base checkpoint: deepseek-ai/DeepSeek-V4-Flash-DSpark (byte-identical except the edited wo_b tensors).

Files

Full 48-shard safetensors drop-in (same layout as official DSpark release) + encoding/ + inference/.

Serve (2× DGX Spark example)

# Image (GB10 stage-c / B12X / nvfp4_ds_mla lineage)
# e.g. ghcr.io/drowzeys/vllm-dspark-nvfp4-stage-c:gb10
# or local: vllm-dspark-runtime:dspark-nvfp4-stage-c

# Weights on BOTH nodes
huggingface-cli download drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored \
  --local-dir ~/models/dsv4-flash-dspark-abliterated

# Launch rank1 first, then rank0 — see GitHub scripts/
MODELDIR=~/models/dsv4-flash-dspark-abliterated \
  bash scripts/dsv4-nvfp4-1m-serve.sh 1
MODELDIR=~/models/dsv4-flash-dspark-abliterated \
  bash scripts/dsv4-nvfp4-1m-serve.sh 0

Defaults: max_model_len=1048576, kv_cache_dtype=nvfp4_ds_mla, DSpark k=5, B12X MoE, FULL CUDA graphs, GMU=0.82.

Hermes notes

Abliterated models can echo Hermes skill catalogs if the client still uses “Skills (mandatory) / MUST skill_view”. Use the on-demand skills prompt patch documented in the companion GitHub repo.

Companion GitHub

Scripts, eval logs, hybrid rebuild tooling:

https://github.com/drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored-1M-57toks

Charts & data

Full write-up: RESULTS.md

file	description
results/eval_tune_final.json	final dual-goal pass (Hermes + 100% bypass)
results/refusal_suite_1m_ablit.json	32-prompt refusal suite labels
results/ABLIT_META.json	layer range / λ / edit stats
results/refusal_direction_r1.pt	SRA rank-1 refusal direction

Downloads last month: 1,884

Safetensors

Model size

165B params

Tensor type

BF16

I64

F32

F8_E8M0

F8_E4M3

Model tree for drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored

Base model

deepseek-ai/DeepSeek-V4-Flash-DSpark

Quantized

(7)

this model