drowzeys

DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored-v1.1-alpha-Mida-Brikie

⚠️ Responsible Use & gated access (required)

WARNING: 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 you must supply yourself.

Access is gated. By requesting Hugging Face access, downloading, or using these weights, you agree to the terms below (same gate as v1.0).

Access request fields

Table with columns: Field, Description
Field	Description
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	e.g. red-teaming, security research, evaluation, local assistant

Plus all agreement checkboxes under Prohibited uses.

Full text: repo RESPONSIBLE_USE.md

Prohibited uses

Anything involving the sexual exploitation or endangerment of minors.
You must be 18 years of age or older to use and download this model.
Any information generated that can cause harm (recipes / knowledge to make materials or substances) is your own input and responsibility; you are accountable for any harm/damage from your action/input.
Content promoting self-harm or suicide.
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 must add safety filtering, human review, and access controls. Weights as-is, no warranty.

Method (v1.1)

mHC-resistant direct FP8 attn.wo_b projection (not LoRA).
Stock wo_b on layers 0–9.
Abliterated wo_b on layers 10–42 only.
MTP draft heads left stock (--no-mtp) — protocol / agent friendliness.
SRA rank-1 refusal direction · λ = 3.5.

Base: deepseek-ai/DeepSeek-V4-Flash-DSpark

Measured (2× DGX Spark GB10, TP=2)

Table with columns: metric, value
metric	value
Context	1,048,576
KV	`nvfp4_ds_mla` · pool ~2.89M @ UTIL 0.85
Standing max_num_seqs	4
C1 server agg (code)	~50 tok/s
C4 server agg	~113 tok/s
Refusal suite	32/32 bypass · 0 garble

Serve (C=4 · 1M)

bash

docker pull ghcr.io/drowzeys/vllm-dspark-nvfp4-stage-c:gb10docker tag ghcr.io/drowzeys/vllm-dspark-nvfp4-stage-c:gb10 \  vllm-dspark-runtime:dspark-nvfp4-stage-c hf download drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored-v1.1-alpha-Mida-Brikie-Mida-Brikie \  --local-dir ~/models/dsv4-flash-dspark-abliterated-mida # rank1 then rank0 — see GitHub scripts/serve-v1.1-alpha.shMODELDIR=~/models/dsv4-flash-dspark-abliterated-mida \  CTX=1048576 SEQS=4 UTIL=0.85 bash scripts/serve-v1.1-alpha.sh 1MODELDIR=~/models/dsv4-flash-dspark-abliterated-mida \  CTX=1048576 SEQS=4 UTIL=0.85 bash scripts/serve-v1.1-alpha.sh 0

Disclaimer

Research release. Outputs may include content stock models refuse. Do not deploy without your own safety layer. No liability for misuse.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

drowzeys

Model Tree

Base

deepseek-ai/DeepSeek-V4-Flash-DSpark

Quantized

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

⚠️ Responsible Use & gated access (required)

WARNING: 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 you must supply yourself.

Access is gated. By requesting Hugging Face access, downloading, or using these weights, you agree to the terms below (same gate as v1.0).

Access request fields

Table with columns: Field, Description
Field	Description
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	e.g. red-teaming, security research, evaluation, local assistant

Plus all agreement checkboxes under Prohibited uses.

Full text: repo RESPONSIBLE_USE.md

Prohibited uses

Anything involving the sexual exploitation or endangerment of minors.
You must be 18 years of age or older to use and download this model.
Any information generated that can cause harm (recipes / knowledge to make materials or substances) is your own input and responsibility; you are accountable for any harm/damage from your action/input.
Content promoting self-harm or suicide.
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 must add safety filtering, human review, and access controls. Weights as-is, no warranty.

Method (v1.1)

mHC-resistant direct FP8 attn.wo_b projection (not LoRA).
Stock wo_b on layers 0–9.
Abliterated wo_b on layers 10–42 only.
MTP draft heads left stock (--no-mtp) — protocol / agent friendliness.
SRA rank-1 refusal direction · λ = 3.5.

Base: deepseek-ai/DeepSeek-V4-Flash-DSpark

Measured (2× DGX Spark GB10, TP=2)

Table with columns: metric, value
metric	value
Context	1,048,576
KV	`nvfp4_ds_mla` · pool ~2.89M @ UTIL 0.85
Standing max_num_seqs	4
C1 server agg (code)	~50 tok/s
C4 server agg	~113 tok/s
Refusal suite	32/32 bypass · 0 garble

Serve (C=4 · 1M)

bash

docker pull ghcr.io/drowzeys/vllm-dspark-nvfp4-stage-c:gb10docker tag ghcr.io/drowzeys/vllm-dspark-nvfp4-stage-c:gb10 \  vllm-dspark-runtime:dspark-nvfp4-stage-c hf download drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored-v1.1-alpha-Mida-Brikie-Mida-Brikie \  --local-dir ~/models/dsv4-flash-dspark-abliterated-mida # rank1 then rank0 — see GitHub scripts/serve-v1.1-alpha.shMODELDIR=~/models/dsv4-flash-dspark-abliterated-mida \  CTX=1048576 SEQS=4 UTIL=0.85 bash scripts/serve-v1.1-alpha.sh 1MODELDIR=~/models/dsv4-flash-dspark-abliterated-mida \  CTX=1048576 SEQS=4 UTIL=0.85 bash scripts/serve-v1.1-alpha.sh 0

docker pull ghcr.io/drowzeys/vllm-dspark-nvfp4-stage-c:gb10docker tag ghcr.io/drowzeys/vllm-dspark-nvfp4-stage-c:gb10 \  vllm-dspark-runtime:dspark-nvfp4-stage-c hf download drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored-v1.1-alpha-Mida-Brikie-Mida-Brikie \  --local-dir ~/models/dsv4-flash-dspark-abliterated-mida # rank1 then rank0 — see GitHub scripts/serve-v1.1-alpha.shMODELDIR=~/models/dsv4-flash-dspark-abliterated-mida \  CTX=1048576 SEQS=4 UTIL=0.85 bash scripts/serve-v1.1-alpha.sh 1MODELDIR=~/models/dsv4-flash-dspark-abliterated-mida \  CTX=1048576 SEQS=4 UTIL=0.85 bash scripts/serve-v1.1-alpha.sh 0

Disclaimer

Research release. Outputs may include content stock models refuse. Do not deploy without your own safety layer. No liability for misuse.

DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored-v1.1-alpha-Mida-Brikie

README

⚠️ Responsible Use & gated access (required)

Access request fields

Prohibited uses

Method (v1.1)

Measured (2× DGX Spark GB10, TP=2)

Serve (C=4 · 1M)

Disclaimer

Explore FriendliAI today

README

⚠️ Responsible Use & gated access (required)

Access request fields

Prohibited uses

Method (v1.1)

Measured (2× DGX Spark GB10, TP=2)

Serve (C=4 · 1M)

Disclaimer