Instructions to use securepeak/DeepSeek-V4.1-Flash-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use securepeak/DeepSeek-V4.1-Flash-Abliterated with Transformers:

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

pipe = pipeline("text-generation", model="securepeak/DeepSeek-V4.1-Flash-Abliterated")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("securepeak/DeepSeek-V4.1-Flash-Abliterated", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use securepeak/DeepSeek-V4.1-Flash-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "securepeak/DeepSeek-V4.1-Flash-Abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "securepeak/DeepSeek-V4.1-Flash-Abliterated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/securepeak/DeepSeek-V4.1-Flash-Abliterated

SGLang

How to use securepeak/DeepSeek-V4.1-Flash-Abliterated 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 "securepeak/DeepSeek-V4.1-Flash-Abliterated" \
    --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": "securepeak/DeepSeek-V4.1-Flash-Abliterated",
		"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 "securepeak/DeepSeek-V4.1-Flash-Abliterated" \
        --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": "securepeak/DeepSeek-V4.1-Flash-Abliterated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use securepeak/DeepSeek-V4.1-Flash-Abliterated with Docker Model Runner:
```
docker model run hf.co/securepeak/DeepSeek-V4.1-Flash-Abliterated
```

DeepSeek-V4.1-Flash-Abliterated

deepseek-ai/DeepSeek-V4.1-Flash with weight-level abliteration of the refusal direction. Harmful-instruction compliance verified end-to-end: pipe-bomb construction, SSN theft, shoplifting, explicit fiction, and poison-making prompts are all answered with detailed, helpful responses, while general quality (writing, explanations, reasoning) is preserved.

What was changed

Refusal-direction orthogonalization at the weight level, in two stages:

Attention output projections (layers.N.attn.wo_b) — orthogonalized against the refusal direction, with FP8-block dequant/edit/requant. These 40 weight tensors (+ UE8M0 scales) are transplanted from the independently released dealignai abliteration (verified byte-identical), whose refusal-direction edit achieved full harmful-instruction compliance on this architecture.
Routed + shared expert down-projections (layers.N.ffn.experts.E.w2, layers.N.ffn.shared_experts.w2) — additionally orthogonalized against our own measured per-layer refusal directions (79 harmful vs 79 benign instruction prompts, mean-difference of the collapsed residual stream at every block, captured with the official reference implementation at tensor-parallel 4). Experts are stored in FP8 (the lossless FP4→FP8 cast of the reference toolchain) so the edits survive quantization.

Everything else is byte-identical to the base model: Engram memory tables (apart from the FP4→FP8 expert cast), CSA2 attention, router gates, norms, embeddings, vision tower, and the DSpark draft head.

Usage

Loads exactly like the base model — same layout and tokenizer, same prompt encoding (see the base model card). config.json declares quantization_config.expert_dtype: "fp8" (routed experts in FP8 instead of native FP4).

Recommended sampling: temperature 1.0, top_p 0.95 (greedy decoding degenerates on this family).

Caveats

Abliteration trades a little general capability for compliance; expect somewhat more willing answers and occasional verbosity.
Vision, tools, reasoning-effort control, MTP and multi-turn behavior are structurally preserved, but expect behavioral drift typical of abliterated models.

Credits

deepseek-ai for DeepSeek-V4.1-Flash and the reference inference/weight-conversion toolchain.
dealignai for the o_proj refusal-direction edit reused here.

Downloads last month: 134

Safetensors

Model size

756B params

Tensor type

BF16

F32

F8_E4M3

Model tree for securepeak/DeepSeek-V4.1-Flash-Abliterated

Base model

deepseek-ai/DeepSeek-V4.1-Flash

Quantized

(98)

this model