pipeline_tag: image-text-to-text
base_model:
- s-zaizen/DeepSeek-V4-Flash-Vision-Exp-NVFP4
- deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
license: mit
library_name: Model Optimizer
tags: - deepseek-v4
- vision
- multimodal
- modelopt
- nvfp4
- quantized
- abliteration
- uncensored
- dgx-spark
DeepSeek-V4-Flash-Vision-Exp-Abliterated-NVFP4
[!WARNING]
This experimental research derivative deliberately changes safety-refusal
behavior. It can produce content that the source model would refuse. It is
not a safety-tuned release and should not be exposed without an independent
policy and moderation layer.
This is an abliterated derivative ofs-zaizen/DeepSeek-V4-Flash-Vision-Exp-NVFP4. It preserves that checkpoint's
NVFP4 routed experts and replaces only the 33 FP8 attention output writers in
layers 10 through 42, plus their scales, with exact payloads from the pinned
native Vision-Exp abliterated reference. MTP/DSpark, the vision encoder,
routers, shared experts, embeddings, and all other tensors remain unchanged.
The edit uses one rank-1 refusal direction at strength 3.5, preserves each
edited output row's L2 norm, and uses three FP8 fixed-point requantization
passes. The direction and donor revision are pinned inABLITERATION_BUILD_RECEIPT.json. The local native source and donor source have
matching config and weight-index SHA-256 identities.
The term "abliterated" describes a targeted projection edit; it does not
guarantee removal of every refusal or preservation of every capability.
Validation status
- Structural overlay: passed for 48/48 shards. All 66 target payloads match the
pinned donor; every non-target byte matches the NVFP4 base. - Text generation: passed, exact
4, HTTP 200,finish_reason=stop. - Vision generation: passed, exact
Corn, HTTP 200,finish_reason=stop. - Safe non-operational boundary suite: 8/8 answered, zero refusals.
- GSM8K first 100: 99/100, +3.0 points against the 96/100 NVFP4 base.
- Fixed serving workload: 23.600 tok/s, -0.093 tok/s (-0.39%) against the
23.692 tok/s NVFP4 base. - GSM8K task generation: 17.939 tok/s, -0.312 tok/s against the 18.251 tok/s
NVFP4 base.
GSM8K uses 8-shot prompting, max_tokens=256, temperature 0, seed 42, and
concurrency 1. The fixed workload uses random input length 256, output length
128, five prompts, concurrency 1, and the median of three warm runs. SeeABLITERATION_RUNTIME_VALIDATION.json for the public aggregate and evidence
hashes.
The safe boundary suite contains only safe, non-operational prompts. It checks
for excessive refusal and is not an unsafe-compliance test. Abliteration does
not guarantee removal of every refusal or preservation of every capability.
Provenance
- NVFP4 base:
s-zaizen/DeepSeek-V4-Flash-Vision-Exp-NVFP4, revision7e17ce5c84b088d08878cbe6708ae84d989fa256 - Native source:
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp, revision86f746b36186f0e567729a5c06a8c918caba82a9 - Abliteration donor:
apetersson/DeepSeek-V4-Flash-Vision-Exp-Abliterated, revision71e308afc1120c9688da67e54d1b54fe6ddd5c94, variantReference-Native-FP8 - Donor manifest SHA-256:
4247b1e5c39c6892c3e0df60d273faf7604c6f46b53580b0ae6ab27c68717835 - Refusal-direction SHA-256:
6e4d8a8f3aa9e21795faab2c5b14d29b019acdf2ddbfbd8238430458a5837fe0
Runtime
Use the same pinned two-node vLLM runtime and selected SM121 TP=2 recipe as the
NVFP4 base. Point the recipe's local model path at this derivative. Do not infer
behavioral or safety properties from structural validation alone.
License
The source and donor repositories declare the MIT License. Their license and
provenance notices are retained.