---
title: DeepSeek-V4-Flash-Vision-NVFP4-Mirror
canonical_url: "https://www.modelscope.cn/models/manateelazycat/DeepSeek-V4-Flash-Vision-NVFP4-Mirror"
md_url: "https://www.modelscope.cn/models/manateelazycat/DeepSeek-V4-Flash-Vision-NVFP4-Mirror.md"
repository: manateelazycat/DeepSeek-V4-Flash-Vision-NVFP4-Mirror
last_updated: 2026-09-21
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - deepseek_v4
architectures:
  - DeepseekV4ForCausalLM
base_model:
  - s-zaizen/DeepSeek-V4-Flash-Vision-Exp-NVFP4
  - deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
base_model_relation: quantized
parameters: 304.6B
tensor_type:
  - I64
  - I8
  - F8_E8M0
  - BF16
  - U8
  - F8_E4M3
  - F32
library_name:
  - safetensors
downloads: 115
stars: 0
tags:
  - deepseek-v4
  - vision
  - multimodal
  - modelopt
  - nvfp4
  - quantized
  - abliteration
  - uncensored
  - dgx-spark
---

# DeepSeek-V4-Flash-Vision-NVFP4-Mirror

> DeepSeek-V4-Flash-Vision-NVFP4-Mirror - manateelazycat 在 ModelScope 开源的模型。NVFP4 vision-language model mirror. Original MIT license, NOTICE and model card are preserved; source and fixed revision are recorded in the repository.

manateelazycat/DeepSeek-V4-Flash-Vision-NVFP4-Mirror 是 ModelScope 魔搭社区上的 304.6B 参数image-text-to-text模型，采用 mit 许可，基于 s-zaizen/DeepSeek-V4-Flash-Vision-Exp-NVFP4、deepseek-ai/DeepSeek-V4-Flash-Vision-Exp 构建。

- **Repository**: manateelazycat/DeepSeek-V4-Flash-Vision-NVFP4-Mirror
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 304.6B
- **Base model**: s-zaizen/DeepSeek-V4-Flash-Vision-Exp-NVFP4, deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
- **Tags**: deepseek-v4, vision, multimodal, modelopt, nvfp4, quantized, abliteration, uncensored, dgx-spark
- **Downloads**: 115
- **Stars**: 0
- **Last updated**: 2026-09-21

Source: https://www.modelscope.cn/models/manateelazycat/DeepSeek-V4-Flash-Vision-NVFP4-Mirror

---

# 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 of
`s-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 in
`ABLITERATION_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. See
`ABLITERATION_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`, revision
  `7e17ce5c84b088d08878cbe6708ae84d989fa256`
- Native source: `deepseek-ai/DeepSeek-V4-Flash-Vision-Exp`, revision
  `86f746b36186f0e567729a5c06a8c918caba82a9`
- Abliteration donor:
  `apetersson/DeepSeek-V4-Flash-Vision-Exp-Abliterated`, revision
  `71e308afc1120c9688da67e54d1b54fe6ddd5c94`, variant
  `Reference-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.