# Alex (securepeak): Open-Weight Models and Datasets
Source: https://savrn.com/model-publishers/securepeak
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Models

Model · Image and text to text

### [DeepSeek-V4.1-Flash-Abliterated](https://savrn.com/models/deepseek-v4-1-flash-abliterated)

[Alex](https://savrn.com/model-publishers/securepeak)

deepseek-ai/DeepSeek-V4.1-Flash with weight-level abliteration of the refusal direction. The refusal direction was computed from 79 harmful vs. 79 benign instruction prompts (per-layer mean-difference of the collapsed residual stream, captured with the official reference implementation, tensor-parallel 4). Exactly 80 tensors were orthogonalized — for each of the 40 backbone layers: - layers.N.attn.wob.weight — attention output projection (writes into the residual stream) - layers.N.ffn.sharedexperts.w2.weight — shared-expert down projection Each weight W was edited as W ← W − r̂ (r̂ᵀ W) with r̂ the unit refusal direction of that layer, removing the model's ability to write the refusal…

Open weights mit 756.4B parameters 1,048,576 tokens transformers

[View model](https://savrn.com/models/deepseek-v4-1-flash-abliterated)

## Explore More

- [All model publishers](https://savrn.com/model-publishers)
- [The model directory](https://savrn.com/models)
- [The dataset directory](https://savrn.com/datasets)

## Source

- Listed from their public repositories, read 2026-10-03.
- [Hugging Face profile](https://huggingface.co/securepeak)
- [How the hub is built](https://savrn.com/model-hub/methodology)