Loke-60000

DeepSeek-V4-Flash-Vision-Exp-Abliterated-EXL3-K2.2-D2

README

License: mit

DeepSeek V4 Flash Vision-Exp, abliterated, EXL3 K2.2/D2

wrldsuksgo2mars/DeepSeek-V4-Flash-Vision-Exp-EXL3-K2.2-D2-v1 with the refusal edit from apetersson/DeepSeek-V4-Flash-Vision-Exp-Abliterated applied: the 33 layers.10..42.attn.wo_b tensors were replaced with the abliterated ones.

42 tok/s on code, 30 tok/s on prose, at a 500k context window with dSpark on a GB10.

Credits: DeepSeek, wrldsuksgo2mars, apetersson, drowzeys. MIT.

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

Loke-60000

Model Tree

Base

apetersson/DeepSeek-V4-Flash-Vision-Exp-Abliterated

Base

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

Base

wrldsuksgo2mars/DeepSeek-V4-Flash-Vision-Exp-EXL3-K2.2-D2-v1

Merged

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer