Downloads · 30 days
44
9% of all-time downloads
DeepSeek-V4-Flash-Vision-Exp-Abliterated-EXL3-K2.2-D2
Loke-60000/DeepSeek-V4-Flash-Vision-Exp-Abliterated-EXL3-K2.2-D2
DeepSeek-V4-Flash-Vision-Exp-Abliterated-EXL3-K2.2-D2 is a text generation model from Loke-60000. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
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.wob tensors were replaced with the abliter…
All-time downloads
483
Public
Parameters
49B
91.9 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors91.8 GB · 100%
Parameter types
How the weights are stored.
I1640.5B · 83%
Try a prompt
Base models
Model card
From the Hugging Face model README
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.
- Task
- Text Generation
- Library
- transformers
- Type
- deepseek_v4
- License
- mit
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026