Downloads · 30 days
0
freaksterz-dflash2-vllm-adapter
halofx/freaksterz-dflash2-vllm-adapter
freaksterz-dflash2-vllm-adapter is a machine learning model from halofx. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository provides the runtime adapter used by halofx82/qwen3.8-27b-smoothquant-w8a8-int8-dflash2-vllm.
Access
Public
Updated Aug 30, 2026
Repo size
105 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors105 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026
- SHA
- 25c37fdf
Base models
Model card
From the Hugging Face model README
Freaksterz DFlash2 basis adapter
This repository provides the runtime adapter used by
halofx82/qwen3.8-27b-smoothquant-w8a8-int8-dflash2-vllm.
It bridges the rotated residual basis of Freaksterz/Qwen3.8-27B-SmoothQuant-W8A8-INT8 with the native basis expected by z-lab/Qwen3.8-27B-DFlash2 and lued/Qwen3.8-27B-DFlash2-W8.
It is not a standalone model. Use it only through the linked runtime project, which downloads this file automatically at container startup.
- License
- apache-2.0
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026