mlboydaisuke
/

Qwen3.8-27B-CoreAI

Image-Text-to-Text

Model card Files Files and versions

Qwen3.8-27B-CoreAI

60.5 GB

Ctrl+K

Ctrl+K

1 contributor

History: 10 commits

mlboydaisuke's picture

Qwen3.8-27B: remove pf32 VL decoder (fp16 overflow on real images; pf16 replaces it)

927bbee verified about 13 hours ago

gpu-pipelined
Qwen3.8-27B: remove pf32 VL decoder (fp16 overflow on real images; pf16 replaces it) about 13 hours ago
.gitattributes
2.46 kB
Qwen3.8-27B: VL decoder pf16 (pf32 chunk overflows fp16 content-dependently) about 13 hours ago
LICENSE
11.5 kB
Qwen3.8-27B: LICENSE about 18 hours ago
README.md
6.55 kB
Link the card back to its collection and the request box about 14 hours ago
config.json
4.31 kB
Qwen3.8-27B: config.json about 18 hours ago