anemll
/

anemll-forge-qwen3.8-27B

Text Generation

speculative-decoding

Model card Files Files and versions

anemll-forge-qwen3.8-27B

15.6 GB

Ctrl+K

Ctrl+K

1 contributor

History: 14 commits

anemll's picture

Release 0.2 card: KL comparison as in the quantized-export card

440f4e3 verified 22 days ago

coreai
Release 0.2: three-bit MLP, token-mixer rotations, distilled weights 22 days ago
drafter
Release 0.2: three-bit MLP, token-mixer rotations, distilled weights 22 days ago
model
Add Core AI Qwen3.8-27B M6 ANE research bundle about 1 month ago
.gitattributes

2.93 kB
Add paired Core AI DFlash2 speculative drafter about 1 month ago
LICENSE

11.5 kB
Add Core AI Qwen3.8-27B M6 ANE research bundle about 1 month ago
MODIFICATIONS.md

11.2 kB
Release 0.2 card: QAT wording 22 days ago
NOTICE

2 kB
Add V8-default selectable Core AI target packages about 1 month ago
QWEN_SOURCE.json

4.05 kB
Add Core AI Qwen3.8-27B M6 ANE research bundle about 1 month ago
README.md

27.4 kB
Release 0.2 card: KL comparison as in the quantized-export card 22 days ago
config.json

4.31 kB
Add Hub library metadata and root config for download tracking about 1 month ago
release.json

19.3 kB
Release 0.2 card: KL comparison as in the quantized-export card 22 days ago