Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Ae55667
/
halogen-qwen3.8-flash-next-abliterated
Like
27
Text Generation
halogen
qwen
Mixture of Experts
abliterated
uncensored
strix-halo
gfx1151
rocm
amd
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
halogen-qwen3.8-flash-next-abliterated
27.1 GB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
Ae55667
Card: document direction recovery (s1/s2, measured lambda_eff), correct the 99 vs 100 tensor count
1e0caca
verified
8 days ago
.gitattributes
Safe
1.59 kB
Abliteration patch kit for Halogen Qwen3.8-Flash-Next
8 days ago
README.md
Safe
8.53 kB
Card: document direction recovery (s1/s2, measured lambda_eff), correct the 99 vs 100 tensor count
8 days ago
apply_expert_patch.py
Safe
3.57 kB
Abliteration patch kit for Halogen Qwen3.8-Flash-Next
8 days ago
expert_patch.bin
23.6 GB
xet
Abliteration patch kit for Halogen Qwen3.8-Flash-Next
8 days ago
expert_patch.manifest.json
Safe
14.6 kB
Abliteration patch kit for Halogen Qwen3.8-Flash-Next
8 days ago
qwen38-flash-next-w4b.overlay.hgn
3.51 GB
xet
Abliteration patch kit for Halogen Qwen3.8-Flash-Next
8 days ago
restore_expert_patch.py
Safe
1.71 kB
Abliteration patch kit for Halogen Qwen3.8-Flash-Next
8 days ago
