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
mlboydaisuke
/
Muse-Glimmer-30B-CoreAI
like
0
Text Generation
muse_glimmer
coreai
aimodel
apple-silicon
on-device
muse-glimmer
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Muse-Glimmer-30B-CoreAI
16.4 GB
Ctrl+K
Ctrl+K
1 contributor
History:
9 commits
mlboydaisuke
card: GSM8K 100q across all three runtimes (98/97/95) + the two-pass budget note
ce8bdda
verified
10 days ago
gpu-pipelined
fix: declare <|eot|> as a stop token — the bundle never terminated
10 days ago
.gitattributes
Safe
1.79 kB
Muse-Glimmer-30B text decoder -> Core AI: decode int4hu (--head-sym), token-exact vs fp16 oracle, 26.69 tok/s on M4 Max
11 days ago
LICENSE
Safe
11.4 kB
Muse-Glimmer-30B text decoder -> Core AI: decode int4hu (--head-sym), token-exact vs fp16 oracle, 26.69 tok/s on M4 Max
11 days ago
README.md
12.7 kB
card: GSM8K 100q across all three runtimes (98/97/95) + the two-pass budget note
10 days ago
config.json
Safe
5.11 kB
Muse-Glimmer-30B text decoder -> Core AI: decode int4hu (--head-sym), token-exact vs fp16 oracle, 26.69 tok/s on M4 Max
11 days ago
gate-muse-glimmer-30b-int4hu.json
Safe
3.08 kB
Muse-Glimmer-30B text decoder -> Core AI: decode int4hu (--head-sym), token-exact vs fp16 oracle, 26.69 tok/s on M4 Max
11 days ago
