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
runanywhere
/
canary_qwen_2.5b_HNPU
like
0
Follow
RunAnywhere, Inc.
8
Automatic Speech Recognition
hnpu
hexagon
npu
asr
v81
License:
cc-by-4.0
Model card
Files
Files and versions
xet
Community
1
Copy to bucket
new
main
canary_qwen_2.5b_HNPU
5.48 GB
Ctrl+K
Ctrl+K
2 contributors
History:
10 commits
sanmonga22
remove v75 bundle: not Plane-B-validated (Plane B load-fail (5.2GB > ceiling); LLM variant decode-over-prompt WIP)
0a57e0a
verified
11 days ago
v81
Prune QHexRT HNPU bundle to runtime-minimum artifacts
13 days ago
.gitattributes
1.69 kB
v75 (Galaxy S24 / SM8650, soc_model 57): Canary-Qwen-2.5B LLM path (LoRA-merged Qwen3-1.7B backbone) — runs 13.4 tok/s; NOT a standalone text LLM (needs audio) (#1)
13 days ago
README.md
553 Bytes
Prune QHexRT HNPU bundle to runtime-minimum artifacts
13 days ago
