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
Spaces:
logic65
/
whittle-45b-chat
Like
0
Running
on
Zero
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
whittle-45b-chat
20.4 kB
Ctrl+K
Ctrl+K
1 contributor
History:
8 commits
logic65
Request at most 140 s of GPU (x2 on xlarge fits a free account's 300 s/day); max 1024 new tokens
9b47d2f
verified
5 days ago
.gitattributes
Safe
1.52 kB
initial commit
5 days ago
README.md
Safe
690 Bytes
Whittle 45B ZeroGPU chat demo: stock transformers + whittle_load.py, model mounted at /models/w45
5 days ago
app.py
Safe
9.54 kB
Request at most 140 s of GPU (x2 on xlarge fits a free account's 300 s/day); max 1024 new tokens
5 days ago
requirements.txt
Safe
79 Bytes
Small files from the Hub, shards from the mount (size-checked); drop flash-linear-attention (no GPU at import on ZeroGPU)
5 days ago
whittle_load.py
Safe
8.6 kB
Table to RAM with 64 MB sequential reads (page-faulting the mmap over the mount was far too slow)
5 days ago
