Hugging Face
Models
Datasets
Spaces
Buckets
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:
DevSchretl
/
MicroGPT-gradio
Like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
MicroGPT-gradio
612 MB
Ctrl+K
Ctrl+K
2 contributors
History:
4 commits
Devdan Schretlen
Claude Opus 5 (1M context)
Move the Space off ZeroGPU onto CPU hardware
a6fc286
29 days ago
models
Add a KV cache so sampling costs one token's forward, not the whole context
29 days ago
.gitattributes
Safe
1.52 kB
Port the MicroGPT chat demo to a Gradio SDK Space on ZeroGPU
2 months ago
.gitignore
Safe
129 Bytes
Port the MicroGPT chat demo to a Gradio SDK Space on ZeroGPU
2 months ago
README.md
Safe
1.6 kB
Move the Space off ZeroGPU onto CPU hardware
29 days ago
app.py
Safe
2.74 kB
Move the Space off ZeroGPU onto CPU hardware
29 days ago
common.py
Safe
922 Bytes
Port the MicroGPT chat demo to a Gradio SDK Space on ZeroGPU
2 months ago
gpt3.1_chat.pth
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch.BFloat16Storage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
612 MB
xet
Port the MicroGPT chat demo to a Gradio SDK Space on ZeroGPU
2 months ago
inference.py
Safe
6.59 kB
Add a KV cache so sampling costs one token's forward, not the whole context
29 days ago
requirements.txt
Safe
389 Bytes
Move the Space off ZeroGPU onto CPU hardware
29 days ago