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:
remcohendriks
/
metrollm
like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
metrollm
1.53 MB
Ctrl+K
Ctrl+K
3 contributors
History:
62 commits
Remco Hendriks
Load LoRA adapter weights on CPU (ZeroGPU spaces>=0.51 fix)
494868c
7 days ago
dashboard
init: MetroLLM-Bench kiosk demo (2B + LoRA, free CPU)
4 months ago
data
demo: re-curate scenarios (first 3 per system ticket+issue, blockers demoted)
2 months ago
harness
sync: HF Space β /simulate prompt-construction parity
3 months ago
.gitattributes
Safe
1.52 kB
initial commit
4 months ago
.gitignore
Safe
58 Bytes
init: MetroLLM-Bench kiosk demo (2B + LoRA, free CPU)
4 months ago
README.md
Safe
833 Bytes
demo: switch to Qwen3.5-9B-metro-v24 (leakage-free retrain)
2 months ago
app.py
Safe
116 kB
Open header/footer paper and repo links in a new tab (iframe breakout)
about 2 months ago
model.py
Safe
9.79 kB
Load LoRA adapter weights on CPU (ZeroGPU spaces>=0.51 fix)
7 days ago
prompts.py
Safe
13.3 kB
sync: HF Space β /simulate prompt-construction parity
3 months ago
render.py
Safe
8.75 kB
landing replays for all 6 systems + render helpers
3 months ago
requirements.txt
Safe
2.18 kB
Unpin spaces (platform force-installs its version); keep peft==0.19.1
7 days ago
tools.py
Safe
4.7 kB
sync: HF Space β /simulate prompt-construction parity
3 months ago