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:
SilverElixir
/
Lumen
Like
0
Running
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
8cdce5e
Lumen
/
eval
91.4 kB
Ctrl+K
Ctrl+K
4 contributors
History:
14 commits
SilverElixir
Probe tools: repeat loop for 500-rate measurement
169a54e
15 days ago
README.md
Safe
3.56 kB
Add harness-eval results: auto-edited AGENTS.md gives no gain on repo tasks
16 days ago
RESULTS.md
Safe
8.96 kB
Close aiohttp session leaks: no session without key, stub session in unit tests
16 days ago
harness_eval.py
Safe
33 kB
Close aiohttp session leaks: no session without key, stub session in unit tests
16 days ago
harness_weak.md
Safe
103 Bytes
Fix harness-eval: agent edits vs setup artifacts, weak arm, atomic cache
16 days ago
persona_models.py
Safe
34.4 kB
Probe tools: repeat loop for 500-rate measurement
15 days ago
persona_questions.json
Safe
9.57 kB
Add persona model eval: same 25 questions, same prompt as the bot, LLM judge
15 days ago
tasks.json
Safe
1.84 kB
Add harness-eval: measure whether auto-edited AGENTS.md helps the agent
16 days ago
