Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
llm-council
/
sandbox
like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
sandbox
Ctrl+K
Ctrl+K
1 contributor
History:
14 commits
justinxzhao
Parse judgments with structured output prompting, one response model, one judge model at a time.
eb4ec23
10 months ago
img
Added general rendering of chats so that they don't disappear during app saving.
10 months ago
.gitattributes
Safe
1.52 kB
initial commit
10 months ago
.gitignore
Safe
40 Bytes
Added general rendering of chats so that they don't disappear during app saving.
10 months ago
README.md
Safe
250 Bytes
initial commit
10 months ago
app.py
Safe
40.2 kB
Parse judgments with structured output prompting, one response model, one judge model at a time.
10 months ago
app2.py
Safe
1.63 kB
Some refactoring, judging responses for direct assessment.
10 months ago
constants.py
Safe
15 kB
Add token usage tracking for openai and fix token usage tracking for anthropic.
10 months ago
judging.py
Safe
660 Bytes
Some refactoring, judging responses for direct assessment.
10 months ago
judging_dataclasses.py
Safe
1.01 kB
Parse judgments with structured output prompting, one response model, one judge model at a time.
10 months ago
prompts.py
Safe
4.38 kB
Parse judgments with structured output prompting, one response model, one judge model at a time.
10 months ago
requirements.txt
Safe
70 Bytes
Streaming working, with different providers.
10 months ago