Commit History

Add Anthropic Opus support
64c61f3

lukestanley commited on

Fix: when using http worker, only download if inference is on localhost
52fc709

lukestanley commited on

remove unused helpers
c4d55d5

lukestanley commited on

Refactor code: Import libraries, compare moderation APIs, and remove unused code
ac30aa7

lukestanley commited on

WIP spicy Jigsaw - Wikipedia talk page dataset review and scoring
759e510

lukestanley commited on

Add retry logic upon schema fail for Mistral API calls
1e622b4

lukestanley commited on

Update .gitignore file to include .jsonl and .json files
135f3ac

lukestanley commited on

Add local logging option if SKIP_NETWORK environment variable is set
960dc11

lukestanley commited on

Add data capture endpoint using Gradio's API hosted by HF's Gradio dynamic hostname
2c65c23

lukestanley commited on

Explain data use in Gradio app
2a1f022

lukestanley commited on

Log to remote server in non-blocking way
d2c07f7

lukestanley commited on

Add log_to_jsonl function to data.py and remove duplicate function from utils.py
44bab49

lukestanley commited on

Moves logging from app.py to chill.py
2ef37b6

lukestanley commited on

Add JSONL disk file logging functionality to app.py and utils.py
abbebf8

lukestanley commited on

Add system map and worker architecture details
293af3a

lukestanley commited on

Readme: Note on Mistral API used, serverless backend for reliability
8c64a35

lukestanley commited on

Show iteration count and time used
2a25399

lukestanley commited on

Show scores as percentages
b68eb49

lukestanley commited on

Count LLM request and show in UI, minor text changes
52ff483

lukestanley commited on

Tidying: reordering code a bit
124003a

lukestanley commited on

Add Mistral API support due to my RunPod serverless system reliability issues
8093276

lukestanley commited on

Add TODO for Runpod timeout handling
3c6c618

lukestanley commited on

Docs: HuggingFace README.md metadata changes
1dba83c

lukestanley commited on

Make Gradio app text more concise
5abc6b6

lukestanley commited on

Add assert in improvement_loop function to make more robust
4901d0f

lukestanley commited on

Assert RunPod env vars are setup before trying to use them
00af17e

lukestanley commited on

Change return type of improvement_loop to dict in app.py
859cc57

lukestanley commited on

Update allow_flagging option in Gradio interface
db708d2

lukestanley commited on

Fix Gradio textbox with placeholder
171111d

lukestanley commited on

Docs: Add local usage instructions for running the Gradio web server GUI
38a55db

lukestanley commited on

Clarify setup comments, remove unused global, increase max iterations
c995e6d

lukestanley commited on

Add JSON parsing and format output in HTML
5fb50e6

lukestanley commited on

Clarify ChillTranslator description
ca6258e

lukestanley commited on

Docs: Move sections around
47a3557

lukestanley commited on

Doc: Idea for speed improvements and intermediate results display, grouping future directions
968cab3

lukestanley commited on

Documentation changes
21ce4d4

lukestanley commited on

Add description to app
9f20b49

Luke Stanley commited on

Add cached examples
acc8b42

Luke Stanley commited on

Documentation: Add image
2dac454

Luke Stanley commited on

Documentation: Update future directions
d72193c

Luke Stanley commited on

Add HuggingFace Space demo link
03b6491

Luke Stanley commited on

Reduce max_iterations value in chill.py
6bfaa63

Luke Stanley commited on

Comment out llama-cpp-python installation command in Docker for HuggingFace Space
56e7667

Luke Stanley commited on

Switch to serverless worker by default (PR #2 from lukestanley/serverless_json_llm)
a054519
unverified

Luke Stanley commited on