Integrating Semantic Wisdom with Predictive Models
active 2024-02-02 → 2025-04-03 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 428 days from 2024-02-02 to 2025-07-20. Pushes: 164 total, peak 48 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 14 total, peak 6 in a day. Comments: 15 total, peak 4 in a day. Stars: 17 total, peak 2 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| furlat | 186 | 157 | 2 | 13 |
| danielpatrickhug | 7 | 7 | 0 | 0 |
| pszemraj | 2 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#7furlat2024-03-21 17:33make some tests and choose an openai api compatible local llm server
- Issue comment#2furlat2024-03-16 00:06add a logger
- Issue comment#4furlat2024-03-12 00:37Add llm and embeddings support for together api
- Issue#15furlat2024-03-05 15:54add multi-task and multi-class support for classification
- Issue comment#7furlat2024-03-01 20:02make some tests and choose an openai api compatible local llm server
- Issue comment#14furlat2024-03-01 20:01Add a way to globally define the cache and output folders
- Issue comment#6furlat2024-02-28 10:50add automatic batch job re-queue for failed pydantic validations in column generation with re-prompting following instructor
- Issue comment#4pszemraj2024-02-27 18:41Add llm and embeddings support for together api
- Issue comment#3pszemraj2024-02-27 17:19add support for local embeddings with hf transformers
- Issue comment#4furlat2024-02-26 17:03Add llm and embeddings support for together api
- Issue#14furlat2024-02-24 18:42Add a way to globally define the cache and output folders
- Issue comment#13furlat2024-02-24 13:45Make all of cross-validation but the model training a lazy polars operation
- Issue#13furlat2024-02-24 13:45Make all of cross-validation but the model training a lazy polars operation
- Issue comment#2furlat2024-02-24 13:29add a logger
- Issue#12furlat2024-02-24 13:26Start working on distributed framework
- Issue comment#1furlat2024-02-24 13:14Move oai embeddings to work with asynclient and json cache and autobatching
- Issue comment#1furlat2024-02-24 13:13Move oai embeddings to work with asynclient and json cache and autobatching
- Pull request#11furlat2024-02-24 09:35
- Pull request#11furlat2024-02-24 09:33
- Issue comment#7furlat2024-02-23 18:22make some tests and choose an openai api compatible local llm server
- Issue#10furlat2024-02-20 16:59add possibility to do multiple structured pydantic extractions at higher temperature and ensemble results
- Issue comment#7furlat2024-02-20 10:45make some tests and choose an openai api compatible local llm server
- Issue#9furlat2024-02-18 22:13rewrite numpy features creation to be effiecient in the loop
- Issue#8furlat2024-02-16 13:09make a general clean of pl.utf8 columns that are supposed to be enums
- Issue#7furlat2024-02-12 01:49make some tests an choose an openai api compatible local llm server
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 17 stars here means stars gained during the window, not the repo's star count.