PICARD - Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models. PICARD is a ServiceNow Research project that was started at Element AI.
active 2023-08-15 → 2026-02-01 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 902 days from 2023-08-15 to 2026-02-01. Pushes: 0 total, peak 0 in a day. Pull requests: 7 total, peak 2 in a day. Issues: 8 total, peak 2 in a day. Comments: 10 total, peak 1 in a day. Stars: 89 total, peak 3 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 |
|---|---|---|---|---|
| dependabot[bot] | 10 | 0 | 7 | 3 |
| wosimidwa | 3 | 0 | 0 | 1 |
| kanseaveg | 2 | 0 | 0 | 2 |
| ravidborse | 2 | 0 | 0 | 1 |
| nzw0301 | 1 | 0 | 0 | 1 |
| qianmuuq | 1 | 0 | 0 | 0 |
| n14b | 1 | 0 | 0 | 0 |
| Shini1996koshy | 1 | 0 | 0 | 0 |
| learnerMa | 1 | 0 | 0 | 0 |
| hanlin1119 | 1 | 0 | 0 | 0 |
| AlexeyKrylov | 1 | 0 | 0 | 1 |
| Jessie-gjx | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#149Jessie-gjx2025-07-05 04:52Request for pretrianed picard models
- Issue#149learnerMa2025-03-16 08:29Request for pretrianed picard models
- Issue comment#144wosimidwa2025-02-09 11:29ImportError: cannot import name 'Picard' from 'picard' (unknown location)
- Issue#148wosimidwa2025-02-09 11:27Import Issue
- Issue#148wosimidwa2025-02-09 09:03Import Issue
- Issue comment#80kanseaveg2024-04-02 12:33Run prediction is so slow.
- Issue comment#80kanseaveg2024-03-30 01:16Run prediction is so slow.
- Issue#147n14b2023-11-02 04:23"Date" related natural Language query support
- Issue comment#108AlexeyKrylov2023-10-19 07:44Why didn't I use GPU during training?
- Pull request#143dependabot[bot]2023-10-18 02:48
- Issue comment#143dependabot[bot]2023-10-18 02:48Bump urllib3 from 1.26.8 to 1.26.17
- Pull request#146dependabot[bot]2023-10-18 02:48
- Pull request#141dependabot[bot]2023-10-10 20:07
- Issue comment#141dependabot[bot]2023-10-10 20:07Bump gitpython from 3.1.27 to 3.1.34
- Pull request#145dependabot[bot]2023-10-10 20:07
- Issue#144hanlin11192023-10-04 04:17ImportError: cannot import name 'Picard' from 'picard' (unknown location)
- Pull request#143dependabot[bot]2023-10-03 05:39
- Issue comment#124nzw03012023-09-29 04:50Use with LLAMA
- Issue#142qianmuuq2023-09-08 14:14model performance
- Pull request#138dependabot[bot]2023-09-06 17:54
- Issue comment#138dependabot[bot]2023-09-06 17:54Bump gitpython from 3.1.27 to 3.1.32
- Pull request#141dependabot[bot]2023-09-06 17:54
- Issue comment#140ravidborse2023-08-29 04:02"make train" stuck at Training
- Issue#140ravidborse2023-08-28 19:29"make train" stuck at Training
- Issue#139Shini1996koshy2023-08-27 15:12Any way to setup this model without docker locally in my machine
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 89 stars here means stars gained during the window, not the repo's star count.