Skip to content

Pull requests: databrickslabs/dolly

New pull request New
Clear current search query, filters, and sorts
0 Open 50 Closed
0 Open 50 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add prompt_templates.py to showcase reusable prompt structures
#214 by KalyanChakravarthyK was closed Mar 27, 2025 Loading…
1
Update README.md with instructions for DBR 13
#200 by edurdevic was merged Jun 24, 2023 Loading…
1
Remove DBR 12 notes in favor of 13; remove test loading data as it doesn't respect flag anyway
#193 by srowen was merged Jun 8, 2023 Loading…
Set bf16 flags correctly for a10/a100
#192 by srowen was merged Jun 7, 2023 Loading…
2
Drop duplicate torch from requirements_dev.txt
#189 by holdenk was merged Jun 5, 2023 Loading…
Allow Dolly's trainer main to be called,
#186 by holdenk was closed May 31, 2023 Loading…
1
A10 & v100 config
#182 by tnixon was merged Jun 2, 2023 Loading…
14
working V100 GPU config
#181 by tnixon was closed May 26, 2023 Loading…
38
[Fix] Move attention mask to the model device type
#180 by BaiqingL was merged May 26, 2023 Loading…
3
Add Dolly as the Input Model
#164 by xuanyuanking was merged May 16, 2023 Loading…
4
Support for Training the Model Using Local Files
#163 by xuanyuanking was closed May 15, 2023 Loading…
6
Fix documentation for max_new_tokens.
#162 by SamiKalliomaki was merged May 15, 2023 Loading…
Eight bit 12b model
#159 by densongenesys was closed May 16, 2023 Loading…
2
convert to 8 bit mode
#157 by densongenesys was closed May 11, 2023 Loading…
Note that dataset should be used from Hugging Face now
#144 by srowen was merged May 3, 2023 Loading…
@srowen
Update to Trainer.train to Allow Override Dataset
#142 by rmosleydb was merged May 3, 2023 Loading…
1
import missing datetime
#135 by opyate was closed Apr 26, 2023 Loading…
2
Drop back to deepspeed 0.8.3 because of issues with 0.9.x bug Something isn't working
#130 by srowen was merged Apr 25, 2023 Loading…
@srowen
1
Reference HF dataset by default, now that it's live enhancement New feature or request
#123 by srowen was merged Apr 21, 2023 Loading…
@srowen
Update reqs to match DBR 13; add torch enhancement New feature or request
#122 by srowen was merged Apr 21, 2023 Loading…
@srowen
Allow Alternate files to be loaded
#120 by rmosleydb was closed Apr 22, 2023 Loading…
5
Added datasets in 5 languages
#115 by Lednik7 was closed Apr 21, 2023 Loading…
4
File edits
#114 by carolyn-gronlund was closed Apr 20, 2023 Loading…
Fix reference to pythia-2.8b documentation Improvements or additions to documentation
#113 by srowen was merged Apr 20, 2023 Loading…
1
@srowen
Improve batch size guidance for other instance training documentation Improvements or additions to documentation
#106 by srowen was merged Apr 19, 2023 Loading…
@srowen
ProTip! Add no:assignee to see everything that’s not assigned.