Skip to content

Pull requests: allenai/OLMo

New pull request New
35 Open 387 Closed
35 Open 387 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

mask instances with too many repetitions
#568 opened May 3, 2024 by epwalsh Loading…
2
Reverse weight decay
#567 opened May 3, 2024 by AkshitaB Loading…
1 task
4
Add OLMo 1.7-7b README + Config
#547 opened Apr 17, 2024 by 2015aroras • Draft
2
Preliminary MoE extension
#541 opened Apr 11, 2024 by Muennighoff • Draft
Add reorder cache for beam search
#526 opened Mar 26, 2024 by cshaib Loading…
2
Add scripts for Dave
#516 opened Mar 21, 2024 by epwalsh • Draft
Scripts for QKV experiments
#510 opened Mar 20, 2024 by AkshitaB Loading…
OLMo 70B official training run
#507 opened Mar 19, 2024 by epwalsh • Draft
hf_olmo: support flash attn 2
#471 opened Feb 29, 2024 by wade3han Loading…
1
Set fs_local_rank as global_rank when FS_LOCAL_RANK is not available
#456 opened Feb 18, 2024 by hxdtest Loading…
1
integrate mock vision backbone into model
#441 opened Feb 8, 2024 by epwalsh Loading…
3
Script for copying W&B runs to public projects
#435 opened Feb 5, 2024 by epwalsh • Draft
DeepSpeed
#384 opened Nov 27, 2023 by Muennighoff • Draft
2
Kebab7
#360 opened Nov 3, 2023 by dirkgr • Draft
Update Llama config to use Llama block and RoPE lower precision
#358 opened Nov 2, 2023 by 2015aroras Loading…
6
Mitchish kempner
#352 opened Oct 31, 2023 by ibeltagy Loading…
5
Llama config with a default layer norm instead of RMS for performance
#336 opened Oct 24, 2023 by dirkgr • Draft
An eval pipeline for reporting token specific perplexities
#334 opened Oct 20, 2023 by IanMagnusson • Draft
Activation logging
#330 opened Oct 12, 2023 by saurabh111233212 Loading…
@epwalsh
12
Configs for LUMI ablations
#324 opened Oct 10, 2023 by epwalsh • Draft
3 tasks
5
Improving evaluation readme
#318 opened Oct 6, 2023 by IanMagnusson • Draft
1
truncated init + bloom init
#285 opened Sep 23, 2023 by ibeltagy Loading…
5
Compiling the AMD layer norm
#284 opened Sep 22, 2023 by dirkgr • Draft
1
Script for reproducing training order for older runs
#268 opened Sep 13, 2023 by drschwenk Loading…
Add triton implementation of layer norm
status/blocked Progress can't be made because we're waiting on something outside of our control
#260 opened Sep 6, 2023 by epwalsh • Draft
2
ProTip! What’s not been updated in a month: updated:<2024-04-03.