Skip to content

Pull requests: CarperAI/trlx

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
Assignee
Filter by who’s assigned
Sort

Pull requests list

Faster & memory-efficient logprobs calculation
#583 opened Dec 2, 2023 by li-plus Loading…
support parallel reward function
#575 opened Oct 24, 2023 by Jingru Loading…
feat: Add support for DPO
#556 opened Sep 7, 2023 by sandeepchittilla Loading…
Inference pipeline
#555 opened Sep 4, 2023 by Dahoas Loading…
Dist ref kl
#529 opened Jul 18, 2023 by Dahoas Loading…
Implement BoN for training and eval
#528 opened Jul 18, 2023 by Dahoas Loading…
Feature: Implementing SFT mixing with PPO
#525 opened Jul 17, 2023 by Dahoas Loading…
8-bit inference (#512)
#513 opened Jun 24, 2023 by glerzing Loading…
feat: support add tokens to tokenizer.
#498 opened Jun 6, 2023 by congchan Loading…
Add Stable Vicuna Training
#487 opened May 24, 2023 by PhungVanDuy Draft
[WIP] Add Minimum Risk Trainer support
#427 opened Apr 10, 2023 by alexandremuzio Draft
4 tasks
Mistobaan/add docwebsite
#274 opened Feb 3, 2023 by Mistobaan Loading…
ProTip! Adding no:label will show everything without a label.