Skip to content

[Feat] Add Reward Server examples#16

Merged
Jayce-Ping merged 6 commits into
mainfrom
reward_server
Jan 24, 2026
Merged

[Feat] Add Reward Server examples#16
Jayce-Ping merged 6 commits into
mainfrom
reward_server

Conversation

@Jayce-Ping

Copy link
Copy Markdown
Collaborator

No description provided.

@Jayce-Ping Jayce-Ping merged commit 56b6930 into main Jan 24, 2026
@Jayce-Ping Jayce-Ping deleted the reward_server branch January 24, 2026 03:43
Jayce-Ping added a commit that referenced this pull request Jun 14, 2026
Resync .agents/, .cursor/, guidance/, AGENTS.md and CLAUDE.md with the
current code after plugin growth (9 trainers, 14 model adapters, 13 reward
models). Fixes registry drift, wrong config/API facts and broken
cross-references found in a full audit.

- architecture.md/AGENTS.md: add diffusion-opd trainer, clap/imagebind/
  geneval rewards, Bagel/LTX2 models; fix RationalRewards* class names
- constraints.md: evaluate() is concrete (not abstract); index #28-29;
  paradigm (#7) and training-args (#16) lists; de-numbered line refs
- philosophy.md: Accelerate (DDP/DeepSpeed ZeRO-1-2/FSDP) backend; fix #27 ref
- guidance: scheduler.* config keys, real sample()/compute_advantages
  snippets, GenEval metadata convention, audio reward param, Bagel link
- skills: model_name_or_path, default_target_modules, data.datasets,
  rewards-as-list, 9 trainers; CLAUDE.md imports AGENTS.md to avoid drift
- topics/samplers.md: correct _resolve_sampler_type + AdvantageProcessor
  group_distributed paths; parity_testing set_scheduler_timesteps
- hparams/model_args.py: model_type Literal now matches registry keys

Co-authored-by: Cursor <cursoragent@cursor.com>
Jayce-Ping added a commit to Jayce-Ping/Flow-Factory-Private that referenced this pull request Jul 2, 2026
* Add remote reward server examples

* Update guidance
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant