Dario Salvati

hf-dwarez's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in rl-llm-wiki/knowledge-base 4 days ago

topic: training-systems/async-and-off-policy-rl (new deep node)

2

#440 opened 4 days ago by

hf-dwarez

New activity in rl-llm-wiki/knowledge-base 10 days ago

topic: distributed-rl-training — weave in NeMo-Aligner (de-orphan #291)

2

#302 opened 10 days ago by

hf-dwarez

topic: length-bias runnable length-control check

2

#301 opened 10 days ago by

hf-dwarez

New activity in rl-llm-wiki/knowledge-base 11 days ago

topic: capability benchmarks runnable pass@k check

2

#300 opened 11 days ago by

hf-dwarez

fix: rlaif — RLAIF (2309.00267) + Self-Rewarding (2401.10020) are now in corpus (de-stale OQ/§6/§7)

2

#295 opened 11 days ago by

lvwerra

fix: dpo-variants — restore ΨPO notation + em-dashes (Unicode regressed by #297)

2

#298 opened 11 days ago by

lvwerra

topic: iterate reasoning-emergence — fold ProRL into §5 (the boundary-expansion counter-position)

2

#294 opened 11 days ago by

lvwerra

topic: win-rate runnable position-swap check

2

#299 opened 11 days ago by

hf-dwarez

topic: rl-training-stability-in-practice — weave in PPO-max (Secrets-I) + entropy mechanism

8

#292 opened 11 days ago by

hf-dwarez

topic: bon runnable selection check

2

#293 opened 11 days ago by

hf-dwarez

source: arxiv:2405.01481 — NeMo-Aligner (clean reopen of #272)

5

#291 opened 11 days ago by

hf-dwarez

topic: rollout-generation-infra — colocated resharding engine + generator layout (clean reopen of #271)

5

#290 opened 11 days ago by

hf-dwarez

meta: CONTRIBUTING — add source-frontmatter template + merge-mechanism note (kill recurring friction)

3

#287 opened 11 days ago by

lvwerra

source: arxiv:2403.14238 — Reinforcement Learning from Reflective Feedback: Aligning and Improving LLMs via Fine-Grained Self-Reflection

6

#249 opened 12 days ago by

lvwerra

source: arxiv:2405.01481 — NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment

2

#272 opened 11 days ago by

hf-dwarez

topic: rollout-generation-infra — colocated resharding engine + generator layout (verl, DeepSpeed-Chat)

2

#271 opened 12 days ago by

hf-dwarez

topic: grpo runnable group baseline check

2

#289 opened 11 days ago by

hf-dwarez

topic: distributed-rl-training — controller paradigm + weight resharding (verl, DeepSpeed-Chat)

4

#243 opened 12 days ago by

hf-dwarez

topic: distributed-rl-training — controller paradigm + weight resharding (verl, DeepSpeed-Chat) [supersedes #243]

2

#285 opened 11 days ago by

hf-dwarez

topic: iterate grpo-and-group-relative — the entropy-collapse mechanism + Clip-Cov/KL-Cov (Cui et al.)

2

#276 opened 11 days ago by

lvwerra