All issues

Search results

[BOUNTY CLAIM] Training guide #61

Status: Open.

#62 In RLHFlow/RLHF-Reward-Modeling;

· nikos1005 opened on Jun 7, 2026

About how to train reward model

Status: Open.

#61 In RLHFlow/RLHF-Reward-Modeling;

· weiminw opened on Jun 13, 2025

关于训练超参

Status: Open.

#60 In RLHFlow/RLHF-Reward-Modeling;

· weiminw opened on Jun 12, 2025

When do you plan to open-source the full code of the [decision_tree]?

Status: Open.

#59 In RLHFlow/RLHF-Reward-Modeling;

· Neroxsh opened on Jun 8, 2025

Scores not bounded to 0 and 1

Status: Open.

#58 In RLHFlow/RLHF-Reward-Modeling;

· mgutierrezc opened on Apr 26, 2025

How to avoid gates overly relying on one head

Status: Open.

#55 In RLHFlow/RLHF-Reward-Modeling;

· zhaoxy92 opened on Feb 11, 2025

Potential Gating Network Coding Error (on softmax) in armo-rm Stage 2

Status: Open.

#54 In RLHFlow/RLHF-Reward-Modeling;

· SWY666 opened on Jan 31, 2025

PRM Data Construct

Status: Open.

#52 In RLHFlow/RLHF-Reward-Modeling;

· Aaronhuang-778 opened on Jan 16, 2025

have trobule reproducing LLaMA-3-8B-it BT

Status: Open.

#49 In RLHFlow/RLHF-Reward-Modeling;

· jijivski opened on Jan 11, 2025

Missing code for ODIN

Status: Open.

#46 In RLHFlow/RLHF-Reward-Modeling;

· maoliyuan opened on Dec 1, 2024

Question regarding ARMO stage2-train code

Status: Open.

#37 In RLHFlow/RLHF-Reward-Modeling;

· RayWang-iat opened on Oct 15, 2024

Armo-rm env set-up and data processing

Status: Open.

#35 In RLHFlow/RLHF-Reward-Modeling;

· MaxwellJryao opened on Sep 21, 2024