Skip to content

Actions: huggingface/trl

Actions

Hugging Face Issue Labeler

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
issue_auto_labeller.yml
83 workflow runs
83 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

feat(GRPOTrainer): reward_func return None to skip Hugging Face Issue Labeler #83: Issue #2737 opened by ctjlewis
February 2, 2025 08:25 35s
February 2, 2025 08:25 35s
PLZ make padding_free for DataCollatorForChatML. Hugging Face Issue Labeler #82: Issue #2736 opened by YooSungHyun
February 2, 2025 05:44 36s
February 2, 2025 05:44 36s
SFTvsRL SFT Memorizes, RL Generalizes Hugging Face Issue Labeler #81: Issue #2735 opened by NickyDark1
February 2, 2025 03:56 22s
February 2, 2025 03:56 22s
GRPO Trainer supports VLMs Hugging Face Issue Labeler #80: Issue #2734 opened by sunildkumar
February 2, 2025 02:59 27s
February 2, 2025 02:59 27s
DPOTrainer Loss Hugging Face Issue Labeler #79: Issue #2733 opened by jeromeku
February 2, 2025 02:39 23s
February 2, 2025 02:39 23s
GKD Example why do not use labels? Hugging Face Issue Labeler #78: Issue #2732 opened by YooSungHyun
February 2, 2025 02:39 42s
February 2, 2025 02:39 42s
Latest TRL code = significantly worse rewards for GRPO training Hugging Face Issue Labeler #77: Issue #2731 opened by abacaj
February 2, 2025 01:18 24s
February 2, 2025 01:18 24s
Training Agents with GRPO Hugging Face Issue Labeler #76: Issue #2723 opened by August-murr
January 31, 2025 19:47 27s
January 31, 2025 19:47 27s
OOM for 7B model on A100 80Gb Hugging Face Issue Labeler #75: Issue #2719 opened by JohnConnor123
January 31, 2025 13:17 36s
January 31, 2025 13:17 36s
AttributeError: 'AutoModelForCausalLMWithValueHead' object has no attribute 'base_model_prefix' Hugging Face Issue Labeler #74: Issue #2718 opened by Tarak200
January 31, 2025 10:08 52s
January 31, 2025 10:08 52s
GRPO for RL on agent trajectories Hugging Face Issue Labeler #73: Issue #2715 opened by korbinian-hoermann
January 31, 2025 09:09 51s
January 31, 2025 09:09 51s
Isn't the reward *minimized* when len(completion)==20 if this is the reward function? Hugging Face Issue Labeler #72: Issue #2714 opened by cfpark00
January 31, 2025 09:03 22s
January 31, 2025 09:03 22s
GRPO with tool calling Hugging Face Issue Labeler #71: Issue #2712 opened by accupham
January 31, 2025 07:25 26s
January 31, 2025 07:25 26s
LoRA 'trainable params: 0' Hugging Face Issue Labeler #70: Issue #2711 opened by shannonruxin
January 31, 2025 04:50 28s
January 31, 2025 04:50 28s
Examples in training VDPO on llava1.6 Hugging Face Issue Labeler #69: Issue #2710 opened by lucasjinreal
January 31, 2025 04:22 42s
January 31, 2025 04:22 42s
GRPO memory bottleneck from num_generations in compute_loss Hugging Face Issue Labeler #68: Issue #2709 opened by willccbb
January 31, 2025 03:54 40s
January 31, 2025 03:54 40s
PPOTrainer + LoRA and Continued Training Hugging Face Issue Labeler #67: Issue #2707 opened by kooryan
January 30, 2025 20:19 37s
January 30, 2025 20:19 37s
Multi-GPU sampling for vLLM in GRPO Trainer Hugging Face Issue Labeler #66: Issue #2706 opened by nch0w
January 30, 2025 20:09 25s
January 30, 2025 20:09 25s
Is DataCollatorForCompletionOnlyLM encoding template form or encoding the string after template form ? Hugging Face Issue Labeler #65: Issue #2705 opened by hiteshsom
January 30, 2025 19:09 34s
January 30, 2025 19:09 34s
GRPO: Why does loss start at 0 for first K steps and then increase over time? Hugging Face Issue Labeler #64: Issue #2703 opened by arnavgarg1
January 30, 2025 18:27 28s
January 30, 2025 18:27 28s
Exposing GenerationConfig in the GRPO Trainer Hugging Face Issue Labeler #63: Issue #2702 opened by Superskyyy
January 30, 2025 18:00 28s
January 30, 2025 18:00 28s
Allow pretokenized dataset in GRPO Trainer Hugging Face Issue Labeler #62: Issue #2701 opened by Superskyyy
January 30, 2025 17:57 27s
January 30, 2025 17:57 27s
GRPO VLLM does not work with Lora Hugging Face Issue Labeler #61: Issue #2698 opened by gagan3012
January 30, 2025 16:03 44s
January 30, 2025 16:03 44s
I cannot launch PPOTrainning script with accelerate launch Hugging Face Issue Labeler #60: Issue #2696 opened by daehuikim
January 30, 2025 15:38 30s
January 30, 2025 15:38 30s
OOM 8xH100 using latest GRPO code with vLLM Hugging Face Issue Labeler #59: Issue #2688 opened by abacaj
January 30, 2025 05:55 31s
January 30, 2025 05:55 31s