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
190 workflow runs
190 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Directory not empty error in checkpointing Hugging Face Issue Labeler #190: Issue #2928 opened by mehdiataei
February 21, 2025 23:24 32s
February 21, 2025 23:24 32s
Is there any problem with GRPOtrainer’s memory usage? Hugging Face Issue Labeler #189: Issue #2927 opened by Tuziking
February 21, 2025 17:11 48s
February 21, 2025 17:11 48s
There is miscaculated attention mask shape in comment in GRPO trainer. Hugging Face Issue Labeler #188: Issue #2924 opened by linkedlist771
February 21, 2025 15:25 36s
February 21, 2025 15:25 36s
NCCL timeout when GRPO training with vllm Hugging Face Issue Labeler #187: Issue #2923 opened by edwardzjl
February 21, 2025 09:26 39s
February 21, 2025 09:26 39s
How to support multi-device VLLM inference in the GRPO Trainer Hugging Face Issue Labeler #186: Issue #2922 opened by 0x404
February 21, 2025 09:24 40s
February 21, 2025 09:24 40s
simple question: SFTTrainer ValueError Hugging Face Issue Labeler #185: Issue #2920 opened by jbw3016
February 21, 2025 02:11 30s
February 21, 2025 02:11 30s
Fine tuning "thinking"/"reasoning" models Hugging Face Issue Labeler #184: Issue #2919 opened by GhostDog98
February 21, 2025 00:47 35s
February 21, 2025 00:47 35s
GRPO from VLM models? Hugging Face Issue Labeler #183: Issue #2917 opened by dipta007
February 20, 2025 19:10 32s
February 20, 2025 19:10 32s
I want to solve this issue: ValueError: Unable to create tensor Hugging Face Issue Labeler #182: Issue #2916 opened by jbw3016
February 20, 2025 17:09 37s
February 20, 2025 17:09 37s
SFTTrainer: Why do we always switch to chatML? Hugging Face Issue Labeler #181: Issue #2915 opened by jbw3016
February 20, 2025 15:42 28s
February 20, 2025 15:42 28s
Clarification on KL Divergence Computation in GRPOTrainer Hugging Face Issue Labeler #180: Issue #2914 opened by zhaopku
February 20, 2025 14:02 34s
February 20, 2025 14:02 34s
How to specify the GPU used by vllm Hugging Face Issue Labeler #179: Issue #2913 opened by xiaolizh1
February 20, 2025 10:32 40s
February 20, 2025 10:32 40s
Getting an error while using a PEFT model as a reward model in PPO training. Hugging Face Issue Labeler #178: Issue #2911 opened by Tarak200
February 20, 2025 06:58 31s
February 20, 2025 06:58 31s
L447 of GRPO trainer 'num_return_sequences=self.num_generations' Hugging Face Issue Labeler #177: Issue #2910 opened by zhengqigao
February 20, 2025 01:57 26s
February 20, 2025 01:57 26s
Cannot import name 'shard_checkpoint' (possibly deprecated in transformers) Hugging Face Issue Labeler #176: Issue #2909 opened by anshuln2
February 20, 2025 00:20 37s
February 20, 2025 00:20 37s
GRPO: Enable updating the reference model for KL divergence penalty calculation Hugging Face Issue Labeler #175: Issue #2908 opened by ko-redtruck
February 19, 2025 21:03 28s
February 19, 2025 21:03 28s
DPOTrainer loss goes down to 0.0 while at the end it reports the train_loss is 0.15 - the loss during training and at end differs substantially Hugging Face Issue Labeler #174: Issue #2907 opened by KemalDrop
February 19, 2025 20:37 43s
February 19, 2025 20:37 43s
What‘s the GRPOTrainer's error 浮点数例外(吐核) Hugging Face Issue Labeler #173: Issue #2906 opened by Tuziking
February 19, 2025 15:16 52s
February 19, 2025 15:16 52s
How to use GRPOTrainer to train a LLM for code generation? What is the format of the dataset? Hugging Face Issue Labeler #172: Issue #2905 opened by xiangxinhello
February 19, 2025 12:38 19s
February 19, 2025 12:38 19s
Save memory when layers are shared with ref model? Hugging Face Issue Labeler #171: Issue #2904 opened by raphael-sch
February 19, 2025 10:58 37s
February 19, 2025 10:58 37s
Is mini-batch updates implemented in GRPO of trl ? Hugging Face Issue Labeler #170: Issue #2903 opened by jackfsuia
February 19, 2025 09:01 34s
February 19, 2025 09:01 34s
GRPO completions skip special tokens ? Hugging Face Issue Labeler #169: Issue #2897 opened by MohamedAliRashad
February 18, 2025 19:51 29s
February 18, 2025 19:51 29s
RuntimeError: q must have shape (batch_size, seqlen_q, num_heads, head_size) Hugging Face Issue Labeler #168: Issue #2896 opened by MohamedAliRashad
February 18, 2025 16:15 32s
February 18, 2025 16:15 32s
Stop at eos_token for sampling in online algorithms Hugging Face Issue Labeler #167: Issue #2892 opened by haoxiongliu
February 18, 2025 13:26 35s
February 18, 2025 13:26 35s
[Qwen2.5] LoRA with SFT seems to be stuck forever with DeepSpeed Hugging Face Issue Labeler #166: Issue #2891 opened by sayakpaul
February 18, 2025 12:17 44s
February 18, 2025 12:17 44s