Repository Issue Activity (beta)

#356 请求更新Qwen3-vl系列的模型

#280 为什么completion_length越训越短

#353 ImportError: cannot import name 'Glm4vForConditionalGeneration' from 'transformers'

#357 加载refcoco 时发生 AssertionError

#160 run lora train: IndexError: pop from an empty deque

#355 Fix performance overhead caused by incorrect indentation in image resizing logic

#245 Total trainable parameter: 0

#298 Question about some details of training

#338 Miss AutoModelForCausalLM

#350 请问多久可以支持Qwen3-VL

#354 multi-image training in GRPO

#352 Agent memory integration

#351 加载internvl模型报错

#317 There may be bug in multi-image mode.

#342 GUI task multi-image training

#337 8 3090 GPU LORA OOM issue

#161 RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

#63 E0225 torch/distributed/elastic/multiprocessing/api.py:826] failed (exitcode: 1)；torch.distributed.elastic.multiprocessing.errors.ChildFailedError

#164 Memory usage keeps increasing during training

#242 AutoModelForCausalLM Bug: ValueError: Unrecognized configuration class <class 'transformers.models.qwen2_5_vl.configuration_qwen2_5_vl.Qwen2_5_VLConfig'> for this kind of AutoModel: AutoModelForCausalLM.

#348 您好，能够提供一下具体的，可直接运行的ovd任务的训练脚本？感谢。

#140 About LoRa Resume Training

#295 Lisa test is invalid.

#220 bug when using run_grpo_rec_internVL.sh

#346 NaN or Inf found in input tensor when using LLaMA-Factory to train the SFT model for REC task.