lyb

where is the coco segmentation vqgan pre-train model

2

when generation segmentation to image i can't find this file **"ckpt_path: logs/2020-11-07T00-08-54_cocostuffthings_vqvae_segmentation_bce/checkpoints/last.ckpt"**

[BUG] <title>合并lora权重时遇到AttributeError: 'QWenTokenizer' object has no attribute 'IMAGE_ST'问题

9

### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答？ | Is there an...

flash-attn error flash_attn_2_cuda.cpython-311-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE

3

My environment is as follows： nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2023 NVIDIA Corporation Built on Wed_Nov_22_10:17:15_PST_2023 Cuda compilation tools, release 12.3, V12.3.107 Build cuda_12.3.r12.3/compiler.33567101_0 torch==2.3.0 how to...

请问modelscope的数据集部分可以添加上LLM的预训练，指令微调，奖励模型分类吗

1

**Describe the feature** Features description **Motivation** A clear and concise description of the motivation of the feature. Ex1. It is inconvenient when [....]. Ex2. There is a recent paper [....],...

单机多卡sft deepspeed zero3 训练一直卡在训练阶段

1

  一致卡在0，但是显存利用率是满的，不知道为啥

### Is your feature request related to a problem? Please describe. Traceback (most recent call last): File "/home/ansible/online/operator/autovision-notebook-cfs/code_base/minimind/eval_model.py", line 202, in main() File "/home/ansible/online/operator/autovision-notebook-cfs/code_base/minimind/eval_model.py", line 182, in main generated_ids =...