-
I'm encountering a KeyError when trying to train Phi-3 using the unsloth library. The error occurs during the generation step with model.generate. Below are the details of the code and the error trace…
-
mpirun python3 scripts/image_sample.py \
--image_size 32 --timestep_respacing 100 \
--model_path PATH_TO_CHECKPOINT \
--num_channels 128 --num_head_channels 32 --num_res_blocks 3 --attention_resol…
-
Is it just a matter of modifying the ldm/modules/attention.py,ldm/modules/embedding_manager.py ldm/modules/encoders/modules.py, ldm/models/diffusion/ddpm.py . Help is desperately needed, thanks!
BBABM updated
8 hours ago
-
@LiheYoung hi so i am loving the eork u guys are doing and the current v2 models are amazing the only problem im having is the metric models u just released thre is a big problem i have the map res at…
-
I have trained a simple DDPO model (5 epochs) at 'Nguyen17/my_DDPO'
But when I use to generate images, i found this error:
ValueError: Cannot load from /root/.cache/huggingface/hub/models--Nguye…
-
**Description**
Hi Team,
I tried to config my ensemble model with reshape : https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/user_guide/model_configuration.html#resha…
-
# 问题
转换完权重之后进行评估验证时出现下述问题
```shell
> number of parameters on (tensor, pipeline) model parallel rank (0, 0): 630167424
loading release checkpoint from /raid/LLM_train/Pai-Megatron-Patch/checkpoint…
-
### Describe the issue
I exported my medium Whisper model correctly. It could run the inference with the correct answer. After that, I optimized my model. I ran the command line: `python -m onnxrunti…
-
Error occurred when executing DownloadAndLoadFlorence2Model:
No module named 'flash_attn_2_cuda'
the error happens with all precision settings and all attention settings
(The model is: Floren…
-
getting this long error
/usr/local/lib/python3.10/dist-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please …