-
### What happened + What you expected to happen
See repro.
I'm trying to load Parquet files that contain image URIs, load those images, and write the loaded images to Parquet files. To ensure that…
-
### 🔍 Before submitting the issue
- [X] I have searched among the existing issues
- [X] I am using a Python virtual environment
### 🐞 Description of the bug
I can use the code below to start flue…
-
Hi,
I am running train.py, and this line of code complains the input is a directory. `complex_names_all = read_strings_from_txt(self.split_path)`
The original code snippet, read_strings_from_t…
-
my loss curve looks something like this.
model_name: "flux-dev"
data_config:
train_batch_size: 1
num_workers: 4
img_size: 512
img_dir: xxx
report_to: wandb
train_batch_size: 1
out…
-
**Description**
The archiver should be integrated into the new architecture. To achieve this we will move the existing archivers from Operate and Tasklist to camunda-exporter, while merging them a…
-
Hello,
I am running some latency benchmarks using TensorRT-LLM on a Mistral 7B Instruct v0.3 model. My hope was that at small batch sizes the overall inference latency should not be impacted as much,…
-
### Prerequisites
- [x] I have carried out troubleshooting steps and I believe I have found a bug.
- [x] I have searched for similar bugs in both open and closed issues and cannot find a duplicate.
…
-
### Bug description
## Description
I'm training a model based on number of iterations instead of a number of epochs. The same model trains on datasets of different sizes, hence one epoch differ…
-
hi，great work，
If I only train the third stage of the i2v model with a resolution of 1024, how should I modify the relevant parameters?
tks
-
Hi Alan.
Need your Help.
I am trying to run vCheck as scheduled task. I have created the task in the scheduler to run daily. The task gets started and shows as running and never gives the output. I …