-
i wish use batch prompt scheduler to produce same element for different image,such as a car,then inpaint different images' car . i can use a controlnet between batch prompt scheduler and the guilder,
…
-
### Checklist
- [x] 1. I have searched related issues but cannot get the expected help.
- [ ] 2. The bug has not been fixed in the latest version.
- [ ] 3. Please note that if the bug-related iss…
-
### System Info
transformers == 4.45
torch == 2.4.1 + cu118
accelerate == 1.0.1
### Who can help?
_No response_
### Information
- [ ] The official example scripts
- [ ] My own modif…
-
`trainer.py`'s `train_batch` function has a number of arguments, it would be nice if each of these had an associated type hint, eg `bool`, `int`, `EmaModel`, etc.
```python
def train_batch(
m…
-
全参微调的超参
```
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 NPROC_PER_NODE=8 swift sft \
--model_type qwen2-vl-7b-instruct \
--model_id_or_path /data/seeclick/pretrain_v3_qwen2vl/Qwen2-VL-7B-Instruct \
…
-
### System Info
python 3.10.15
torch 2.5.1
transformers 4.46.2
tokenizers 0.20.3
### Information
- [ ] The official example scripts
- [x] My own modified scripts
### 🐛 Describe the bug…
-
When I run this program at startup/login using Task Scheduler (preferred) **OR** via a batch file, the program does not show any games in the drop down window from the 'Plugins' folder; just shows a b…
-
**Expected behaviour**: I can run the `docker-compose` example and get a basic remote executor
**Actual behaviour**: I run the `docker-compose` example and get a remote cache, but not a remote execut…
-
I used orpo colab example for mistral model and I am getting this error. I am using below configs
from trl import ORPOConfig, ORPOTrainer
from unsloth import is_bfloat16_supported
orpo_trainer …
-
gmloose improved the test coverage of `slurm.py` by using snapshots of outputs of the results of the Slurm command line tools to improve tests coverage without requiring that Slurm be installed
https…