-
Hi, I'm training a model (essentially copied from https://huggingface.co/blog/unsloth-trl#unsloth--trl-integration):
```python
import torch
from trl import SFTTrainer
from transformers import Tr…
-
Paddle版本：
```
python -c "import paddle; print(paddle.version.commit)"
CustomDevice: npu, visible devices count: 2
2ef8abae65f11fa3cdae784b4ac58750e0fa3bbb
```
CANN版本：`8.0.RC1`
操作系统版本：`Ubun…
yimuu updated
3 months ago
-
thank you very much for your MFM !!!
when i run (bash dist_finetune.sh ...) , get error
how can i run (bash dist_finetune.sh ...) with only 1 gpu , not multi gpu ?
```
/opt/conda/envs/py3.9_cu…
-
### 🐛 bug 说明
**使用指令**
CUDA_VISIBLE_DEVICES=2,3 accelerate launch --num_processes 2 path_to_train_m3e.py path_to_model path_to_dataset \
--output-dir output_dir
**报错信息**
…
-
**Describe the feature**
没有使用swift进行微调，自己进行lora训练后的模型权重如何在swift中如何加载、合并、导出？
**Paste any useful information**
参考[Qwen2.5-7B-Instruct Lora 微调](https://github.com/datawhalechina/self-llm/blob/master…
-
### Describe the bug
On default settings provided in flux train example readme, with 10 validation images training will error out with out of memory error during validation. on A100 80GB
```
…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### System Info
pass
### Reproduction
```
CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7" accelerate launch \
--config_fil…
-
RuntimeError: Error(s) in loading state_dict for PeftModelForCausalLM:
size mismatch for base_model.model.model.embed_tokens.weight: copying a param with shape torch.Size([32001, 4096]) from …
-
Hello, Ashwinee Panda
I was very impressed with your work and wanted to thank you for the excellent contribution. I am currently following the tutorial using the openbookqa task to finally experime…
-
- 环境：
- WLS-2，Ubuntu22.04， 4090 GPU x1
- train_sft.sh
```bash
CUDA_VISIBLE_DEVICES=0 python dbgpt_hub/train/sft_train.py \
--model_name_or_path $model_name_or_path \
--quantizati…