-
When I set up just the `dataset_num_proc=2` process in `DPOTrainer`, it seemed to completely pause the step of initializing the trainer map dataset, even though my dataset only had two data points and…
-
**Describe the bug**
I am trying to SFT fine-tune the model `llava-onevision-qwen2-0_5b-ov` using the following command:
```
swift sft \
--model_type llava-onevision-qwen2-0_5b-ov \
--dat…
-
Thanks for your wonderful work.
When I tried to load the dataset, an error occurred. However, the data extracting process goes well.
How to fix it?
OSError: Cannot find data file.
Original erro…
-
### Feature request
https://github.com/CarperAI/trlx
### Motivation
https://twitter.com/i/web/status/1668337702440165376
![image](https://github.com/OpenAdaptAI/OpenAdapt/assets/774615/d04…
-
首先恭喜获得best paper!!!
我这面有个疑问,我想试验一下论文中label smooth这块,但是在代码中没有发现有关label smooth的损失修改,另外也没有发现任何关于损失添加margin的代码,请问这块是没有release出来吗?
-
**This bug has re-appeared in the latest ms-swift version.**
This bug was initially reported in [this issue](https://github.com/modelscope/ms-swift/issues/1734), and was solved promptly. Now, with th…
-
### Required prerequisites
- [X] I have read the documentation .
- [X] I have searched the [Issue Tracker](https://github.com/PKU-Alignment/align-anything/issues) and [Discussions](https://github.com…
-
Hello, and Thanks for the amazing work! Very much appreciated :)
I have read the [MiniCPM-V 2 blog](https://openbmb.vercel.app/minicpm-v-2-en) and the sources you cite in the blog post, as well as …
-
### 🐛 Describe the bug
I got the following error when running supervised fine tuning of LLAMA2-7b model on P4 instance.
Command that I ran:
`deepspeed trainer_sft.py --configs llama2-7b-sft-RLAIF…
-
When creating a PEFT model and then trying to train it, we get an error;
```
File "/scratch/gpfs/ashwinee/unsloth/unsloth/kernels/fast_lora.py", line 106, in backward
d_do…