-
Hi, @TaoShuchang
Thank you for the wonderful work.
Are there any plans to open-source the SFT models in step1?
-
Exciting to read this work. I'm curious about why SFT for all parameters is chosen in the paper instead of existing PEFT methods like LoRA series. I would like to know if you have tried and evaluate…
-
Dear Dr. Li
The work of StarGLM has inspired me a lot. What kind of fine-tuning method is this based on?
-
Fluxgym asks for ae.sft but I have only ae.safetensors. Do I have to keep manually modifying the text in the GUI everytime renaming "sft" to "safetensors"?
-
In the README file, I only found instructions on how to set the image size during inference, but how do I set the image resolution during SFT with LLamA-Factory?
-
请问多图sft应该如何组织输入,这个示例中的第一个对应第一张图,第二个对应第二张图吗?
-
### Feature request
Extend the `sft_vlm.py` script to support the new Molmo models from AllenAI: https://huggingface.co/collections/allenai/molmo-66f379e6fe3b8ef090a8ca19
Paper: https://arxiv.org/…
-
Hi,
Firstly, I would like to express my appreciation for the outstanding work on your project. It's truly inspiring.
I am currently interested in applying SFT to a custom speaker. Could you plea…
-
hello, nice work. could share the sft-dataset in hf?
-
We met an error:
`[2024-09-23 11:13:54,886] [INFO] [launch.py:315:sigkill_handler] Killing subprocess 123969
[2024-09-23 11:13:54,887] [ERROR] [launch.py:321:sigkill_handler] `
with with return co…