-
@NielsRogge Thanks a lot for your tutorial on how to fientune SAM!
I am trying to finetune SAM for multiclass segmentation following your notebook.
Everything went fine until I create the dataload…
-
Hello,
I've ran a full finetuning on Flux using guidance_scale=1.0.
Now when I try to inference the model, I need to set the CFG scale > 1 because if I let it at 1 to disable it like I'm used t…
-
Is there an option in the codebase to do the finetuning on only selected datasets mentioned in the readme?
-
Hello, thanks for sharing this amazing work with all the codes and weights !
I created my own RGB-D dataset with custom dataloaders following #105 and ran a finetuning
My finetuning results are no…
-
I would like to format both VQA and Grounding Object detection. How should I format the dataset for finetuning ? Should I generate json like the following ?
{"query": "How many apples ?", "respon…
-
### Requested feature
Add Latex and [mathpix-markdown-it](https://github.com/Mathpix/mathpix-markdown-it) formats as available outputs
nougat uses Mathpix Markdown and it creates beautiful formula…
-
Hi there!
So we are using this model and this repository in particular for our Research on a novel problem statement and would like to fine tune on medical datasets. Can you please provide support fo…
-
Hi. I'm working on enhancing long sequence forecasting performance through finetuning. I have successfully replicated the zero-shot learning results shown in Table 22 and will use them as a baseline f…
-
**Describe the bug**
4xA100 gpu fine-tuning llama-3.1-8b-instruct (also tried llama2-13b-ms, same error), cli
```
CUDA_VISIBLE_DEVICES=0,1,2,3 \
NPROC_PER_NODE=4 \
LOCAL_WORLD_SIZE=4 \
swift…
-
Is it fine to add multiple personalities for fine tuning? Can that increase generalization of the model?