-
**Is your feature request related to a problem? Please describe.**
With increasing parameter sizes of pre-trained models, it has become necessary to adapt parameter efficient fine-tuning methods like…
-
### Checks
- [X] This template is only for question, not feature requests or bug reports.
- [X] I have thoroughly reviewed the project documentation and read the related paper(s).
- [X] I have search…
-
Both the performance and quality are amazing. Thank you!
I have a few questions:
Is the input size of 768x512 fixed?
Are there any plans for SFT or LoRA training in the future?
-
### 🚀 The feature, motivation and pitch
I'm glad to use the vLLM framework to accelerate LLM inference. Could you provide support for the LoRA fine-tuned model of DeepSeek V2?
### Alternatives
_No …
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
Dear author, @LiheYoung , hello. The metric depth fine-tune really have baffled me these days:
I used my own datasets(sparse labels), and try to lower the lr of the pretrained model vitb or vitl…
-
When I try to fine-tune the mt5 model, I cannot obtain the 'llm-coref/mt5-coref-ontonotes' dataset. Is this a private dataset? How can I obtain it? Thank you!
-
The navmesh still allows slight walking through walls in a couple of spots. Example is right at the beginning where the two double doors stand open and you can walk through them.
This has been a k…
-
Currently if we use the `ddp` and the `fcmae` model for fine-tuning for the virtual staining tasks, there seems to be a 'memory leak'. The solution could be to expose these parameters at the `ViscyTra…
-
I adapted your fine tuning notebook to a regression task. Unfortunately the model gets unstable during training and only returns NANs as hidden states to my regression head.
Also I wanted to try ql…