-
-
Hello!
First of all, congratulations on your amazing work. I'm doing my MSc Thesis on audio classification (respiratory disease diagnosis from lung sounds). My main objective is to improve the curre…
-
Hello @justinkay,
In your paper, you mentioned that you used a 'feature alignment algorithm' to adapt the source and target features in student.
I reviewed your code, and I was wondering how can I…
-
Hello, I'm very interested in your project! However, I'm unsure about the differences between the three training stages in the `train.sh` file. Could you please explain the differences between `obj2tx…
-
I hope this email finds you well. I would like to express my gratitude for your captivating and outstanding work titled "Fine-Tuning Global Model via Data-Free Knowledge Distillation for Non-IID Feder…
-
Perform prompt engineering to ensure accuracy, minimize hallucinations, watch out for unnecessary jargon, adjust tone and level of depth to match user’s.
-
Hello. First of all, thank you for your work.
I came upon this repo when trying to improve the transcription speed in whispercpp by using a lower `audio_ctx`.
However, while fine-tuning with this …
-
Hello,
I got this error for onnx exporting.
```
Traceback (most recent call last):
File "/home/ubuntu/CAT/onnx_export.py", line 13, in
exporter = Exporter()
File "/home/ubuntu/CAT/onn…
-
I run finetuning on my server and it get error after ~300 iterations.
My run command:
```
torchrun --nproc_per_node 2 \
-m FlagEmbedding.finetune.embedder.encoder_only.m3 \
--model_name…
-
Thank you for sharing this great work! Is it ok to train with a smaller model? The model parameters are 16697987, is it ok to use half of the parameters?