|
Hosting own model on hugging face
|
|
0
|
142
|
February 27, 2024
|
|
AttributeError: module 'PIL.Image' has no attribute 'ANTIALIAS'
|
|
0
|
775
|
February 27, 2024
|
|
Premature story/conversation end by Mistral-7b-Instruct
|
|
0
|
419
|
February 26, 2024
|
|
Google/pegasus-xsum for summerization is very slow
|
|
2
|
209
|
February 26, 2024
|
|
Train model from scratch on own dataset
|
|
0
|
583
|
February 26, 2024
|
|
Fine-tuned Llama2 model for text classification generating new instances
|
|
0
|
1419
|
February 26, 2024
|
|
Mixtral batch inference or in general fast inference
|
|
2
|
4059
|
February 26, 2024
|
|
How to translate japanese voice into english subtitle filewith fast-whisper
|
|
1
|
1175
|
February 26, 2024
|
|
ValueError: expected sequence of length 25 at dim 1 (got 43)
|
|
1
|
261
|
February 26, 2024
|
|
Can I call prepare() separately on multiple models or should it be a single call?
|
|
0
|
202
|
February 26, 2024
|
|
How is loss and eval_loss calculated?
|
|
0
|
196
|
February 26, 2024
|
|
Problems running a whisper model locally on a mac
|
|
1
|
460
|
February 26, 2024
|
|
Pipeline not using GPU
|
|
0
|
1550
|
February 26, 2024
|
|
Multi-gpu training does not optimize as expected
|
|
1
|
458
|
February 26, 2024
|
|
Training using multiple GPUs
|
|
20
|
20147
|
February 25, 2024
|
|
Fine-tune summarization never works well
|
|
0
|
246
|
February 25, 2024
|
|
Why BPE encoding trained on English and applied on Bengali doesnot return unknown tokens?
|
|
1
|
328
|
February 25, 2024
|
|
Korean finetuning on Whisper
|
|
1
|
1651
|
February 25, 2024
|
|
Starting a project and wanting "in" on the community
|
|
0
|
176
|
February 25, 2024
|
|
Password authentication error when using a SSH key, for git clone
|
|
1
|
1736
|
February 25, 2024
|
|
3 Burning Questions About Real-World Model Use Cases, Model Selection, and Mac Compatibility
|
|
1
|
297
|
February 25, 2024
|
|
Use case for work
|
|
0
|
72
|
February 25, 2024
|
|
How to invoke model.predict on this
|
|
1
|
344
|
February 25, 2024
|
|
How to restrict Trainer to use certain GPUs?
|
|
2
|
538
|
February 25, 2024
|
|
Local computation
|
|
0
|
95
|
February 24, 2024
|
|
How to represent old vs new data?
|
|
0
|
73
|
February 24, 2024
|
|
Help with custom handler.py for model inference endpoint
|
|
1
|
751
|
February 24, 2024
|
|
DDP gradient checkpoint crashes
|
|
4
|
3517
|
February 24, 2024
|
|
How to find the path of a model?
|
|
4
|
1950
|
February 23, 2024
|
|
Starcoder: CUDA out of memory
|
|
4
|
444
|
February 23, 2024
|