|
How to convert natural languages into vec?
|
|
2
|
95
|
April 29, 2024
|
|
Negative Kl values during PPO training (TRL library)
|
|
0
|
323
|
April 28, 2024
|
|
DPOTrainer and sequence length
|
|
0
|
119
|
April 27, 2024
|
|
ValueError: attention_mask is missing in the dataloader
|
|
0
|
238
|
April 27, 2024
|
|
Training Reformer model from scratch with deepspeed - backprop error
|
|
0
|
99
|
April 26, 2024
|
|
What should I do if I want to use local dataset xsum in this project
|
|
0
|
91
|
April 26, 2024
|
|
Train T5 from scratch
|
|
4
|
3535
|
April 26, 2024
|
|
(Audio-to-audio models) Should I use 2 models sequentially or create 1 model for attempting to make a music to music model?
|
|
0
|
102
|
April 26, 2024
|
|
Does generate's max_length influence training?
|
|
0
|
102
|
April 25, 2024
|
|
Finetuned State-space/mamba model not working on huggingface model
|
|
0
|
105
|
April 25, 2024
|
|
DPOTrainer consumes lots of VRAM
|
|
0
|
206
|
April 25, 2024
|
|
Error to import transformers[torch] or accelerate -U
|
|
0
|
379
|
April 25, 2024
|
|
Prohibitively large RAM consumption on Trainer validation
|
|
2
|
1512
|
April 24, 2024
|
|
ValueError: Mixed precision training with AMP or APEX (`--fp16`) and FP16 evaluation can only be used on CUDA devices
|
|
9
|
23332
|
April 24, 2024
|
|
Multiple time fine-tuning VideoMAE model adding n class each time
|
|
0
|
93
|
April 24, 2024
|
|
How to not show the progress bar for evaluation only?
|
|
1
|
588
|
April 24, 2024
|
|
How to disable Huggingface Hub during Trainer saving of PEFT models?
|
|
2
|
613
|
April 24, 2024
|
|
Multivariate time-series transformer
|
|
0
|
172
|
April 24, 2024
|
|
Using Trainer class + 4/8 bit quantised model for prediction
|
|
0
|
233
|
April 24, 2024
|
|
Why the model loading of llama2 is so slow?
|
|
6
|
9418
|
April 24, 2024
|
|
Out of bounds Error in label conversion , two labels getting converted to 0 and 247
|
|
0
|
89
|
April 24, 2024
|
|
How to cluster words into semantic entities, when performing information extraction?
|
|
2
|
1081
|
April 23, 2024
|
|
Program hangs when creating a transformers.TrainingArguments object
|
|
2
|
427
|
April 23, 2024
|
|
Unable to open file 'model.bin' in model 'ct2fast_m2m100_418M'
|
|
1
|
1289
|
April 22, 2024
|
|
Confusing Benchmark results Running whisper on 4080 Super vs A10 vs H100
|
|
0
|
442
|
April 22, 2024
|
|
How to finetune with a own private data and then build chatbot on that?
|
|
4
|
13437
|
February 16, 2024
|
|
Conversion from finetune m2m_100 model to huggingface format
|
|
0
|
111
|
April 22, 2024
|
|
ETA for training time is 60k hours for first generation
|
|
0
|
106
|
April 22, 2024
|
|
Error after 501 steps
|
|
2
|
510
|
April 22, 2024
|
|
Issue with Optuna visualization in web browser
|
|
0
|
175
|
April 20, 2024
|