Different generations during test time and validation time
|
|
0
|
166
|
August 9, 2023
|
After fine tuning, saving and reloading the model, he is "forgetting" fine tuning
|
|
0
|
810
|
August 9, 2023
|
MusicGen Audio Prompt, need help
|
|
0
|
265
|
August 9, 2023
|
[Blenderbot] Getting runtime error while using generate
|
|
3
|
3762
|
August 8, 2023
|
Error on later checkpoint when doing generation using TextGenerationPipeline
|
|
1
|
929
|
August 8, 2023
|
Why i can't use EarlyStoppingCallback and load_best_model_at_end=False
|
|
0
|
714
|
August 8, 2023
|
Keras callback error and model config 'NoneType' after training
|
|
1
|
417
|
August 8, 2023
|
Slow Tokenizer adds whitespace after special token
|
|
4
|
1411
|
August 8, 2023
|
Running generate while evaluating test set?
|
|
0
|
195
|
August 8, 2023
|
How to add java_home in HF space(spark + llama)
|
|
0
|
367
|
August 8, 2023
|
BioGPT error with right padding
|
|
0
|
577
|
August 7, 2023
|
Saving Checkpoint on S3 using Trainer
|
|
0
|
781
|
August 7, 2023
|
Loading finetuned model to generate text
|
|
12
|
3325
|
August 7, 2023
|
Importing TrainingArguments gives error
|
|
2
|
2509
|
August 7, 2023
|
Tensor size error in PEFT(Prefix Tuning)
|
|
5
|
1558
|
August 7, 2023
|
Closest model available to OpenAI's codex/ GitHub Copilot for code completion
|
|
6
|
7727
|
August 7, 2023
|
ZeRO uses more RAM than DDP?
|
|
0
|
1062
|
August 7, 2023
|
Fintune whisper model returns exclamation marks
|
|
1
|
566
|
August 7, 2023
|
Confusion of token id in tokenizer and model
|
|
0
|
225
|
August 6, 2023
|
Tokenizer progress bar
|
|
2
|
3811
|
August 6, 2023
|
Why is that I am not getting the full file path; thus unable to play the audio file
|
|
0
|
464
|
August 6, 2023
|
Freeze Deberta Layers
|
|
0
|
493
|
August 5, 2023
|
Eval_pred vs. EvalPrediction confusion
|
|
0
|
881
|
August 5, 2023
|
Vision Transformer, can I put a multi-task classifier on it for fine-tuning?
|
|
0
|
639
|
August 5, 2023
|
How to set generation parameters for transformers.pipeline?
|
|
4
|
12579
|
August 4, 2023
|
Transformers for GPT 4
|
|
1
|
1866
|
August 4, 2023
|
How to use an unsupported Beam Search decoder in ASR Pipeline?
|
|
0
|
550
|
August 4, 2023
|
Eval_batch_size VS per_device_eval_batch_size
|
|
0
|
911
|
August 4, 2023
|
Is there a way to use object detect model DETR to mark different sizes of stones in a image/video?
|
|
0
|
212
|
August 4, 2023
|
KeyError when loading any dinov2 model
|
|
1
|
3107
|
August 4, 2023
|