|
Using map take 7,2x times longer than set_transform
|
|
0
|
191
|
November 15, 2023
|
|
HuggingFace transformers BERT for classification: dimensionality of output with classification layer is expected to be 1, but is 512 instead
|
|
1
|
1297
|
November 14, 2023
|
|
Meaning of loss for timeseries transformers/Informer/Autoformer
|
|
0
|
206
|
November 14, 2023
|
|
Unable to prepare model for kbit training
|
|
2
|
2414
|
November 14, 2023
|
|
RuntimeError: a leaf Variable that requires grad is being used in an in-place operation
|
|
4
|
1488
|
November 14, 2023
|
|
How does summarization work with pretrained models?
|
|
0
|
596
|
November 14, 2023
|
|
Deploying model.safetensors to kotlin
|
|
0
|
344
|
November 14, 2023
|
|
ValueError: You have to specify either decoder_input_ids or decoder_inputs_embeds
|
|
3
|
1809
|
November 14, 2023
|
|
Create a custom tokenizer from a dictionary
|
|
0
|
313
|
November 13, 2023
|
|
Model.generate generates same output for different inputs
|
|
1
|
623
|
November 13, 2023
|
|
Error replicating training a TensorFlow model with Keras
|
|
3
|
2163
|
November 13, 2023
|
|
Get the predictions using DataCollator For Completion OnlyLM after fine-tuning Llama2 using SFT trainer
|
|
0
|
526
|
November 13, 2023
|
|
The same hyperparameters with deepspeed is worse than without deepseepd
|
|
2
|
447
|
November 13, 2023
|
|
Resume_from_checkpoints leads to RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0!
|
|
4
|
713
|
November 13, 2023
|
|
Provide alternative translations on click
|
|
0
|
171
|
November 13, 2023
|
|
Is attention_mask implemented correctly in BERT?
|
|
2
|
2598
|
November 12, 2023
|
|
Does all masking during training take place in data_collator.py?
|
|
0
|
118
|
November 11, 2023
|
|
Answer template generation from question
|
|
0
|
211
|
November 11, 2023
|
|
Packing issue, SFTTrainer
|
|
0
|
330
|
November 10, 2023
|
|
Translator-model stops in the middle of the text
|
|
0
|
139
|
November 10, 2023
|
|
Trainer Loads old TrainingArguments
|
|
0
|
120
|
November 10, 2023
|
|
Calling the model after registering it with automodel.register
|
|
0
|
178
|
November 10, 2023
|
|
Constrain generation to a pre-defined vocabulary
|
|
0
|
436
|
September 4, 2023
|
|
Setting max_steps with IterableDataset still errors
|
|
4
|
1117
|
November 10, 2023
|
|
Resume_from_checkpoint & skipping batches, why does the processing function need to be run for skipped batches?
|
|
7
|
3528
|
May 15, 2023
|
|
How Can I use cashed models from HuggingFace?
|
|
0
|
235
|
November 9, 2023
|
|
Cannot reproduce the BAAI/bge-reranker-large re-ranker model results
|
|
0
|
393
|
November 9, 2023
|
|
LED Config default encoder and decoder layers
|
|
0
|
118
|
November 9, 2023
|
|
Getting this error during creating space for ChatUI using docker
|
|
1
|
228
|
November 9, 2023
|
|
Looking for help converting transformers to ONNX with HF Optimum
|
|
0
|
278
|
November 9, 2023
|