|
Read data of pdf or just image format as a part of promt
|
|
0
|
1351
|
May 29, 2023
|
|
Adding a new mask_token for BERT-like models/tokenizers
|
|
0
|
551
|
May 26, 2023
|
|
Does Trainer.train repeat streaming dataset when max_steps is not reached?
|
|
0
|
384
|
May 26, 2023
|
|
How to save model in S3 with Trainer?
|
|
5
|
5130
|
May 26, 2023
|
|
DeepSpeed Zero3 and Peft LoRA fp16 issue
|
|
3
|
3025
|
May 24, 2023
|
|
Comparing Inference Instances for Text Embedding and Completion Tasks
|
|
1
|
341
|
May 23, 2023
|
|
Creating an Instruction-to-Code model for a custom library: Strategies and Guidelines?
|
|
0
|
312
|
May 23, 2023
|
|
How can state-of-the-art classifiers be so wrong?
|
|
13
|
1639
|
May 22, 2023
|
|
Sockpuppet detector based on NLP: where to start?
|
|
0
|
214
|
May 21, 2023
|
|
Interpreting logs by the trainer
|
|
1
|
916
|
May 19, 2023
|
|
Mismatched Tokenizer and LLM leading to odd evaluation result
|
|
0
|
358
|
May 18, 2023
|
|
Continue Pre-Training Roberta
|
|
3
|
2715
|
May 18, 2023
|
|
How does DDP + huggingface Trainer handle input data?
|
|
3
|
1039
|
May 18, 2023
|
|
Timm & HuggingFace
|
|
0
|
195
|
May 16, 2023
|
|
Sampling strategies
|
|
1
|
572
|
April 4, 2023
|
|
A specific documents AI API for Hugging Face?
|
|
0
|
229
|
May 12, 2023
|
|
How to fine tune BertForSequenceClassification with PEFT?
|
|
0
|
951
|
May 10, 2023
|
|
Learning sets and disabling positional embedding knowledge?
|
|
0
|
296
|
May 10, 2023
|
|
Finetuned MT5 model generating the same first token for any input
|
|
0
|
231
|
May 9, 2023
|
|
Import HuggingFace PatentSBERTa Model support in EMR and PySpark
|
|
0
|
254
|
May 8, 2023
|
|
Machine Translation using Hugging Face problem
|
|
0
|
323
|
May 8, 2023
|
|
Using Transformers with DistributedDataParallel — any examples?
|
|
11
|
23507
|
May 8, 2023
|
|
Fine-tuning with LoRA; can't learn
|
|
0
|
1056
|
May 7, 2023
|
|
Implementing one prompt recommender
|
|
0
|
234
|
May 3, 2023
|
|
Train Roberta from scratch for custom dataset
|
|
1
|
946
|
May 2, 2023
|
|
Typical sampling decoding technique
|
|
1
|
1679
|
April 28, 2023
|
|
ValueError: Unable to generate dummy inputs for the model. Please provide a tokenizer or a preprocessor
|
|
0
|
559
|
April 28, 2023
|
|
Plotting separate loss curves for different datasets
|
|
0
|
262
|
April 28, 2023
|
|
Training large language models to consider two texts to generate output text
|
|
0
|
209
|
April 26, 2023
|
|
Generation is always CPU limited
|
|
0
|
585
|
April 21, 2023
|