|
Pre-training LayoutLMv2
|
|
0
|
660
|
November 16, 2021
|
|
Facebook FAISS on Databricks
|
|
2
|
656
|
July 8, 2025
|
|
Baffling performance issue on most NVidia GPUs with simple transformers + pytorch code
|
|
5
|
4602
|
April 9, 2024
|
|
Past_key_value with multiple new tokens
|
|
1
|
1377
|
August 10, 2023
|
|
502 server error when running model
|
|
3
|
5467
|
July 4, 2023
|
|
How to customize behavior of added special tokens in a pretrained tokenizer?
|
|
0
|
609
|
May 5, 2021
|
|
Deepspeed integration with Trainer in Colab crashing: TypeError: object.__init__() takes exactly one argument (the instance to initialize)
|
|
2
|
1954
|
October 1, 2023
|
|
Retraining peft model
|
|
3
|
2970
|
March 1, 2024
|
|
How to train the embedding of special token?
|
|
1
|
4174
|
October 17, 2021
|
|
Saving model per some step when using Trainer
|
|
3
|
9311
|
December 11, 2023
|
|
TextIteratorStreamer compatibility with batch processing
|
|
3
|
1482
|
December 6, 2024
|
|
You should probably TRAIN this model on a down-stream task with BertForQuestionAnswering
|
|
3
|
8270
|
November 21, 2023
|
|
Custom trainer evaluation function
|
|
0
|
2814
|
June 20, 2022
|
|
Error saving quantized model
|
|
4
|
3957
|
February 16, 2023
|
|
SAM image size for fine-tuning
|
|
5
|
6291
|
April 3, 2024
|
|
How to use SentenceTransformers for contrastive learning?
|
|
5
|
5922
|
June 30, 2022
|
|
404 when instantiating private model/tokenizer
|
|
1
|
10060
|
March 5, 2021
|
|
Fine-tuning Zero-shot models
|
|
4
|
6357
|
February 7, 2023
|
|
Transformer vs Sentence-Transformer for text classification
|
|
0
|
2446
|
March 12, 2024
|
|
Fine tuning LLM for text classification -- error with SFTTrainer
|
|
2
|
1395
|
June 3, 2025
|
|
New Project - Echo Nova
|
|
3
|
117
|
September 3, 2025
|
|
How to deal with differences between CoNLL 2003 dataset tokenisation and BER tokeniser when fine tuning NER model?
|
|
6
|
2752
|
November 23, 2021
|
|
BART - Input format
|
|
4
|
1794
|
December 13, 2023
|
|
How is CLS special token embedding initialized?
|
|
1
|
2823
|
March 16, 2022
|
|
Torchrun, trainer, dataset setup
|
|
4
|
997
|
December 20, 2024
|
|
Running huggingface-cli from script
|
|
2
|
3950
|
May 2, 2022
|
|
Resuming training BERT from scratch with run_mlm.py
|
|
2
|
2212
|
October 31, 2021
|
|
Accessing model from a callback to predict between epochs
|
|
1
|
1498
|
August 17, 2023
|
|
HTML Embedding processing
|
|
8
|
3967
|
February 13, 2022
|
|
Unable to load checkpoint after finetuning
|
|
5
|
4810
|
February 21, 2024
|
|
Stucked on "Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding."
|
|
0
|
2083
|
June 27, 2023
|
|
Conversational AI + question answering model
|
|
5
|
2676
|
January 30, 2023
|
|
Multilabel classification performance metrics using Trainer API
|
|
3
|
5763
|
September 26, 2023
|
|
Parallel/ Concurrent request with vLLM
|
|
3
|
3231
|
November 27, 2024
|
|
Remove causal mask from Llama decoder
|
|
5
|
821
|
October 22, 2024
|
|
Finding gradients in zero-shot learning
|
|
4
|
2837
|
November 17, 2020
|
|
Need help with making a Nepali-to-English Translator
|
|
0
|
354
|
November 16, 2023
|
|
Tokenization: different results when tokenizing in one pass vs sample-by-sample
|
|
3
|
1762
|
October 23, 2023
|
|
Causal masks in BERT vs. GPT2
|
|
4
|
2748
|
December 30, 2022
|
|
Downloading larger models with xet fails on macOS
|
|
3
|
931
|
June 5, 2025
|
|
Resize embeddings on Peft model
|
|
4
|
831
|
May 12, 2025
|
|
Save LORA weights only in intermediate checkpoints
|
|
0
|
1838
|
June 14, 2023
|
|
Manual splitting of model across multi-GPU setup
|
|
1
|
4100
|
December 29, 2023
|
|
Finetuning Segment Anything and automatic prediction
|
|
2
|
5837
|
June 7, 2023
|
|
DeBERTa-v3: How to keep ELECTRA-style task-head?
|
|
5
|
2283
|
January 10, 2024
|
|
Fine tuning bert on next sentence prediction task
|
|
5
|
4053
|
September 30, 2020
|
|
Pruning a model embedding matrix for memory efficiency
|
|
7
|
3494
|
July 27, 2022
|
|
Multi-Task dataset with Custom Sampler and Sharding
|
|
4
|
1382
|
August 1, 2023
|
|
[Solved] Cannot restart training from deepspeed checkpoint
|
|
3
|
2727
|
December 28, 2023
|
|
Continue Pre-Training Roberta
|
|
3
|
2724
|
May 18, 2023
|