|
Training Fails after multiple passes: ValueError: The model did not return a loss from the inputs
|
|
3
|
4268
|
December 9, 2023
|
|
How can you delete BERT Layers after Finetuning
|
|
0
|
1493
|
April 30, 2021
|
|
Classification Problem - Which class of Hugging Face LLM models should I try?
|
|
2
|
4839
|
September 3, 2023
|
|
CPU Optimization PyTorch Strategies
|
|
1
|
588
|
February 1, 2022
|
|
T5 outperforms BART when fine-tuned for summarization task
|
|
3
|
3988
|
August 8, 2022
|
|
Cant reproduce Optuna results
|
|
3
|
2242
|
January 17, 2022
|
|
Is it possible to add simple custom pytorch-crf layer on top of TokenClassification model. It will make the model more robust
|
|
4
|
3549
|
April 19, 2023
|
|
Different results from checkpoint evaluation when loading fine-tuned LLM model
|
|
5
|
3224
|
September 22, 2023
|
|
Difference between model.generate() and model() outputs
|
|
2
|
2570
|
March 3, 2024
|
|
Streaming Dataset of Sequence Length 2048
|
|
7
|
2783
|
May 12, 2022
|
|
Facebook FAISS on Databricks
|
|
1
|
549
|
January 23, 2025
|
|
Loading an LoRA adapter trained on quantized model on a non-quantized model
|
|
0
|
1365
|
November 7, 2023
|
|
Pre-training a BERT model from scratch with custom tokenizer
|
|
5
|
3076
|
January 11, 2022
|
|
LLM or NLP project idea for final year
|
|
1
|
939
|
February 18, 2025
|
|
Can Q&A model say "I don't know"
|
|
8
|
2439
|
September 14, 2022
|
|
Pretraining ALBERT
|
|
2
|
1335
|
February 16, 2022
|
|
Saving weights and checkpoints
|
|
3
|
3616
|
April 14, 2022
|
|
Encoding/decoding NLP model in tensorflow lite (fine-tuned GPT2)
|
|
3
|
1130
|
September 21, 2024
|
|
Fine-tuning ViT with more patches/higher resolution
|
|
3
|
3568
|
December 26, 2022
|
|
BERT finetuning "index out of range in self"
|
|
2
|
4114
|
August 24, 2021
|
|
Why is uploaded model twice the size of actual model?
|
|
6
|
2677
|
June 12, 2022
|
|
Scaling up BERT-like model Inference on modern CPU - Part 1
|
|
3
|
1115
|
April 22, 2021
|
|
Trying to understand XForSequenceClassification heads
|
|
8
|
1319
|
September 24, 2020
|
|
Based on HF documentation, unnaswerable questions from Squad 2.0 don't make it into train/val data
|
|
4
|
973
|
December 3, 2020
|
|
Running Optuna on Two HuggingFace Trainer Tasks
|
|
5
|
1570
|
October 7, 2022
|
|
Finetune Donut with new tokenizer
|
|
6
|
2531
|
October 10, 2023
|
|
How to give equal importance of all labels while dealing with unbalanced samples
|
|
4
|
2942
|
January 28, 2022
|
|
How to create the fsdp_config json file for Trainer?
|
|
4
|
2855
|
June 19, 2023
|
|
ZeRO 2 and 3 with Tensor Parallelism
|
|
0
|
1123
|
July 3, 2022
|
|
Finetuning classification model with new labels
|
|
0
|
1121
|
June 23, 2022
|
|
Resize embeddings on Peft model
|
|
4
|
502
|
May 12, 2025
|
|
12% into epoch training loss drops to 0.0
|
|
2
|
641
|
March 6, 2024
|
|
Way to fine tune pre trained model & get the embeddings
|
|
2
|
3530
|
May 28, 2024
|
|
Online learning in a 🤗 Space
|
|
2
|
626
|
December 1, 2021
|
|
Performing Back Translation with T5 network
|
|
4
|
1521
|
August 1, 2020
|
|
Extract most important words from model
|
|
3
|
3019
|
February 6, 2023
|
|
Weights and biases not showing train loss correctly
|
|
2
|
1096
|
December 7, 2021
|
|
Continue pre-training BERT
|
|
5
|
2449
|
November 13, 2023
|
|
DeepSpeed Zero3 and Peft LoRA fp16 issue
|
|
3
|
2973
|
May 24, 2023
|
|
Chatbot PDF - Only local
|
|
1
|
1318
|
April 21, 2024
|
|
Clm repeats tokenization when distributed
|
|
5
|
1307
|
July 15, 2022
|
|
Fine tune vocab size of pre-trained Causal Language Model
|
|
2
|
1837
|
October 17, 2022
|
|
PEFT fine-tuning as slow as full model fine-tuning
|
|
3
|
1584
|
December 6, 2023
|
|
Teaming Up for Kaggle NLP Competitions
|
|
7
|
1104
|
May 9, 2022
|
|
Calculate the probability of a given sequence for a seq2seq model
|
|
0
|
978
|
April 22, 2022
|
|
Onnx Errors pipeline_name ='question-answering'
|
|
5
|
2210
|
February 28, 2022
|
|
TPU trainer with multi-core
|
|
5
|
2193
|
April 21, 2022
|
|
Huggingface on Databricks
|
|
0
|
954
|
November 12, 2021
|
|
Finetuning T5 for multi class classification
|
|
0
|
945
|
January 6, 2022
|
|
Improving Zero-shot accuracy
|
|
0
|
943
|
March 31, 2022
|