|
Matching alphabetic labels with indices in a fine-tuned model
|
|
1
|
183
|
October 4, 2023
|
|
Unexpected .item on an int when using accelerate HF trainer with multiple GPUs only, how to fix?
|
|
1
|
202
|
October 4, 2023
|
|
Info about insertion of "distillation_token" into the audio spectrogram transformer class
|
|
0
|
179
|
October 4, 2023
|
|
App.hf.io bad certificate
|
|
1
|
263
|
October 4, 2023
|
|
Img2img How is training and inference different from text2img
|
|
0
|
1747
|
October 4, 2023
|
|
`GPT2Tokenizer` Tokenizer handling `\n\n` differently in different settings
|
|
4
|
774
|
October 4, 2023
|
|
How to run Pytorch, huggingface pretrained DeBerta in jupyter notebook? Setup: Win11, RTX3070
|
|
4
|
792
|
October 4, 2023
|
|
Using encoder and decoder portion separately from encoder-decoder
|
|
1
|
442
|
October 4, 2023
|
|
Separate pre-trained encoder and decoder
|
|
0
|
435
|
October 4, 2023
|
|
Compatibility of transformers version 4.11.1 with Python 3.11
|
|
0
|
2071
|
October 4, 2023
|
|
How to evaluate bert model from MLM task result?
|
|
0
|
249
|
October 4, 2023
|
|
Deployment issue on Sagemaker
|
|
16
|
3280
|
October 4, 2023
|
|
Speed up beam search for item generation
|
|
1
|
934
|
October 4, 2023
|
|
ValueError: Predictions and/or references don't match the expected format
|
|
3
|
4433
|
October 4, 2023
|
|
Distributed data sampling for streaming
|
|
2
|
1730
|
October 4, 2023
|
|
Proofreader using local LLM?
|
|
0
|
1102
|
October 4, 2023
|
|
Wer is 1 when using wav2vec2pretrained model
|
|
0
|
226
|
October 4, 2023
|
|
Possibility of allowing iframe option/custom domain in the roadmap
|
|
4
|
1425
|
October 4, 2023
|
|
Help debugging diffusion model
|
|
0
|
988
|
October 4, 2023
|
|
ImportError: cannot import name 'WhisperFeatureExtractor' from 'transformers' (unknown location)
|
|
1
|
646
|
October 3, 2023
|
|
Sequence numerical clasification
|
|
1
|
895
|
October 3, 2023
|
|
Fine tuning Llama 2 walkthrough missing scripts directory error
|
|
5
|
805
|
October 3, 2023
|
|
DeBERTa - ValueError: Unable to create tensor, you should probably activate truncation and/or padding with 'padding=True' 'truncation=True' to have batched tensors with the same length
|
|
2
|
1479
|
October 3, 2023
|
|
How to add a new column to a dataset
|
|
11
|
35192
|
October 3, 2023
|
|
Shuffling and buffer size
|
|
1
|
810
|
October 3, 2023
|
|
Common voice dataset 15.0 version release
|
|
1
|
1233
|
October 3, 2023
|
|
Two text submit buttons in gr.ChatInterface to simulate a conversation
|
|
0
|
384
|
October 3, 2023
|
|
Speech to text using whisper timestamped and gradio
|
|
2
|
442
|
October 3, 2023
|
|
Evaluating on MMLU while finetuning using Trainer
|
|
0
|
789
|
October 3, 2023
|
|
# Die Revolution des Kommunikationszeitalters: Chat GPT auf Deutsch
|
|
1
|
796
|
October 3, 2023
|