|
Batch generation with GPT2
|
|
12
|
17207
|
January 16, 2024
|
|
HF hosted interface API for a finetuned model with LoRA
|
|
2
|
711
|
January 15, 2024
|
|
How can I save a fine tuned ViT Transformer Model as a SavedModel (Tensorflow)?
|
|
0
|
191
|
January 15, 2024
|
|
Transformer model for pdf invoice field extraction
|
|
0
|
810
|
January 15, 2024
|
|
Some weights of BertModel were not initialized from the model checkpoint
|
|
6
|
11868
|
January 15, 2024
|
|
How do I get the model file after training is completed?
|
|
0
|
114
|
January 15, 2024
|
|
Training doesn't end properly but stops the machine with no error message
|
|
5
|
2381
|
January 15, 2024
|
|
Fine tune GPT2/LLaMA in seq2seq manner
|
|
2
|
1576
|
January 14, 2024
|
|
How to concatenate additional features to the last layer of Bert
|
|
6
|
2404
|
January 14, 2024
|
|
AutoTokenizer.from_pretrained('google/pegasus-cnn_dailymail') giving valueerror Couldn't instantiate the backend tokenizer
|
|
1
|
355
|
January 14, 2024
|
|
The model's parameters' names are inconsistent with the saved safetensors, which leads to loading failure
|
|
0
|
164
|
January 14, 2024
|
|
Changing the device of Pipeline
|
|
1
|
2730
|
January 13, 2024
|
|
Loading half precision Pipeline
|
|
1
|
4153
|
January 13, 2024
|
|
Transformers module - parameter count and size
|
|
0
|
1227
|
January 12, 2024
|
|
Time required to pipeline's preprocess, forward pass and postprocessing function
|
|
0
|
89
|
January 10, 2024
|
|
GPTQ model to bfloat16
|
|
0
|
436
|
January 10, 2024
|
|
AttributeError: module 'datasets.metric' has no attribute 'compute'
|
|
0
|
727
|
January 10, 2024
|
|
How to run two LLMs in series for inference?
|
|
0
|
407
|
January 10, 2024
|
|
Error when using pipeline library on offline mode
|
|
0
|
329
|
January 9, 2024
|
|
Pushing a quantized (4bit) model on the Hub
|
|
9
|
4252
|
January 8, 2024
|
|
Chat agent for multiple documents (billing invoices PDFS)
|
|
0
|
303
|
January 8, 2024
|
|
Data collator issue: ValueError: You should supply an encoding or a list of encodings to this method that includes input_ids, but you provided []
|
|
0
|
347
|
January 8, 2024
|
|
Vocabulary count mismatch when loading the previously created tokenizer
|
|
0
|
168
|
January 8, 2024
|
|
Rewrite trainer's save_model method get unexpected pytorch_model.bin file
|
|
0
|
407
|
January 8, 2024
|
|
How to clone model ForSequenceClassification
|
|
3
|
1126
|
January 8, 2024
|
|
Are there any smart loss functions for a sequence of float vectors?
|
|
0
|
149
|
January 7, 2024
|
|
How the vocabulary of BERT tokenizer is generated?
|
|
2
|
3038
|
January 6, 2024
|
|
Model (Pipeline) Parallelism in SLURM cluster
|
|
0
|
244
|
January 6, 2024
|
|
ValueError: Invalid image type. Expected either PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray, but got
|
|
6
|
4269
|
January 5, 2024
|
|
Pytorch NLP model doesnât use GPU when making inference
|
|
5
|
14236
|
January 5, 2024
|