|
Enabling Flash Attention 2
|
|
2
|
6170
|
July 3, 2024
|
|
Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length. (Paligemma)
|
|
2
|
1479
|
July 3, 2024
|
|
Can't Import TFBertModel
|
|
0
|
135
|
July 3, 2024
|
|
Document Similarity of long documents e.g. legal contracts
|
|
6
|
8906
|
July 2, 2024
|
|
Loading ViT Adapter Model with Classification Head
|
|
1
|
888
|
July 2, 2024
|
|
Why is the following condition checked after obtaining `outputs`?
|
|
0
|
79
|
July 2, 2024
|
|
Using hyperparameter-search in Trainer
|
|
101
|
38304
|
July 2, 2024
|
|
Trainer doesn't get to compute_metrics after upgrading to v4.32
|
|
4
|
1482
|
July 2, 2024
|
|
Size mismatch error in PEFT fine tuned model
|
|
4
|
1560
|
July 2, 2024
|
|
Download fails for llava-hf/bakLlava-v1-hf
|
|
0
|
239
|
July 1, 2024
|
|
Issue with Loading BLIP Processor and Model for Image Captioning
|
|
0
|
288
|
June 30, 2024
|
|
Constrained Beam Search - Very Slow
|
|
1
|
807
|
June 30, 2024
|
|
Doubts about attention masks
|
|
1
|
613
|
June 29, 2024
|
|
Issue with Running Hugging Face Pipeline via SSH on Ubuntu in Mainland China
|
|
0
|
122
|
June 29, 2024
|
|
`merge_and_unload` moves some layers in CPU
|
|
0
|
103
|
June 29, 2024
|
|
Can't compile project to .exe, that uses transformers (Windows 10)
|
|
4
|
1684
|
June 29, 2024
|
|
ComfyUI requires Hub 0.23.0
|
|
0
|
377
|
June 28, 2024
|
|
Cannot pass a kwargs into `torch.onnx.export` arguments
|
|
0
|
128
|
June 28, 2024
|
|
SetFit - SageMaker Deployment
|
|
0
|
80
|
June 28, 2024
|
|
Mathematic Mistakes
|
|
1
|
128
|
June 28, 2024
|
|
How data should be structured to Fine-Tune a CausalLM
|
|
1
|
662
|
June 28, 2024
|
|
Continual Training on my own checkpoint
|
|
1
|
84
|
June 27, 2024
|
|
Tensor not on the same device after using BitsandBytesConfig
|
|
0
|
106
|
June 27, 2024
|
|
How to combine ReFT Modules to Base Model?
|
|
0
|
102
|
June 26, 2024
|
|
Save only best model in Trainer
|
|
31
|
86142
|
June 25, 2024
|
|
Hugging face truncated output via langchain
|
|
0
|
111
|
June 25, 2024
|
|
How to obtain a good sentence embedding?
|
|
2
|
2351
|
June 25, 2024
|
|
Finetuning existing Lora Adapters gives "Attempting to unscale FP16 gradients" - Error
|
|
2
|
1412
|
June 25, 2024
|
|
How to export bert tokenizer to onnx?
|
|
0
|
157
|
June 25, 2024
|
|
2 possible bugs for adding new tokens to T5
|
|
3
|
1326
|
June 25, 2024
|