What is ViTImageProcessor doing?
|
|
3
|
68
|
April 18, 2024
|
Minimal example on heavy pre-processing on different devices
|
|
0
|
20
|
April 18, 2024
|
Should i use LLama-2 for text summerization?
|
|
0
|
24
|
April 18, 2024
|
How to avoid re-decoding for multiple inputs that have shared prefixes
|
|
0
|
25
|
April 17, 2024
|
Fine Tuning A sentence transformer model with my own data
|
|
2
|
259
|
April 17, 2024
|
"share this conversation" error
|
|
0
|
24
|
April 17, 2024
|
Train MLM on my own domain and fine tune on downstream classification task
|
|
3
|
625
|
April 16, 2024
|
TRL SFT super prone to nan when using data collator
|
|
1
|
241
|
April 16, 2024
|
Fine-tuning with Different Model Heads
|
|
0
|
39
|
April 15, 2024
|
Chatbot PDF - Only local
|
|
0
|
71
|
April 15, 2024
|
Evaluation of a large image dataset
|
|
0
|
34
|
April 14, 2024
|
How to replace the weights of certain layers in a model
|
|
0
|
32
|
April 14, 2024
|
How do I fix this error when training in TRL with QLora and PPO?
|
|
0
|
68
|
April 13, 2024
|
Requirements Llama2
|
|
0
|
49
|
April 13, 2024
|
Using the Trainer API with a timm model
|
|
0
|
45
|
April 12, 2024
|
Qlora - 8 bit quantization using bitsandbytes gives error for owl-vit model
|
|
1
|
214
|
April 12, 2024
|
🔬 Exploring Reinforcement Learning for Molecule Generation with GPT-Based Models; Loss Fluctuations
|
|
2
|
74
|
April 11, 2024
|
The model did not return a loss from the inputs, only the following keys: logits. For reference, the inputs it received are input_values
|
|
16
|
22736
|
April 10, 2024
|
Text spotting on wide images
|
|
0
|
48
|
April 10, 2024
|
Gpt-j gpt4all thread and anomaly detection
|
|
0
|
56
|
April 9, 2024
|
Baffling performance issue on most NVidia GPUs with simple transformers + pytorch code
|
|
5
|
2913
|
April 9, 2024
|
How to obtain latent vectors from model with transformers
|
|
1
|
94
|
April 9, 2024
|
Unpacking transformer's trainer.eval() to see every example's output, loss
|
|
4
|
88
|
April 9, 2024
|
Weighed Loss Function in Regression Task
|
|
1
|
448
|
April 6, 2024
|
Chat bot for Question and answer in csv ,all open source models
|
|
0
|
84
|
April 4, 2024
|
Weight and shape different than the number of channels in input
|
|
0
|
79
|
April 4, 2024
|
Cuda out of memory error
|
|
8
|
26125
|
April 4, 2024
|
Inference after QLoRA fine-tuning
|
|
6
|
2868
|
April 4, 2024
|
LayoutLM data format for bounding box classification
|
|
0
|
81
|
April 3, 2024
|
Efficient Conditional Selection of Data Set Rows
|
|
0
|
68
|
April 3, 2024
|