|
Ethical AI x Narrative Intervention
|
|
0
|
16
|
April 24, 2025
|
|
How to start fsdp2 when using trainer?
|
|
0
|
49
|
April 23, 2025
|
|
Saving pretrained to same directory as load
|
|
2
|
42
|
April 23, 2025
|
|
Can't perform image inference with Gemma 3 12b it qat4.0
|
|
1
|
131
|
April 23, 2025
|
|
Sample weighting in DPOTrainer
|
|
0
|
10
|
April 23, 2025
|
|
How to avoid PreTrainedTokenizerFast.decode to add space between tokens
|
|
3
|
25
|
April 22, 2025
|
|
How can I make use of GPU manually to run inference faster?
|
|
3
|
26
|
April 22, 2025
|
|
Error using deepspeed for sftconfig
|
|
1
|
25
|
April 21, 2025
|
|
AI Microsoft hackthon 4=1
|
|
0
|
8
|
April 21, 2025
|
|
Deepspeed zero3 does not work with Diffusion Models. Does anyone know how to fix this?
|
|
1
|
2137
|
April 18, 2025
|
|
Code from HF tutorial on the customization of transformer components is not working as intended
|
|
4
|
27
|
April 18, 2025
|
|
The current text generation call will exceed the model's predefined maximum length
|
|
1
|
2393
|
April 16, 2025
|
|
SSL Certificate Issue
|
|
11
|
25512
|
April 16, 2025
|
|
Push_to_hub() stucked
|
|
5
|
51
|
April 15, 2025
|
|
ValueError: Image features and image tokens do not match
|
|
2
|
931
|
April 14, 2025
|
|
[Owlv2 - image_guided_detection - embed_image_query] Why choosing the least similar box from selected ones?
|
|
5
|
604
|
April 13, 2025
|
|
How to properly load the PEFT LoRA model
|
|
4
|
6807
|
April 13, 2025
|
|
Caching image prototype embeddings for image-guided object detection using OWL-ViT
|
|
1
|
437
|
April 11, 2025
|
|
2B Model Fill Up Memory Usage on 4xA100s
|
|
1
|
71
|
April 10, 2025
|
|
How to ensure the dataset is shuffled for each epoch using Trainer and Datasets?
|
|
13
|
19172
|
April 10, 2025
|
|
Fine-tuning TrOCR on new language
|
|
4
|
2235
|
April 10, 2025
|
|
Issue with 'learn_initial_query=True' in RT-DETR: AttributeError on 'tile'
|
|
3
|
63
|
April 8, 2025
|
|
Gemma3 - shift labels to the right
|
|
3
|
44
|
April 8, 2025
|
|
Scalar Reward Model
|
|
2
|
19
|
April 8, 2025
|
|
AutoModelforCausalLM fails only on Cuda due to inf/nan/<0 tensors
|
|
4
|
131
|
April 8, 2025
|
|
Reward becomes nan when switching from full precision to fp16 for gemma3-12b-it
|
|
3
|
46
|
April 7, 2025
|
|
How to use LayoutLMv3 for Relation Extraction?
|
|
3
|
1361
|
April 7, 2025
|
|
ð Transformer's Missing Native Rosetta Stone: pareto-lang + Symbolic Residue
|
|
0
|
15
|
April 6, 2025
|
|
On Symbolic Residue: The Missing Biological Knockout Experiments in Advanced Transformer Models
|
|
0
|
130
|
April 6, 2025
|
|
How to get normal LLava-1.6 attention maps?
|
|
1
|
97
|
April 6, 2025
|