|
valueError: Supplied state dict for layers does not contain `bitsandbytes__*` and possibly other `quantized_stats`(when load saved quantized model)
|
|
4
|
669
|
May 30, 2025
|
|
RGBA -> RGB default background color vs padding color
|
|
1
|
6
|
May 30, 2025
|
|
Why is Static Cache latency high?
|
|
2
|
8
|
May 29, 2025
|
|
Error using Trainer with Colab notebook, anyone have a solution?
|
|
1
|
17
|
May 29, 2025
|
|
LoRA training with accelerate / deepspeed
|
|
3
|
2218
|
May 28, 2025
|
|
How does Q, K, V differ in LLM?
|
|
1
|
17
|
May 28, 2025
|
|
The effect of padding_side
|
|
13
|
14150
|
May 27, 2025
|
|
Prompt caching in pipelines
|
|
1
|
26
|
May 27, 2025
|
|
GETTING ERROR >> AttributeError: 'InferenceClient' object has no attribute 'post'
|
|
5
|
135
|
May 27, 2025
|
|
How does Llama For Sequence Classification determine what class corresponds to what label?
|
|
10
|
4747
|
May 25, 2025
|
|
Best practice for usage of Data Collator For CompletionOnlyLM in multi-turn chat
|
|
2
|
583
|
May 25, 2025
|
|
How to merge fine-tuned LLaMA-3.1-8B (via LLaMA-Factory) into a single GGUF for LM Studio?
|
|
1
|
20
|
May 25, 2025
|
|
Generate keeps increasing memory usage on ubuntu
|
|
6
|
32
|
May 25, 2025
|
|
How does Transformers Library work under the hood?
|
|
1
|
15
|
May 22, 2025
|
|
Identical Evaluation Metrics for SFT & DPO–Fine-Tuned LoRA Adapter on SeaLLMs-v3-7B
|
|
1
|
11
|
May 22, 2025
|
|
Create a weighted loss function to handle imbalance?
|
|
3
|
928
|
May 21, 2025
|
|
Incorrect total train batch size when using tp_size > 1 and deepspeed
|
|
1
|
26
|
May 20, 2025
|
|
Distributed Training w/ Trainer
|
|
10
|
8765
|
May 20, 2025
|
|
How do I load a trained checkpoint model?
|
|
1
|
24
|
May 20, 2025
|
|
Fine tuning on qwen3
|
|
2
|
206
|
May 19, 2025
|
|
TokenClassificationPipeline produce entities with "##" characters
|
|
6
|
23
|
May 19, 2025
|
|
PPO Training does not improve SFT model outputs (Metrics identical before and after PPO)
|
|
1
|
32
|
May 19, 2025
|
|
Grouping by length makes training loss oscillate and makes evaluation loss worse
|
|
1
|
217
|
May 16, 2025
|
|
Cuda out of memory in SD3
|
|
4
|
21
|
May 16, 2025
|
|
Stopiteration error
|
|
1
|
76
|
May 16, 2025
|
|
AttributeError: 'CustomQwen3Model' object has no attribute 'config'
|
|
1
|
12
|
May 16, 2025
|
|
How to freeze layers while fine-tuning?
|
|
2
|
61
|
May 16, 2025
|
|
Trainer default distributed training behaviour
|
|
2
|
14
|
May 15, 2025
|
|
What does increasing number of heads do in the Multi-head Attention?
|
|
5
|
29670
|
May 15, 2025
|
|
Does high number of output labels affect the performance of BERT and how to handle the class imbalance issue while doing multi text classification?
|
|
2
|
415
|
May 14, 2025
|