|
How to add new language to NLLB tokenizer in Huggingface?
|
|
3
|
2002
|
December 6, 2025
|
|
Is it possible to remove all other language from NLLB200 except English and German?
|
|
2
|
746
|
December 6, 2025
|
|
How to use nllb1.3b model to fine-tune the English to German bidirectional translation task?
|
|
2
|
93
|
December 6, 2025
|
|
SAE for Codegemma
|
|
3
|
8
|
December 6, 2025
|
|
Obtain raw logits before decoding scaling is applied
|
|
1
|
11
|
December 5, 2025
|
|
CUDA Out Of Memory when training a DETR Object detection model with compute_metrics
|
|
4
|
156
|
December 3, 2025
|
|
How to understand the special tokens?
|
|
7
|
69
|
December 2, 2025
|
|
GETTING ERROR >> AttributeError: 'InferenceClient' object has no attribute 'post'
|
|
18
|
1991
|
November 30, 2025
|
|
Dora training taking 8x time? Why?
|
|
2
|
96
|
November 27, 2025
|
|
ContractNLI-based NDA Risk Analyzer using RoBERTa + Chunking – Looking for Feedback
|
|
6
|
38
|
November 25, 2025
|
|
Train instance segmentation model with dinov3 backbone
|
|
3
|
76
|
November 24, 2025
|
|
DistilBERT reaches 76% accuracy but still predicts “believable” for impossible/fantasy excuses — why?
|
|
3
|
29
|
November 23, 2025
|
|
Search query autocomplete from the queries I have in my data
|
|
1
|
1690
|
November 21, 2025
|
|
How to sample from the validation set when using Trainer?
|
|
5
|
1972
|
November 21, 2025
|
|
Evaluate subset of data during training
|
|
6
|
5944
|
November 21, 2025
|
|
NeuroTrace – GPT-2 Small Residual Attack & Defence Framework (IOI Task)
|
|
0
|
26
|
November 21, 2025
|
|
Passing Inputs Longer Than 512 Tokens After Pretraining a T5 Model: Is It Safe?
|
|
3
|
52
|
November 20, 2025
|
|
[LLaVA-1.5] Validating Logic for Token-Level KV Cache Extraction
|
|
3
|
21
|
November 20, 2025
|
|
Evalutation of expert router logits simultanous to generation
|
|
4
|
50
|
November 19, 2025
|
|
AetherMind-KD-Student (184M) Compact, fast, and robust NLI model distilled from DeBERTa-v3
|
|
2
|
15
|
November 15, 2025
|
|
Fine-tuning a custom module but do not use LoRA
|
|
1
|
43
|
November 14, 2025
|
|
Inconsistent output between flash attention and eager
|
|
3
|
82
|
November 14, 2025
|
|
Num_return_sequences > num_beams
|
|
3
|
17
|
November 13, 2025
|
|
Debugging inf/NaN Loss in Multi-Process Optuna/PyTorch Lightning HPO in Colab
|
|
3
|
40
|
November 13, 2025
|
|
Why does using `TextIteratorStreamer` result in so many empty outputs?
|
|
6
|
43
|
November 11, 2025
|
|
Creating language model only Lora Config
|
|
3
|
67
|
November 10, 2025
|
|
IndexError: index -1 is out of bounds for dimension 0 with size 0
|
|
3
|
48
|
November 7, 2025
|
|
How to use Qwen3-VL generate() with num_return_sequences > 1?
|
|
3
|
43
|
November 6, 2025
|
|
How can I get a list of word segmentation results for non-English string?
|
|
14
|
54
|
November 6, 2025
|
|
PEFT with SFTTrainer unexpected 'resume_from_checkpoint'
|
|
2
|
35
|
November 6, 2025
|