AI Powered Constructions
|
|
1
|
24
|
February 14, 2025
|
Error with accelerate when Fine tuning LLaVa
|
|
3
|
27
|
February 13, 2025
|
91.7% on MMLU with Llama 3.1 405B AWQ 4-bit
|
|
0
|
38
|
February 13, 2025
|
Got rejected while acquiring access to meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8
|
|
1
|
168
|
February 13, 2025
|
Special tokens & Embeddings requries grad?
|
|
2
|
25
|
February 12, 2025
|
Masking the user prompt/question for LLaVA loss computation
|
|
2
|
106
|
February 12, 2025
|
Whisper large v3 Finetune result is all lowercased
|
|
2
|
25
|
February 11, 2025
|
Llama Model access rejection
|
|
1
|
120
|
February 11, 2025
|
Model overloaded!
|
|
2
|
96
|
February 11, 2025
|
TypeError: SentenceTransformerTrainer.compute_loss() got an unexpected keyword argument 'num_items_in_batch'
|
|
6
|
5424
|
February 10, 2025
|
Problem with installing huggingface models via jupyter terminal
|
|
0
|
9
|
February 10, 2025
|
Why is MMS-TTS-ITA model not available?
|
|
2
|
26
|
February 10, 2025
|
BEST RAG LLM for interraction with emails and files
|
|
6
|
644
|
February 10, 2025
|
Pretraining of BertForMaskedLM - What CELoss should I aim for?
|
|
0
|
13
|
February 9, 2025
|
LM STUDIO very week quality with great models
|
|
3
|
312
|
February 9, 2025
|
Does download for dataset and model through web UI button counted?
|
|
1
|
19
|
February 8, 2025
|
Which classification model to use?
|
|
0
|
19
|
February 7, 2025
|
Best model to complete piece of phrase
|
|
0
|
13
|
February 6, 2025
|
OCR Confidence score extraction for OpenGVLab/InternVL2_5-8B-MPO
|
|
2
|
42
|
February 6, 2025
|
How can I read PDFs with mPLUG/DocOwl2?
|
|
3
|
34
|
February 6, 2025
|
Fine tuning a LLM with a code
|
|
7
|
3306
|
February 5, 2025
|
How to find confidence score in QA model in the pipeline module
|
|
3
|
2546
|
February 5, 2025
|
Ask for a structured JSON object in the call to meta-llama/Llama-3.2-3B-Instruct
|
|
1
|
150
|
February 5, 2025
|
Having issues accessing tokenizer_config.json for T5
|
|
1
|
31
|
February 4, 2025
|
Sentence similarity models not capturing opposite sentences
|
|
10
|
4291
|
February 4, 2025
|
New to Docker model getting stuck
|
|
0
|
19
|
February 2, 2025
|
Download instability , disconnects
|
|
4
|
169
|
February 2, 2025
|
Finetuning Meta-Llama-3.1-8B using PEFT
|
|
4
|
2905
|
February 1, 2025
|
Prediction/Classification problem
|
|
0
|
23
|
January 30, 2025
|
Best Model for sorting a dataset based on a user question
|
|
2
|
42
|
January 30, 2025
|