|
LLM Zero shot-text classification - How do you answer multiple questions computationally efficiently?
|
|
0
|
1611
|
December 8, 2023
|
|
For MLM task, TextDataset or LineByLineTextDataset which one is better?
|
|
1
|
2545
|
December 8, 2023
|
|
Two questions about Segment Anything Model (SAM) in Transformers
|
|
5
|
3921
|
December 8, 2023
|
|
PEFT LORA for Text Classification?
|
|
1
|
1660
|
December 8, 2023
|
|
Saving the trained model "Trainer.save_model" error
|
|
0
|
378
|
December 7, 2023
|
|
Domain Specific Pretraining using BERT models vs other smaller architecture models
|
|
0
|
211
|
December 7, 2023
|
|
Wav2Vec2 Processor padding strategy
|
|
0
|
332
|
December 7, 2023
|
|
How to train mnist with trainer?
|
|
1
|
508
|
December 7, 2023
|
|
Limit predictions computing to single CPU core?
|
|
2
|
3205
|
December 6, 2023
|
|
Training a model with custom attention masks in each layer
|
|
0
|
676
|
December 6, 2023
|
|
Can't use multi GPU in evaluation from Trainer
|
|
3
|
971
|
December 6, 2023
|
|
When to use SFTTrainer
|
|
5
|
12449
|
December 6, 2023
|
|
How to get T5 decoded logits using TFT5ForConditionalGeneration from encoded outputs?
|
|
1
|
561
|
March 19, 2023
|
|
Asymmetry in validation step vs. autoregressive inference
|
|
0
|
180
|
December 5, 2023
|
|
CUDA Out-of-Memory Error with llama2-13b-chat Model on Multi-GPU Server
|
|
0
|
1151
|
December 5, 2023
|
|
How is the number of steps calculated in trl's SFTTrainer under multiple-GPU?
|
|
2
|
2872
|
December 5, 2023
|
|
Fine-tuning MT5 - base and make it more ChatGPT like
|
|
2
|
366
|
December 5, 2023
|
|
Getting the same embedding from llama 2 class token for any input
|
|
1
|
1306
|
December 4, 2023
|
|
Memory continuously increasing during `compute_loss()`
|
|
0
|
396
|
December 4, 2023
|
|
Form Completion
|
|
0
|
178
|
December 4, 2023
|
|
Suitable Data for Task Adaptive Pretraining (TAPT)
|
|
0
|
203
|
December 4, 2023
|
|
RoBERTa fine-tuning on a dataset of short sentences and low cardinality
|
|
0
|
736
|
December 4, 2023
|
|
Do I Need to Use zero_to_fp32.py After Training Llama with run_clm.py?
|
|
0
|
208
|
December 4, 2023
|
|
ValueError when using Roc_Auc as metric
|
|
0
|
210
|
December 3, 2023
|
|
What is possible to achieve with whisper prompting?
|
|
0
|
2996
|
December 3, 2023
|
|
InvokeEndpoint Error : Predict function Invocation Timeout
|
|
3
|
3247
|
December 1, 2023
|
|
How to Export a LLM as a .bin instead of Safetensors
|
|
0
|
954
|
December 1, 2023
|
|
Ctransformers error : Failed to create LLM 'stablelm'
|
|
1
|
860
|
November 30, 2023
|
|
Shouldn't `_flash_attn_2_enabled` be documented?
|
|
1
|
5711
|
November 30, 2023
|
|
Get all labels / entity groups available to a model
|
|
1
|
1089
|
November 30, 2023
|