|
Transformer shifting output question
|
|
1
|
321
|
May 13, 2024
|
|
Create variation images based on small dataset
|
|
0
|
76
|
May 13, 2024
|
|
Not able to add data_collator to Trainer
|
|
1
|
477
|
May 13, 2024
|
|
How can we automatically run the script with a token included in a script
|
|
0
|
82
|
May 13, 2024
|
|
How to launch multi node training using accelerate launch
|
|
0
|
550
|
May 13, 2024
|
|
Negative KL-divergence RLHF implementation
|
|
1
|
1511
|
May 13, 2024
|
|
Looking for open source NLP projects to contribute
|
|
3
|
765
|
May 13, 2024
|
|
Index Error: Target {} is out of bounds
|
|
0
|
261
|
May 13, 2024
|
|
Load_in_8bit vs. loading 8-bit quantized model
|
|
6
|
6043
|
May 13, 2024
|
|
GPU usage increasing every loop when running inference
|
|
2
|
1040
|
May 13, 2024
|
|
Unable To Create A New Space Via API
|
|
0
|
118
|
May 13, 2024
|
|
Error loading tokenizer from local checkpoint directory
|
|
3
|
1503
|
May 13, 2024
|
|
How do you use segmentation image processor with more than 3 channel images?
|
|
1
|
291
|
May 13, 2024
|
|
Speech detection in records from SIP-telephony with G.729 codec
|
|
0
|
66
|
May 12, 2024
|
|
Convert Conv1D to nn.Linear
|
|
2
|
911
|
May 12, 2024
|
|
Simple Basic Question about the Assistants
|
|
0
|
157
|
May 12, 2024
|
|
Our new classification algorithm outperforms CatBoost, XGBoost, LightGBM on five benchmark datasets, on accuracy and response time
|
|
0
|
355
|
May 12, 2024
|
|
Difference between tokenizer and convert_tokens_to_ids
|
|
0
|
282
|
May 12, 2024
|
|
Can the parquet-converter bot handle list[str] dtypes found in a webdataset?
|
|
4
|
157
|
May 12, 2024
|
|
SFTrainer doesn't show added column
|
|
0
|
101
|
May 12, 2024
|
|
Medical QnA dataset with context
|
|
0
|
203
|
May 12, 2024
|
|
How can I keep use of the base model version for inference after fine-tuning
|
|
1
|
93
|
May 12, 2024
|
|
Error. Model cannot be quantized if a LoRA adapter has been applied to it via merge_and_unload()
|
|
0
|
279
|
May 12, 2024
|
|
Download LLM Model
|
|
4
|
10467
|
May 12, 2024
|
|
Tokenizer Saving Issues, Wrapper Issues and Push to Hub issues
|
|
3
|
1453
|
May 12, 2024
|
|
How to generate multiple text completions per prompt (like vLLM) using HuggingFace Transformers Pipeline without triggering an error?
|
|
4
|
2424
|
May 12, 2024
|
|
BartForConditionalGeneration: loss function diverges instead of converging
|
|
0
|
118
|
May 12, 2024
|
|
Beam search error
|
|
2
|
537
|
May 12, 2024
|
|
BART max_new_tokens in generate function
|
|
2
|
170
|
May 11, 2024
|
|
Exploring AI Solutions for Laptop Component Compatibility and Identification
|
|
0
|
86
|
May 11, 2024
|