|
UnboundLocalError: cannot access local variable 'input_ids' where it is not associated with a value
|
|
1
|
166
|
October 9, 2024
|
|
Index Error while Summarizing splitted Documents
|
|
7
|
75
|
October 9, 2024
|
|
Do I need to dequantization before merging the qlora
|
|
10
|
734
|
October 9, 2024
|
|
How to do model.generate() in evaluation steps with Trainer + FSDP?
|
|
4
|
2997
|
October 8, 2024
|
|
How can I obtain the logits via model.generate()?
|
|
2
|
3052
|
October 8, 2024
|
|
Fine Tune with/without LORA
|
|
1
|
263
|
October 7, 2024
|
|
Not getting substantial training time improvement with LORA - is this expected?
|
|
1
|
687
|
October 7, 2024
|
|
BitsAndBytes With DDP
|
|
3
|
98
|
October 7, 2024
|
|
How to Configure LLaMA-3:8B on HuggingFace to Generate Responses Similar to Ollama?
|
|
7
|
1661
|
October 7, 2024
|
|
Number of tokens (2331) exceeded maximum context length (512) error.Even when model supports 8k Context length
|
|
8
|
15441
|
October 6, 2024
|
|
Model max length not set. Default value
|
|
1
|
639
|
October 6, 2024
|
|
Having trouble loading a fine-tuned PEFT model (CodeLlama-13b-Instruct-hf base)
|
|
2
|
4423
|
October 6, 2024
|
|
Google Document AI Alternative
|
|
3
|
1030
|
October 6, 2024
|
|
Custom 4D attention masks in training OOM
|
|
7
|
523
|
October 6, 2024
|
|
The following columns in the training set don't have a corresponding argument
|
|
2
|
8145
|
October 5, 2024
|
|
Cannot download ViTModel
|
|
3
|
212
|
October 4, 2024
|
|
Tracking resource utilization per process with callbacks
|
|
1
|
38
|
October 4, 2024
|
|
Asynchronous Data Pre-Processing for Multi Modal Models
|
|
5
|
569
|
October 4, 2024
|
|
Not able to download Model not showing progress bar when downloading using from_pretrained
|
|
7
|
930
|
October 4, 2024
|
|
Constrained decoding based on position
|
|
0
|
39
|
October 4, 2024
|
|
Token classification metric
|
|
0
|
27
|
October 3, 2024
|
|
Ensuring Consistency in Results: A Focus on Reproducibility BERT
|
|
2
|
95
|
October 3, 2024
|
|
ValueError: Input sequence length (100) doesn't match model configuration (32)
|
|
9
|
111
|
October 3, 2024
|
|
How to solve factual inconsistency when fine tuning
|
|
10
|
71
|
October 3, 2024
|
|
How to extend model.generate() to accept additional parameters to be used by the forward of Llama
|
|
0
|
97
|
October 2, 2024
|
|
T5-small for multiple ICD-10 codes from cause of death
|
|
0
|
17
|
October 2, 2024
|
|
Incremental learning for image captioning
|
|
3
|
96
|
October 1, 2024
|
|
Poor results (val_loss) on fine-tuning the NLLB-200-600M with LoRA for French-Wolof translation
|
|
3
|
342
|
October 1, 2024
|
|
Llama 2 repeats its prompt as output without answering the prompt
|
|
3
|
3741
|
September 30, 2024
|
|
RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasGemmEx( handle, opa, opb, m, n, k, &falpha, a, CUDA_R_16F, lda, b, CUDA_R_16F, ldb, &fbeta, c, CUDA_R_16F, ldc, CUDA_R_32F, CUBLAS_GEMM_DEFAULT_TENSOR_OP)
|
|
11
|
4078
|
October 1, 2024
|