Merry CHRISTmas HN! Got a super awesome CHRISTmas gift - this Kosmos run is probably saying that I found a "“Parsimonious Multi-Module Multi-Omics Stacked Classifier for Neonatal Hypothermia Neuroprotection” https://platform.edisonscientific.com/kosmos/ef0a71d0-ca4d-4...
This is so good! I've been looking for a tool that will simulate the "listen to the Spiderman movie 50x" experiment https://www.youtube.com/watch?v=eliB_y0fmSk and this site can do it!
hello @ihid - would love to support Exercism through the Insiders program as your site is great resource for developer education! Is there a way you can provide PPP (Purhasing Power Parity) pricing for people outside of the U.S. and Europe? For example if you use this PPP calculator https://ppp.jackmcdade.com/ and compute PPP pricing for the Philippines, $10/month feels more like $20.88. If you want to recalibrate it, the PPP Pricing would be P4.79. Thanks in advance!
What if they revise and re-issue the video based on the comments?
The alternate titles suggested are also interesting:
“ A good wording could be:
Почему я обратился в ЦРУ
Почему я вышел на ЦРУ
Почему я начал работать с ЦРУ
Почему я написал ЦРУ
Почему я пошел к ЦРУ (not "в ЦРУ", as the latter is for cadets who start their work for the agency)
or even Почему я выбрал ЦРУ”
From Google translate:
“ A good wording could be:
Why I turned to the CIA
Why did I contact the CIA?
Why I started working with the CIA
Why did I write to the CIA
Why did I go to the CIA (not ‘to the CIA’, as the latter is for cadets who start their work for the agency)
or even Why I chose the CIA”
"LoftQ aims to solve the problem of the discrepancy between the quantized and full-precision model in the context of quantization and LoRA fine-tuning for Large Language Models (LLMs). By simultaneously quantizing an LLM and finding a proper low-rank initialization for LoRA fine-tuning, LoftQ significantly enhances generalization in downstream tasks."
"Based on the abstract, LoftQ aims to solve the performance gap observed when applying both quantization and LoRA fine-tuning to a pre-trained Large Language Model (LLM).
Here's a breakdown of the problem and LoftQ's approach:
Problem:
Quantization: Reduces the precision of model weights to save memory and computation, but can lower accuracy.
LoRA fine-tuning: Improves accuracy on specific tasks by adding a low-rank adapter, but can struggle with quantized models.
Combined approach: Applying both quantization and LoRA fine-tuning often leads to a performance gap compared to full fine-tuning.
LoftQ's solution:
Simultaneous quantization and LoRA initialization: LoftQ proposes a novel framework that quantizes the LLM while also finding a suitable low-rank initialization for LoRA. This helps bridge the gap between the quantized and full-precision model.
Improved generalization: This approach improves the model's ability to generalize well on downstream tasks, especially in challenging memory-constrained settings.
Evaluation and results:
LoftQ is tested on various NLP tasks like question answering and summarization.
It outperforms existing quantization methods, particularly in low-precision scenarios like 2-bit and 2/4-bit mixed precision.
Overall, LoftQ tackles the challenge of combining quantization and LoRA fine-tuning for LLMs, leading to better performance and efficiency, especially in resource-limited environments."