| 1. |
QLoRA: Efficient Finetuning of Quantized LLMs (arxiv.org) |
|
315 points by Garcia98 on May 24, 2023 | hide | past | pdf | 107 comments
|
|
| 2. |
VanillaNet: The power of minimalism in deep learning (arxiv.org) |
|
33 points by pizza on May 24, 2023 | hide | past | pdf | 5 comments
|
|
| 3. |
High-Quality Video Reconstruction from Brain Activity (arxiv.org) |
|
18 points by kevinventullo on May 24, 2023 | hide | past | pdf | 3 comments
|
|
| 4. |
Meta AI Megabyte: Predicting Million-Byte Sequences with Multiscale Transformers (arxiv.org) |
|
5 points by ftxbro on May 24, 2023 | hide | past | pdf | 3 comments
|
|
| 5. |
Google researchers: non-editable LLMs can be modified by chatting, no finetuning (arxiv.org) |
|
4 points by eliomattia on May 24, 2023 | hide | past | pdf | discuss
|
|
| 6. |
Generative AI for Document Understanding (arxiv.org) |
|
3 points by yujian on May 24, 2023 | hide | past | pdf | discuss
|
|
| 7. |
QLoRA: Efficient Finetuning of Quantized LLMs (arxiv.org) |
|
3 points by MacsHeadroom on May 24, 2023 | hide | past | pdf | 1 comment
|
|
| 8. |
Sophia: A Scalable Stochastic Second-Order Optimizer (arxiv.org) |
|
2 points by kelseyfrog on May 24, 2023 | hide | past | pdf | discuss
|
|
| 9. |
Goat: Fine-Tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks (arxiv.org) |
|
2 points by malshe on May 24, 2023 | hide | past | pdf | 1 comment
|
|
| 10. |
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling (arxiv.org) |
|
1 point by ftxbro on May 24, 2023 | hide | past | pdf | discuss
|
|
| 11. |
Putting People in Their Place: Affordance-Aware Human Insertion into Scenes (arxiv.org) |
|
1 point by rntn on May 24, 2023 | hide | past | pdf | discuss
|
|
| 12. |
Billion-scale similarity search with GPUs (2017) (arxiv.org) |
|
1 point by opisthenar84 on May 24, 2023 | hide | past | pdf | discuss
|
|
| 13. |
Why Is the Winner the Best? (arxiv.org) |
|
1 point by sytelus on May 24, 2023 | hide | past | pdf | 1 comment
|
|
