Views
No views yet
bitsandbytestorch.float16"nf4" (Nonlinear)q_proj, v_projCAUSAL_LMpaged_adamw_8bitfp16)wikitext-2-raw-v1
DistributedDataParallel1# Load model directly
2from transformers import AutoTokenizer, AutoModelForCausalLM
3
4tokenizer = AutoTokenizer.from_pretrained("diabolic6045/ELN-Llama-1B")
5model = AutoModelForCausalLM.from_pretrained("diabolic6045/ELN-Llama-1B")1@misc{eln2024,
2 title={Evolution Learning Network (ELN): Combining QLoRA and Genetic Algorithms for LLM Optimization},
3 year={2024},
4 howpublished={\url{https://github.com/diabolic6045/ELN-llama-1B-adapter}}
5}1@article{dettmers2023qlora,
2 title={QLoRA: Efficient Finetuning of Quantized LLMs},
3 author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
4 journal={arXiv preprint arXiv:2305.14314},
5 year={2023}
6}
7
8@article{touvron2023llama,
9 title={Llama: Open and Efficient Foundation Language Models},
10 author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
11 journal={arXiv preprint arXiv:2302.13971},
12 year={2023}
13}
14
15@article{such2017deep,
16 title={Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning},
17 author={Such, Felipe Petroski and Madhavan, Vashisht and Conti, Edoardo and Lehman, Joel and Stanley, Kenneth O and Clune, Jeff},
18 journal={arXiv preprint arXiv:1712.06567},
19 year={2017}
20}
21
22@article{real2019regularized,
23 title={Regularized Evolution for Image Classifier Architecture Search},
24 author={Real, Esteban and Aggarwal, Alok and Huang, Yanping and Le, Quoc V},
25 journal={Proceedings of the AAAI Conference on Artificial Intelligence},
26 volume={33},
27 number={01},
28 pages={4780--4789},
29 year={2019}
30}