Σχεδιασμός και Υλοποίηση εξειδικευμένου chatbot για διαδικτυακές πλατφόρμες
124
[48]
Meta AI. (2024). Llama 3.1 model card: υποστηριζόμενες γλώσσες [Διαδικτυακός τόπος].
https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md
(πρόσβαση: Ιούνιος 2026).
[49]
LLM Stats. (2026). Llama 3.1 8B Instruct vs Qwen2.5 7B Instruct: σύγκριση επιδόσεων (IFEval,
MMLU-Pro κ.ά.) [Διαδικτυακός τόπος]. https://llm-stats.com/models/compare/llama-3.1-8b-
instruct-vs-qwen-2.5-7b-instruct (πρόσβαση: Ιούνιος 2026).
[50]
Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., & Steinhardt, J. (2021).
Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300.
[51]
Shieber, S. M. (1994). Lessons from a restricted Turing test. Communications of the ACM,
37(6), 70–78.
[52]
Spärck Jones, K. (1972). A statistical interpretation of term specificity and its application in
retrieval. Journal of Documentation, 28(1), 11–21.
[53]
Robertson, S. E., & Walker, S. (1994). Some simple effective approximations to the 2-Poisson
model for probabilistic weighted retrieval. In Proceedings of the 17th Annual International ACM
SIGIR Conference on Research and Development in Information Retrieval (pp. 232–241).
[54]
Hoy, M. B. (2018). Alexa, Siri, Cortana, and more: An introduction to voice assistants. Medical
Reference Services Quarterly, 37(1), 81–88.
[55]
Kaplan, J., et al. (2020). Scaling laws for neural language models. arXiv preprint
arXiv:2001.08361.
[56]
OpenAI. (2023). GPT-4 technical report. arXiv preprint arXiv:2303.08774.
[57]
Touvron, H., et al. (2023). LLaMA: Open and efficient foundation language models. arXiv
preprint arXiv:2302.13971.
[58]
Zhao, W. X., et al. (2023). A survey of large language models. arXiv preprint arXiv:2303.18223.
[59]
Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M. W., & Keutzer, K. (2021). A survey of
quantization methods for efficient neural network inference. arXiv preprint arXiv:2103.13630.
[60]
Frantar, E., Ashkboos, S., Hoefler, T., & Alistarh, D. (2022). GPTQ: Accurate post-training
quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323.
[61]
Advanced Micro Devices, Inc. (2020). “RDNA 2” Instruction Set Architecture: Reference
Guide. Technical Report, AMD. https://docs.amd.com/v/u/en-US/rdna2-shader-instruction-set-
architecture (πρόσβαση: Ιούνιος 2026).
[62]
Auffarth, B. (2023). Generative AI with LangChain. Birmingham, UK: Packt Publishing.
[63]
Zirnstein, B. (2023). Extended context for InstructGPT with LlamaIndex. Technical Report.
Hochschule für Wirtschaft und Recht Berlin.
[64]
Kwon, W. (2025). vLLM: An efficient inference engine for large language models (Doctoral
dissertation, UC Berkeley).
[65]
Academic Reference. (2026). Which quantization should I use? A unified evaluation of
llama.cpp quantization on Llama-3.1-8B-Instruct. arXiv preprint arXiv:2601.14277.