Sources & Further Reading
iSources checked: September 2026
Sources reviewed in September 2026: links checked for availability and extended with references for the current state. As the AI landscape evolves quickly, some details may have changed since then.
Sources
-
Hu, E. J. et al. (2021). LoRA: Low-Rank Adaptation of Large Language Models. arXiv:2106.09685. https://arxiv.org/abs/2106.09685
-
Dettmers, T. et al. (2023). QLoRA: Efficient Finetuning of Quantized Language Models. arXiv:2305.14314. https://arxiv.org/abs/2305.14314
-
Meta (2025). Llama 4 Model Card. https://github.com/meta-llama/llama-models/blob/main/models/llama4/MODEL_CARD.md
-
Mistral AI (2025). Mistral 3 Announcement. https://mistral.ai/news/
-
Hugging Face (2025). PEFT – Parameter-Efficient Fine-Tuning Library. https://huggingface.co/docs/peft/
-
DeepSeek (2026). DeepSeek V4 – model cards and API documentation. V4-Pro and V4-Flash, open weights under MIT license, 1M token context. https://api-docs.deepseek.com/ · https://huggingface.co/deepseek-ai
-
Alibaba (2026). Qwen 3.8 model family. Open weights under Apache 2.0, 262K token context, native image and video input. https://qwen.ai/ · https://huggingface.co/Qwen
Further Reading
Fine-Tuning Tools
- Unsloth: Fast fine-tuning with reduced memory requirements. https://github.com/unslothai/unsloth
- Axolotl: User-friendly framework supporting various fine-tuning methods. https://github.com/axolotl-ai-cloud/axolotl
- Hugging Face TRL: Transformer Reinforcement Learning library for RLHF and DPO. https://huggingface.co/docs/trl/
Models & Benchmarks
- Hugging Face Open LLM Leaderboard: Ranking of open-source language models. https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
- LMSYS Chatbot Arena: Community-driven comparison of language models. https://arena.ai/