Suri: Multi-constraint instruction following for long-form text generation (EMNLP’24)
-
Updated
Oct 3, 2025 - Python
#
orpo
Here are 17 public repositories matching this topic...
Genshin Impact Character Instruction Models tuned by Lora on LLM
instructions prompt chinese npc webui llama glm characters gradio genshin genshin-impact game-characters llm chatglm llama2 chinese-llama chatglm3 llama2zh chinese-llama2 orpo
-
Updated
Jun 3, 2024 - Python
Advanced LLM fine-tuning techniques: SFT (LoRA, QLoRA, DoRA, P-/Prefix-Tuning), GRPO, DPO, ORPO, KTO & PPO; composable correctness/format rewards + LLM-as-a-Judge evals (DeepEval, Evidently AI) across math, multi-hop, medical & general QA on Llama 3, Mistral, Phi-4, Gemma & Qwen3. Built on TRL, PEFT & Unsloth.
-
Updated
May 9, 2026 - Python
Lightweight preference optimization for LLMs using LoRA and ORPO
-
Updated
Oct 9, 2025 - Python
Creating a GPT-2-Based Chatbot with Human Preferences
natural-language-processing chatbot pytorch language-model gpt-2 huggingface pytorch-lightning langchain instruction-tuning preference-alignment orpo
-
Updated
May 9, 2025 - Jupyter Notebook
Preference optimization framework for text classification (DPO/ORPO/KTO), with SFT, encoder, and XGBoost baselines plus unified run pipeline and reproducible outputs.
nlp machine-learning text-classification xgboost lora peft dpo kto tranformers qlora llm-fine-tuning orpo preference-optimization
-
Updated
Apr 4, 2026 - Python
This comprehensive technical guide, developed at the request of OnlyFans founder, demonstrates advanced AI model fine-tuning methodologies to transform Qwen2-72b into a Jessica Rabbit personality emulation using cutting-edge QLoRA and ORPO techniques.
reinforcement-learning ai reinforcement-learning-algorithms fine-tuning llm-training finetuning-llms orpo
-
Updated
Jun 30, 2025
Span-cited English investor memos from Japanese 有価証券報告書, produced by a 14B nekomata-qfin fine-tune on a single AMD Instinct MI300X.
nlp amd multi-agent rocm fine-tuning structured-extraction huggingface edinet instinct llm qlora qwen gguf langgraph orpo mi300x japanese-finance yuho investor-memos
-
Updated
May 13, 2026 - Python
End-to-end LLM preference learning pipeline: training, evaluation, and comparison of DPO, ORPO, KTO, and RLHF with 4-bit quantization, LoRA, and memory-efficient training on a single 8GB GPU.
-
Updated
Feb 11, 2026 - Python
Korean 3B LLM (pure Transformer) pretrained from scratch on 8× NVIDIA B200 GPUs with SFT + ORPO alignment
-
Updated
Mar 26, 2026 - Python
Improve this page
Add a description, image, and links to the orpo topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the orpo topic, visit your repo's landing page and select "manage topics."