Implementation of Direct Preference Optimization (DPO) for fine-tuning large language models, including training pipelines, dataset handling, and experiment configurations for preference-based model alignment.
☆30Jul 2, 2024Updated last year
Alternatives and similar repositories for DPO_LLM_finetuning
Users that are interested in DPO_LLM_finetuning are comparing it to the libraries listed below
Sorting:
- Finds stocks likely to outperform, but always outputs “why”☆29Jan 29, 2026Updated last month
- A complete pipeline for classifying news into financial events and forecasting their impact on stock returns using FinBERT and regression…☆30Jan 30, 2026Updated last month
- Open-source UX/Product Design Toolkit - A comprehensive design workflow solution from research to handover☆189Feb 24, 2026Updated last week
- ☆30Jan 19, 2026Updated last month
- AI-powered companion for Homebox. Snap photos and let AI auto-identify and catalog items into your inventory, then use the AI Chat to org…☆242Feb 24, 2026Updated last week
- A private, local meeting notes assistant. Capture audio, transcribe locally with Whisper, and generate AI-powered summaries — all on your…☆189Mar 1, 2026Updated last week
- A complete, minimal-yet-practical PyTorch Transformer (decoder-only) built from scratch with a char-level tokenizer, training pipeline, c…☆27Jan 31, 2026Updated last month
- This framework provides a modular and extensible architecture for learning and deploying robot manipulation policies.☆27Jan 20, 2026Updated last month
- Agent Discovery & Work Exchange Platform☆356Feb 27, 2026Updated last week
- The Ark framework.☆587Feb 27, 2026Updated last week
- AI Development Governance - Stop babysitting your AI agent. Login → Tier → Interview → Build.☆180Updated this week
- Open-source RAG platform with multi-LLM support. Build AI agents that connect to your data, tools, and workflows - no code required.☆333Mar 3, 2026Updated last week
- Production-Grade ML System for Automated Unit of Measure Error Detection | 88-92% Accuracy | 94% Autonomy | KNIME Workflow☆865Oct 21, 2025Updated 4 months ago
- BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx☆1,353Updated this week