reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step
- 5.9k
- Jupyter Notebook
- Apache-2.0
- 3 wk ago
(ACL 2025 Main) Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
Repo VILA-Lab/DRAG, read from GitHub 1 min ago. VILA-Lab has not joined Take My Repo.
VILA-Lab/DRAG is a public repo on GitHub by VILA-Lab. (ACL 2025 Main) Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation. It declares no license on GitHub. Public does not mean open source: without a license, nobody is granted the right to reuse it. It is written mainly in Python, has 36 stars and last changed on 2025-08-23. Nobody has reviewed it on Take My Repo yet, which says nothing about its quality. Read from GitHub on 2026-11-22.
VILA-Lab/DRAG is a public repo on GitHub by VILA-Lab. (ACL 2025 Main) Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation.
It declares no license on GitHub. Public does not mean open source: without a license, nobody is granted the right to reuse it.
Its maker has not tagged a system, so it is unknown here. Its README says what it needs.
Open "Take it" on its page: Take My Repo writes an install plan for your machine and hands it to your AI agent (Claude Code, Codex or Cursor), which asks you before each step. Take My Repo has not tested it on any machine.
Its last change on GitHub was on 2025-08-23. GitHub counts 1 open issue and pull requests. Take My Repo does not judge from that whether it is maintained.
Nobody has reviewed it on Take My Repo yet, which says nothing about its quality.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A unified inference and post-training framework for accelerated video generation.